Please note: In the following program the listed affiliation for each paper refers only to the first author of that paper and is not necessarily the affiliation of any other authors.
Tuesday 1 December, 1998
Opening Ceremony
Time & Place: 0930 - 1000, Antechinus Room
Chair: Bruce Millar
Plenary Session
Tu2A - Keynote Speech 1
Title: Cochlear Implants in the Second and Third Millennia
Speaker: Graeme Clark
University of Melbourne, AUSTRALIA
Time & Place: 1000 - 1100, Antechinus Room
Chair: Robert Dale
Tu3A - Text-To-Speech Synthesis 1
Time & Place: 1130 - 1230, Antechinus Room
Chair: Shuichi Itahashi
1130
Tu3A1
.
Unsupervised training of phone duration and energy models for
text-to-speech synthesis
Bagshaw, P C
France Telecom, CNET, FRANCE
1145
Tu3A2
Improved Duration Modeling of English Phonemes Using a Root
Sinusoidal Transformation
Bellegarda, J Silverman, K
Apple Computer, USA
1200
Tu3A3
Efficient Adaptation of TTS Duration Model to New Speakers
Shih, C Gu, W van Santen, J P H
Bell Labs - Lucent Technologies, USA
1215
Tu3A4
Duration Modeling for HMM-Based Speech Synthesis
Yoshimura, T Tokuda, K Masuko, T Kobayashi, T Kitamura, T
Nagoya Institute of Technology, JAPAN
Tu3B - Spoken Language Models and Dialog 1
Time & Place: 1130 - 1230, Bandicoot Room
Chair: Greg Aist
1130
Tu3B1
An educational dialogue system with a user controllable dialogue
manager
Gustafson, J Elmberg, P Carlson, R Jönsson, A
Center for Speech Technology, TMH-KTH, SWEDEN
1145
Tu3B2
End-user driven dialogue system design: The REWARD experience
Failenschmid, K Thornton, J H S
Vocalis Ltd, UNITED KINGDOM
1200
Tu3B3
The Design of a Multi-domain Mandarin Chinese Spoken Dialogue
System
Lin, Y-C Chiang, T-H Wang, H-M Peng, C-M Chang, C-H
Industrial Technology Research Institute, TAIWAN R.O.C.
1215
Tu3B4
An Integrated Dialogue System for the Automation of Call Centre
Services
Georgila, K Tsopanoglou, A Fakotakis, N Kokkinakis, G
University of Patras, GREECE
Tu3C - Prosody and Emotion 1
Time & Place: 1130 - 1230, Currawong Room
Chair: Phil Rose
1130
Tu3C1
Tones of a Tridialectal: Acoustic and Perceptual data on Ten Linguistic
Tonetic contrasts between Lao, Nyo and Standard Thai
Rose, P
Australian National University, AUSTRALIA
1145
Tu3C2
Tone Sandhi between Complex Tones in a Seven-Tone Southern Thai
Dialect
Thompson, N G I
Australian National University, AUSTRALIA
1200
Tu3C3
The Acoustic and Perceptual Features of Tone in the Tibeto-Burman
Language Ao Naga
Coupe, A R
The Australian National University, AUSTRALIA
1215
Tu3C4
The Differential Status of Semivowels in the Acoustic Phonetic
Realisation of Tone
Rose, P
Australian National University, AUSTRALIA
Tu3D - Hidden Markov Model Techniques 1
Time & Place: 1130 - 1230, Dingo Room
Chair: Roberto Togneri
1130
Tu3D1
Nonreciprocal Data Sharing in Estimating HMM parameters
Luo, X Jelinek, F
Johns Hopkins University, USA
1145
Tu3D2
Data-Driven Extensions to HMM Statistical Dependencies
Bilmes, J A
U.C. Berkeley / ICSI, USA
1200
Tu3D3
Use of High-Level Linguistic Constraints for constructing Feature Based
Phonological Model in Speech Recognition
Sun, J Deng, L
University of Waterloo, CANADA
Tu3P - Speaker and Language Recognition 1
Time & Place: 1130 - 1430, Platypus Room
Chair: Kay Berkling
Tu3P1
Sub-Band Based Speaker Verification Using Dynamic Recombination
Weights
Sivakumaran, P Ariyaeeinia, A M Hewitt, J
University of Hertfordshire, UNITED KINGDOM
Tu3P2
Measuring the Dynamic Encoding of Speaker Identity and Dialect in
Prosodic Parameters
Barlow, M Wagner, M
Australian Defence Force Academy, AUSTRALIA
Tu3P3
German Regional Variants - A Problem for Automatic Speech
Recognition?
Beringer, N Schiel, F Regel-Brietzmann, P
University of Munich, GERMANY
Tu3P4
Improving Accent Identification through Knowledge of English Syllable
Structure
Berkling, K Vonwiller, J Cleirigh, C Zissman, M
MIT Lincoln Laboratory, USA
Tu3P5
Multi-dimensional Scaling of Listener Responses to Complex Auditory
stimuli
Bond, Z S Fucci, D Stockmal, V McColl, D
Ohio University, USA
Tu3P6
Same Talker, Different Language
Stockmal, V Moates, D Bond, Z
Ohio University, USA
Tu3P7
The Impact of Regional Variety upon Specific Word Categories in
Spontaneous German
Burger, S Oppermann, D
University of Munich, GERMANY
Tu3P8
Speech pre-processing against intentional imposture in speaker
recognition
Genoud, D Chollet, G
IDIAP, SWITZERLAND
Tu3P9
A Comparison of Two Unsupervised Approaches to Accent Identification
Lincoln, M Cox, S Ringland, S
University of East Anglia, UNITED KINGDOM
Tu3P10
The Influence of Accents in Australian English Vowels and their Relation
to Articulatory Tract Parameters
Dersch, D Cleirigh, C Vonwiller, J
Sydney University /
APPEN Speech Technology, AUSTRALIA
Tu3P11
Automatic language recognition using high-order HMMs
du Preez, J A Weber, D M
University of Stellenbosch, SOUTH AFRICA
Tu3P12
Speaker Recognition Using Residual Signal of Linear and Nonlinear
Prediction Models
Faundez-Zanuy, M Rodriguez-Porcheron, D
Escola Universitaria Politecnica De Mataro, SPAIN
Tu3P13
An Implementation and Evaluation of an On-line speaker Verification
System for Field Trials
Gu, Y Thomas, T
Vocalis Ltd, UNITED KINGDOM
Tu3P14
Speaker Verification on the POLYCOST database using frequency
filtered spectral energies
Hernando, J Nadeu, C
Polytechnical University of Catalonia, SPAIN
Tu3P15
A High-Performance Text-Independent Speaker Identification System
Based On BCDM
Jin, Q Si, L Hu, Q
Tsinghua University, P.R. CHINA
Tu3P16
Representation of Voice Quality Features Associated with Talker
Individuality
Kido, H Kasuya, H
Utsunomiya University, JAPAN
Tu3P17
Candidate Selection Based on Significance Testing and its Use in
Normalisation and Scoring
Kim, J Jang, G Yun, S Oh, Y
Advanced Institute of Science and Technology, KOREA
Tu3P18
Japanese Forensic Phonetics:Non-contemporaneous within-speaker
variation in Natural and Read-out Speech
Kinoshita, Y
The Australian National University, AUSTRALIA
Tu3P19
Statistical Modeling of Pronunciation and Production Variations for
Speech Recognition
Korkmazskiy, F E Juang B-H
Lucent Technologies Bell Laboratories, USA
Tu3P20
Dialect Maps and Dialect Research; Useful Tools for Automatic Speech
Recognition?
Foldvik, A K Kvale, K
Telenor R&D, NORWAY
Tu3P21
Text Independent Speaker Recognition Using Micro-Prosody
Kyung, Y J Lee, H S
Korea Advanced Institute of Science and Technology, KOREA
Tu3P22
Speaker Verification Using Fundamental Frequency
Cheng, Y Leung, H C
Chinese University of Hong Kong, HONG KONG
Tu3P23
On Optimum Normalization Method Used for Speaker Verification
Liu, W Isobe, T Mukawa, N
NTT Data Corporation, JAPAN
Tu3P24
Recurrent Substrings and Data Fusion for Language Recognition
Lloyd-Thomas, H Parris, E S Wright, J H
Ensigma Ltd, UNITED KINGDOM
Tu3P25
Text-Independent Speaker Recognition using Multiple Information
Sources
Markov, K Nakagawa, S
Toyohashi University of Technology, JAPAN
Tu3P26
Discriminative Training of GMM using a Modified EM Algorithm for
Speaker Recognition
Markov, K Nakagawa, S
Toyohashi University of Technology, JAPAN
Tu3P27
Language Identification Incorporating Lexical Information
Matrouf, D Adda-Decker, M Lamel, L Gauvain, J-L
LIMSI-CNRS, FRANCE
Tu3P28
A VQ based Speaker Recognition System Based in Histogram Distances.
Text Independent and for Noisy Environments
Monte, E Arqué, R Miró, X
Polytechnical University of Catalonia, SPAIN
Tu3P29
Spanish Dialects: Phonetic Transcription
Moreno, A Marino, J B
Polytechnical University of Catalonia, SPAIN
Tu3P30
Acoustic analysis of Japanese English prosody: Comparison between
Fukushima dialect speakers and Tokyo dialect speakers in declarative
sentences and yes-no questions
Muramatsu, M
Fukushima Medical University, JAPAN
Tu3P31
A Context-Dependent Approach for Speaker Verification Using
Sequential Decision
Noda, H Harada, K Kawaguchi, E Sawai, H
Kyushu Institute of Technology, JAPAN
Tu3P32
Quantitative Influence of Speech Variability Factors for Automatic
Speaker Verification in Forensic Tasks
Ortega-Garcia, J Cruz-Llanas, S Gonzalez-Rodriguez, J
Universidad Politecnica Madrid, SPAIN
Tu3P33
Creating Hidden Markov Models for Fast Speech
Pfau, T Ruske, G
Technical University of Munich, GERMANY
Tu3P34
Speaker Identification using Relaxation Labeling
Pham, T D Wagner, M
University of Canberra, AUSTRALIA
Tu3P35
A Novel Technique for the Combination of Utterance and Speaker
Verification Systems in a Text-dependent Speaker Verification Task
Rodriguez-Linares, L Garcia-Mateo, C
University of Vigo, SPAIN
Tu3P36
A Forensic Phonetic Investigation into Non-contemporaneous Variation
in the F-pattern of Similar-sounding Speakers
Rose, P
Australian National University, AUSTRALIA
Tu3P37
Human vs. Machine Speaker Identification with Telephone Speech
Schmidt-Nielsen, A Crystal, T H
U.S. Naval Research Laboratory, USA
Tu3P38
A Comparison of Fusion Techniques in Mel-Cepstral based Speaker
Identification
Slomka, S Sridharan, S Chandran, V
Queensland University of Technology, AUSTRALIA
Tu3P39
On the Influence of Hyperarticulated Speech on Recognition Performance
Soltau, H Waibel, A
Carnegie Mellon University, USA
Tu3P40
Text-independent speaker identification and verification using the TIMIT
Database
Ward, N C Dersch, D R
Alcatel Australia, AUSTRALIA
Tu3P41
Incorporating Linguistic Knowledge into Automatic Dialect Identification
of Spanish
Yanguas, L O'Leary, G Zissman, M
Mit Lincoln Laboratory, USA
Tu3P42
A Novel Text-Independent Speaker Verification Method Using the Global
Speaker Model
Zhang, Y Zhu, X-Y
Tsinghua University, P.R. CHINA
Tu3Q - Multimodal Spoken Language Processing 1
Time & Place: 1130 - 1430, Quokka Room
Chair: Sharon Oviatt
Tu3Q1
A fast method of producing talking head mouth shapes from real speech
Breen, A P Gloaguen, O Stern, P
BT Labs, UNITED KINGDOM
Tu3Q2
The Efficiency of Multimodal Interaction: A Case Study
Cohen, P R Johnston, M McGee, D Oviatt, S L Clow, J Smith, I
Oregon Graduate Institute, USA
Tu3Q3
Audio and Audio-visual Perception of Consonants Disturbed by White
Noise and 'Cocktail Party'
Czap, L
University of Miskolc, HUNGARY
Tu3Q4
Overview of the Maya Spoken Language System
Downey, S Breen, A P Fernandez, M Kaneen, E
BT Labs, UNITED KINGDOM
Tu3Q5
Automatic Recognition of Spontaneous Speech Dialogues
Cettolo, M Falavigna, D
ITC-IRST, ITALY
Tu3Q6
Using an Animated Talking Character in a web-based City Guide
Demonstrator
Fries, G Feldes, S Corbet, A
Deutsche Telekom Berkom, GERMANY
Tu3Q7
Influence of facial views on the McGurk effect in auditory noise
Kanzaki, R Kato, T
ATR Information Processing Research Laboratories, JAPAN
Tu3Q8
The Intellimedia WorkBench - a generic environment for multimodal
systems
Brondsted, T Larsen, L B Manthey, M Moeslund, T B McKevitt, P
Olesen, K G
Aalborg University, DENMARK
Tu3Q9
Stamp: A Suite of Tools for Analyzing Multimodal System Processing
Clow, J Oviatt, S L
Oregon Graduate Institute of Science & Technology, USA
Tu3Q10
Cultural similarities and differences in the recognition of audio-visual
speech stimuli
Shigeno, S
Kitasato University, JAPAN
Tu3Q11
A Multimodal-Input Multimedia-Output Guidance System: MMGS
Takezawa, T Morimoto, T
ATR Interpreting Telecommunications Research Laboratories, JAPAN
Tu3Q12
HMM-based Visual Speech Recognition using Intensity and Location
Normalization
Vanegas, O Tanaka, A Tokuda, K Kitamura, T
Nagoya Institute of Technology, JAPAN
Tu3Q13
A Hierarchy Probability-based Visual Features Extraction Method for
Speechreading
Xu, Y Du, L Li, G Hou, Z
Chinese Academy of Science, P.R. CHINA
Tu3Q14
Integration of Talking Heads and Text-to-Speech Synthesizers for Visual
TTS
Ostermann, J Beutnagel, M Fischer, A Wang, Y
AT&T Labs Research
Tu3R - Isolated Word Recognition
Time & Place: 1130 - 1430, Rosella Room
Chair: Li Deng
Tu3R1
Improving Accuracy of telephony-based, speaker-independent speech
recognition
Azzopardi D Semnani S Milner B Wiseman R
BT Labs, UNITED KINGDOM
Tu3R2
Rejection in Speech Recognition Systems with Limited Training
Bayya, A
Rockwell Semiconductor Systems, USA
Tu3R3
A Four Layer Sharing HMM System for Very Large Vocabulary Isolated
Word Recognition
Chen, R Tanaka, M Wu, D Olorenshaw, L Amador, M
SONY Research Labs, USA
Tu3R4
A Comparative Study of Hybrid Modelling Techniques for Improved
Telephone Speech Recognition
Chengalvarayan, R
Lucent Technologies, USA
Tu3R5
Smoothing and Tying for Korean Flexible Vocabulary Isolated Word
Recognition
Choi, J-S Lee, J-S Lee, H-Y
LG Corporate Institute of Technology, KOREA
Tu3R6
Recent Work on a Preselection Module for a Flexible Large Vocabulary
Speech Recognition System in Telephone Environment
Ferreiros, J Macias-Guarasa, J Gallardo, A Colas, J Cordoba, R Pardo, J
Villarrubia, L
GTH-IEL-UPM, SPAIN
Tu3R7
A Study of Noise Robustness for Speaker Independent Speech Recognition
Method Using Phoneme Similarity Vector
Hoshimi, M Yamada, M Niyada, K Makino, S
Matsushita Research Institute Tokyo, Inc., JAPAN
Tu3R8
Classification of Taiwanese tones based on pitch and energy movements
Jian, F
University of Reading, UNITED KINGDOM
Tu3R9
Phoneme-based recognition for the Norwegian SpeechDat(II) database
Johansen, F T
Telenor R&D, NORWAY
Tu3R10
Robust Feature Extraction for Alphabet Recognition
Karnjanadecha, M Zahorian, S A
Old Dominion University, USA
Tu3R11
Recognition of Connected Digit Speech in Japanese Collected over the
Telephone Network
Kawai, H Higuchi, N
KDD R&D Laboratories Inc., JAPAN
Tu3R12
Improving the Speaker-Dependency of Subword-Unit-Based Isolated
Word Recognition
Koizumi, T Taniguchi, S Kohtoh, K
Fukui University, JAPAN
Tu3R13
Speaker Independent Speech Recognition Method using Constrained Time
Alignment near Phoneme Discriminative Frame
Konuma, T Suzuki, T Yamada, M Ono, Y Hoshimi, M Niyada, K
Matsushita Research Institute Tokyo, Inc, JAPAN
Tu3R14
A Nonatationary Autoregressive HMM with Gain Adaptation for Speech
Recognition
Lee, K Y Lee, J
Soongsil University, KOREA
Tu3R15
A Large-Vocabulary Taiwanese (Min-nan) Multi-syllabic Word
Recognition System Based upon Right-Context-Dependent Phones with
State Clustering by Acoustic Decision Tree
Lyu, R-Y Chiang, Y-C Hsieh, W-P
Chang Gung University, TAIWAN R.O.C.
Tu3R16
Speech Recognition Based on the Distance Calculation Between
Intermediate Phonetic Code Sequences in Symbolic Domain
Tanaka, K Kojima, H
Electrotechnical Laboratory, JAPAN
Tu3R17
High Accuracy Chinese Speech Recognition Approach with Chinese
Input Technology for Telecommunication Use
Yang, Y C-H Kuo, J-J
Matsushita Institute of Technology, Taipei, TAIWAN R.O.C.
Tu4A - Robust Speech Processing in Adverse
Environments 1
Time & Place: 1330 - 1500, Antechinus Room
Chair: Sridha Sridharan
1330
Tu4A1
Robust Speech Recognition using HMM's With Toeplitz State Covariance
Matrices
Roberts, W Ephraim, Y
Defence Science & Technology Organisation, AUSTRALIA
1345
Tu4A2
Modeling of Output Probability Distributions to improve Small
Vocabulary Speech Recognition in Adverse Environments
Thambiratnam, D Sridharan, S
Queensland University of Technology, AUSTRALIA
1400
Tu4A3
Robust and compact multilingual word recognizers using features
extracted from a phoneme similarity front-end
Morin, P Applebaum, T H Boman, R Zhao, Y Junqua, J-C
Panasonic Technologies Inc., USA
1415
Tu4A4
An Effect of Adaptive Beamforming on Hands-free Speech Recognition
Based on 3-D Viterbi Search
Yamada, T Nakamura, S Shikano, K
Nara Institute of Science and Technology, JAPAN
1430
Tu4A5
Coherence-based Subband Decomposition for Robust Speech and
Speaker Recognition in Noisy and Reverberant Rooms
Gonzalez-Rodriguez, J Cruz-Llanas, S Ortega-Garcia, J
Universidad Politecnica Madrid, SPAIN
1445
Tu4A6
A Minimax Search Algorithm for CDHMM based Robust Continuous
Speech Recognition
Jiang, H Hirose, K Huo, Q
The University of Tokyo, JAPAN
Tu4B - Spoken Language Models and Dialog 2
Time & Place: 1330 - 1500, Bandicoot Room
Chair: Rolf Carlson
1330
Tu4B1
An event driven model for dialogue systems
Wang, K
Microsoft Research, USA
1345
Tu4B2
Automatic Classification of Dialogue Contexts for Dialogue Predictions
Popovici, C Baggia, P Laface, P Moisa, L
Politecnico Di Torino, ITALY
1400
Tu4B3
Automatic Identification of Command Boundaries in a Conversational
Natural Language User Interface
Ramaswamy, G N Kleindienst, J
I.B.M. Research Center, USA
1415
Tu4B4
The Predictive Power of Game Structure in Dialogue Act Recognition:
Experimental Results Using Maximum Entropy Estimation
Poesio, M Mikheev, A
University of Edinburgh, HCRC, UNITED KINGDOM
1430
Tu4B5
A schema based approach to dialog control
Constantinides, P Hansma, S Tchou, C Rudnicky, A
Carnegie Mellon University, USA
1445
Tu4B6
Expanding a time-sensitive conversational architecture for turn-taking to
handle content-driven interruption
Aist, G
Carnegie Mellon University, USA
Tu4C - Articulatory Modelling 1
Time & Place: 1330 - 1500, Currawong Room
Chair: Alain Marchal
1330
Tu4C1
A Three-Dimensional Linear Articulatory Model Based on MRI Data
Badin, P Bailly, G Raybaudi, M Segebarth, C
Institut Communication Parlee, FRANCE
1345
Tu4C2
On Loops and Articulatory Biomechanics
Perrier, P Payan, Y Perkell, J Jolly, F Zandipour, M Matthies, M
Institut De La Communication Parlée - INPG, FRANCE
1400
Tu4C3
Magnetic Resonance Measurements of the Velum port opening
Demolin, D Lecuit, V Metens, T Nazarian, B Soquet, A
Universite Libre De Bruxelles, BELGIUM
1415
Tu4C4
Cantilever-type force-sensor-mounted palatal plate for measuring
palatolingual contact stress and pattern during speech phonation.
Matsumura, M Niikawa, T Tanabe, T Tachimura, T Wada, T
Osaka Electro-Communication University, JAPAN
1430
Tu4C5
Determination of the vocal tract spectrum from the articulatory
movements based on the search of an articulatory-acoustic database
Kaburagi, T Honda, M
NTT Basic Research Laboratories, JAPAN
1445
Tu4C6
An MRI study on the relationship between oral cavity shape and larynx
position
Honda, K Tiede, M
ATR Human Information Processing Research Laboratories, JAPAN
Tu4D - Talking To Infants, Pets and Lovers
Time & Place: 1330 - 1500, Dingo Room
Chair: Cecile Pereira
1330
Tu4D1
Acoustic and Affective Qualities of IDS in English
Kitamura, C Burnham, D
University of New South Wales, AUSTRALIA
1345
Tu4D2
Acoustic Qualities of IDS and ADS in Thai
Thanavisuth, C Luksaneeyanawin, S
Chulalongkorn University, THAILAND
1400
Tu4D3
Pragmatic Characteristics of Infant Directed Speech
Luksaneeyanawin, S Thanavisuth, C Sittigasorn, S Rukkarangsarit, O
Chulalongkorn University, THAILAND
1415
Tu4D4
Are You My Little Pussy-Cat? Acoustic, Phonetic and Affective Qualities
of Infant- and Pet-Directed Speech
Burnham, D Francis, E Vollmer-Conna, U Kitamura, C Averkiou, V Olley,
A Nguyen, M Paterson, C
University of New South Wales, AUSTRALIA
1430
Tu4D5
Special Speech Registers: Talking To Australian and Thai Infants, and
To Pets.
Burnham, D
University of New South Wales, AUSTRALIA
Tu5A - Robust Speech Processing in Adverse
Environments 2
Time & Place: 1530 - 1700, Antechinus Room
Chair: Phil Woodland
1530
Tu5A1
Performance improvements through combining phone- and syllable-scale
information in automatic speech recognition
Wu, S-L Kingsbury, B E D Morgan, N Greenberg, S
Nuance Communications, USA
1545
Tu5A2
Predictive Adaptation and Compensation for Robust Speech Recognition
Surendran, A C Lee, C-H
Bell Labs, Lucent Technologies, USA
1600
Tu5A3
Influence of the speaking style and the noise spectral tilt on the Lombard
reflex and automatic speech recognition
Junqua, J-C Fincke, S Field, K
Speech Technology Laboratory, USA
1615
Tu5A4
Data-Driven PMC and Bayesian Learning Integration for Fast Model
Adaptation in Noisy Conditions
Crafa, S Fissore, L Vair, C
CSELT, ITALY
1630
Tu5A5
Improving the noise and spectral robustness of an isolated-word
recognizer using an auditory-model front end
Hunke, M Hyun, M Love, S Holton, T
San Francisco State University, USA
1645
Tu5A6
A Model for Speech Reverberation and Intelligibility Restoring Filters
Kenny, O P Nelson, D J
USA
Tu5B - Spoken Language Models and Dialog 3
Time & Place: 1530 - 1700, Bandicoot Room
Chair: Michael Barlow
1530
Tu5B1
On Different Functions of Repetitive Utterances
Swerts, M Koiso, H Shimojima, A Katagiri, Y
IPO, Center for Research On User-System Interaction, THE NETHERLANDS
1545
Tu5B2
Prosody based detection of the context of backchannel responses
Noguchi, H Den, Y
NAIST, JAPAN
1600
Tu5B3
Robust Interpretation for Spoken Dialogue Systems
Strömbäck, L Jonsson, A
Linkoping University, SWEDEN
1615
Tu5B4
System-User Interaction and Response Strategy in Spoken Dialog System
Okato, Y Kato, K Yamamoto, M Itahashi, S
University of Tsukuba, JAPAN
1630
Tu5B5
Organizing Self-Motivated Dialogue with Autonomous Creatures
Suzuki, N Ishii, K Okada, M
ATR Media Integration & Communications Research Labs, JAPAN
1645
Tu5B6
Fly with the EAGLES: Evaluation of the ACCeSS Spoken Language
Dialogue System
Hanrieder, G Heisterkamp, P Brey, T
Daimler-Benz AG, GERMANY
Tu5C - Speech Coding 1
Time & Place: 1530 - 1700, Currawong Room
Chair: Ian Burnett
1530
Tu5C1
A very low bit rate speech coder using HMM with speaker adaptation
Masuko, T Tokuda, K Kobayashi, T
Tokyo Institute of Technology, JAPAN
1545
Tu5C2
ITU-T G.729 extension at 6.4 kbps
Ekudden, E Hagen, R Johansson, B Hayashi, S Kataoka, A Kurihara, S
Ericsson Radio Systems AB, SWEDEN
1600
Tu5C3
Adaptive Transformation for Segmented Parametric Speech Coding
Mudugamuwa D J Bradley A B
RMIT, AUSTRALIA
1615
Tu5C4
Speech enhancement using STC-based bandwidth extension
Epps, J Holmes, W H
University of NSW, AUSTRALIA
1630
Tu5C5
Performance and Optimization of the SEEVOC Algorithm
Zhang, W Holmes, WH
The University of New South Wales, AUSTRALIA
Tu5D - Articulatory Modelling 2
Time & Place: 1530 - 1700, Dingo Room
Chair: Frantz Clermont
1530
Tu5D1
Acoustic-articulatory evaluation of the upper vowel-formant region and
its presumed speaker-specific potency
Clermont, F Mokhtari, P
Australian Defence Force Academy, AUSTRALIA
1545
Tu5D2
Control of larynx height in vowel production
Hoole, P Kroos, C
Munich University, GERMANY
1600
Tu5D3
Analyzing the effect of secondary excitations of the vocal tract on vocal
intensity in different loudness conditions
Alku, P Vintturi, J Vilkman, E
University of Turku, FINLAND
1615
Tu5D4
An Analysis of Modal Coupling Effects During the Glottal Cycle :
Formant Synthesizers From Time-Domain Finite-Difference Simulations
Ramsay, G
Institut De La Communication Parlee, FRANCE
1630
Tu5D5
Laryngoscopic Analysis of Pharyngeal Articulations and Larynx-Height
Voice Quality Settings
Esling, J
University of Victoria, CANADA
1645
Tu5D6
Effects of shapes of radiational aperture on radiation characteristics
Matsuzaki, H Motoki, K Miki, N
Hokkai-Gakuen University, JAPAN
Tu5P - Prosody and Emotion 2
Time & Place: 1530 - 1800, Platypus Room
Chair: David House
Tu5P1
De-accentuation: Linguistic Environments and Prosodic Realizations
Alter, K Steinhauer, K Friederici, A D
Max-Planck-Institute of Cognitive Neuroscience, GERMANY
Tu5P2
Towards an automatic classification of emotions in speech
Amir, N Ron, S
Center for Technological Education Holon, ISRAEL
Tu5P3
Can we hear smile?
Schröder, M Auberge, V Cathiard, M
ICP - ESA 5009 CNRS, FRANCE
Tu5P4
The Automatic Marking of Prominence in Spontaneous Speech Using
Duration and Part of Speech Information
Aylett, M P Bull, M
University of Edinburgh, UNITED KINGDOM
Tu5P5
On a Pitch Alteration Technique in Excited Cepstral Spectrum for High
Quality TTS
Kim, J D Baek, S J Bae, M J
Soongsil University, KOREA
Tu5P6
Dovetailing of acoustics and prosody in spontaneous speech recognition
Buckow, J Batliner, A Huber, R Noeth, E Warnke, V Niemann, H
University of Erlangen, GERMANY
Tu5P7
A Computational Memory and Processing Model for Prosody
Cahn, J E
M.I.T. Media Laboratory, USA
Tu5P8
Convergence of Fundamental Frequencies in Conversation: If it Happens,
Does it Matter?
Collins, B M
Australian National University, AUSTRALIA
Tu5P9
Analysis and Interpretation of Fundamental Frequency Contours of
British English in Terms of a Command-Response Model
Fujisaki, H Ohno, S Yagi, T Ono, T
Science University of Tokyo, JAPAN
Tu5P10
Common Patterns in Word Level Prosody
Holm, F Hata, K
Speech Technology Laboratory, USA
Tu5P11
Prosodic Structure in Japanese Spontaneous Speech
Horiuchi, Y Ichikawa, A
Chiba University, JAPAN
Tu5P12
An acoustic-phonetic description of word tone in Kagoshima Japanese
Ishihara, S
The Australian National University, AUSTRALIA
Tu5P13
Representing Prosodic Words Using Statistical Models of Moraic
Transition of Fundamental Frequency Contours of Japanese
Iwano, K Hirose, K
University of Tokyo, JAPAN
Tu5P14
Disambiguation of Korean Utterances Using Automatic Intonation
Recognition
Jang, T Song, M Lee, K
University of Edinburgh, UNITED KINGDOM
Tu5P15
Multi-level rhythm control for speech synthesis using hybrid data driven
and rule-based approaches
Jokisch, O Hirschfeld, D Eichner, M Hoffmann, R
Dresden University of Technology, GERMANY
Tu5P16
EGG Model of Ditoneme in Mandarin*
Kong, J
City University of Hong Kong, HONG KONG
Tu5P17
Temporal Organization of Speech for normal and fast rates
Krishnan, G Ward, W
Carnegie Mellon University, USA
Tu5P18
A syllable-based generalization of Japanese accentuation
Kubozono, H
Kobe University, JAPAN
Tu5P19
Non-adjacent Segmental Effects in Tonal Realization of Accentual Phrase
in Seoul Korean
Lee, H-J
UCLA, USA
Tu5P20
Improvement on Connected Numbers Recognition Using Prosodic
Information
Lopez-Gonzalo, E Caminero, J Cortazar, I Hernandez-Gomez, L
ETSIT-UPM, SPAIN
Tu5P21
Phonetic investigation of boundary pitch movements in Japanese
Maeda, K Venditti, J J
University of Pennsylvania, USA
Tu5P22
Phonetic and phonological characteristics of paralinguistic information in
spoken Japanese
Maekawa, K
The National Language Research Institute, JAPAN
Tu5P23
ToBI Accent Type Recognition
Maghbouleh, A
Stanford University, USA
Tu5P24
The Influence of Syllable Structure on the Timing of Intonational Events
in German
Mixdorff, H Fujisaki, H
Dresden University of Technology, GERMANY
Tu5P25
New Prosodic Control Rules for Expressive Synthetic Speech
Mizuno, O Nakajima, S
NTT Human Interface Labs, JAPAN
Tu5P26
The Use of F0 Reliability Function for Prosodic Command Analysis on F0
Contour Generation Model
Nakai, M Shimodaira, H
JAIST, JAPAN
Tu5P27
Analysis of Effects of Lexical Accent, Syntax and Global Speech Rate
upon the Local Speech Rate
Ohno, S Fujisaki, H Taguchi, H
Department of Applied Electronics, Science University of Tokyo, JAPAN
Tu5P28
On the Effects of Speech Rate upon Parameters of the Command-Response
Model for the Fundamental Frequency Contours of Speech
Ohno, S Fujisaki, H Hara, Y
Science University of Tokyo, JAPAN
Tu5P29
The maximum-based description of F0 contours and its application to
English
Portele, T Heuft, B
IKP, University of Bonn, GERMANY
Tu5P30
Perceived prominence and acoustic parameters in American English
Portele, T
IKP, University of Bonn, GERMANY
Tu5P31
Generating Emotional Speech with a Concatenative Synthesizer
Rank, E Pirker, H
OFAI, AUSTRIA
Tu5P32
A Perceptive Measure of Pure Prosody Linguistic Functions with
Reiterant Sentences
Rilliard, A Auberge, V
Institut De La Communication Parlee, FRANCE
Tu5P33
Prosodic Parameters in Emotional Speech
Koike, K Suzuki, H Saito, H
Keio University, JAPAN
Tu5P34
Automatic detection of prominence (as defined by listeners’ judgments) in
read aloud Dutch sentences
Streefkerk, B M Pols, L C W ten Bosch, L F M
Institute of Phonetic Science Amsterdam, THE NETHERLANDS
Tu5P35
A Schema for Illocutionary Act Identification with Prosodic Feature
Tamoto, M Kawabata, T
NTT Basic Research Laboratory, JAPAN
Tu5P36
An Algorithm for Choosing Japanese Acknowledgments using Prosodic
Cues and Context
Tsukahara, W
University of Tokyo, JAPAN
Tu5P37
A Study of Tones and Tempo in Continuous Mandarin Digit Strings and
their Application in Telephone Quality Speech Recognition
Wang, C Seneff, S
MIT Laboratory for Computer Science, USA
Tu5P38
Simulated emotions: an acoustic study of voice and perturbation
measures
Whiteside, S P
University of Sheffield, UNITED KINGDOM
Tu5P39
A Robust Tone Recognition Method of Chinese Based on Sub-syllabic F0
Contours
Zhang, J-S Hirose, K
The University of Tokyo, JAPAN
Tu5P40
The Microprosodics of Tone Sandhi in Shanghai Disyllabic Compounds
Zhu, X S
Australian National University, AUSTRALIA
Tu5P41
Jitter and Shimmer Differences Between Pathological Voices of School
Children
Bolfan-Stosic, N Prizl, T
University of Zagreb, CROATIA
Tu5Q - Neural Networks, Fuzzy and Evolutionary
Methods 1
Time & Place: 1530 - 1800, Quokka Room
Chair: Christian Wellekens
Tu5Q1
A Comparison of Thai Speech Recognition Systems using Hidden Markov
Model, Neural Network, and Fuzzy-Neural Network
Ahkuputra, V Jitapunkul, S Jittiwarangkul, N Maneenoi, E Kasuriya, S
Chulalongkorn University, THAILAND
Tu5Q2
Phoneme recognition with statistical modeling of the prediction error of
neural networks
Freitag, F Monte, E
Polytechnical University of Catalonia, SPAIN
Tu5Q3
Neural network based pronunciation modeling with applications to
speech recognition
Fukada, T Yoshimura, T Sagisaka, Y
ATR Interpreting Telecommunications Research Laboratories, JAPAN
Tu5Q4
A Comparative Study of OCON and MLP Architectures for Phoneme
Recognition
Haskey, S Datta, S
Loughborough University, UNITED KINGDOM
Tu5Q5
Evaluation and Integration of Neural-Network Training Techniques for
Continuous Digit Recognition
Hosom, J P Cole, R A Cosi, P
Oregon Graduate Institute, USA
Tu5Q6
Hierarchical Neural Networks (HNN) for Chinese Continuous Speech
Recognition
Jia, Y Du, L Hou, Z
Chinese Academy of Sciences, P.R. CHINA
Tu5Q7
Neural Network Motivation for Segmental Distribution
Keller, E
University of Lausanne, SWITZERLAND
Tu5Q8
Combining Connectionist Multi-Band and Full-Band Probability Streams
for Speech Recognition of Natural Numbers
Mirghafori, N Morgan, N
International Computer Science Institute, USA
Tu5Q9
Initial Speech Recognition Results using the Multinet Architecture
Pizzolato, E B Reynolds, TJ
University of Essex, UNITED KINGDOM
Tu5Q10
Selection of the Optimal Structure of the Continuous HMM Using the
Genetic Algorithm
Takara, T Iha, Y Nagayama, I
University of the Ryukyus, JAPAN
Tu5Q11
A Proposed Decision Rule for Speaker Recognition Based on Fuzzy
C-Means Clustering
Tran, D Wagner, M Le, T V
University of Canberra, AUSTRALIA
Tu5Q12
Fuzzy Gaussian Mixture Models for Speaker Recognition
Tran, D Le, T V Wagner, M
University of Canberra, AUSTRALIA
Tu5Q13
A New Strategy of Fuzzy-Neural Network for Thai Numeral Speech
Recognition
Wutiwiwatchai, C Jitapunkul, S Ahkuputra, V Maneenoi, E
Luksaneeyanawin, S
Chulalongkorn University, THAILAND
Tu5Q14
Thai Polysyllabic Word Recognition Using Fuzzy-Neural Network
Wutiwiwatchai, C Jitapunkul, S Ahkuputra, V Maneenoi, E
Luksaneeyanawin, S
Chulalongkorn University, THAILAND
Tu5R - Utterance Verification and Word Spotting 1 /
Speaker Adaptation 1
Time & Place: 1530 - 1800, Rosella Room
Chair: Douglas O'Shaughnessy
Tu5R1
Word Verification Using Confidence Measures in Speech Recognition
Benitez, C Rubio Ayuso, A Garcia Teodoro, P Diaz Verdejo, J E
Universidad De Granada, SPAIN
Tu5R2
Improving Posterior Based Confidence Measures in Hybrid HMM/ANN
Speech Recognition Systems
Bernardis, G Bourlard, H
IDIAP, SWITZERLAND
Tu5R3
Two-pass Utterance Verification Algorithm for Long Natural Numbers
Recognition
Caminero, J Lopez, E Hernandez, L
ETSIT-UPM, SPAIN
Tu5R4
A*-Admissible Key-Phrase Spotting with Sub-Syllable Level Utterance
Verification
Chen, B Wang, H-M Shien, L-F Lee, L-S
Academica Sinica, Taiwan, TAIWAN R.O.C.
Tu5R5
Speaker-Independent Upfront Dialect Adaptation in a Large Vocabulary
Continuous Speech Recognizer
Fischer, V Gao, Y Janke, E
IBM Speech Systems, GERMANY
Tu5R6
Word-Based Acoustic Confidence Measures for Large-Vocabulary
Speech Recognition
Gunawardana, A Hon, H-W Jiang, L
Microsoft Research, USA
Tu5R7
Improved Utterance Rejection using Length Dependent Thresholds
Gupta, S K Soong, F
Bell Laboratories - Lucent Technologies, USA
Tu5R8
Bayesian Constrained Frequency Warping HMMs for Speaker
Normalization
Ho, C H Vaseghi, S Chen, A
Queen's University of Belfast, UNITED KINGDOM
Tu5R9
An Evaluation of Keyword Spotting Performance utilizing False Alarm
Rejection based on Prosodic Information
Ida, M Yamasaki, R
OMRON Corporation, JAPAN
Tu5R10
Predictive Speaker Adaptation and Its Prior Training
Tran, D Iso, K-I
NEC, JAPAN
Tu5R11
Powerful Syllabic Fillers for General-Task Keyword-Spotting and
Unlimited-Vocabulary Continuous-Speech Recognition
El Meliani, R O'Shaughnessy, D
INRS-Telecommunications, CANADA
Tu5R12
Confidence Scoring for Speech Understanding Systems
Pao, C Schmid, P Glass, J
MIT Laboratory for Computer Science, USA
Tu5R13
Phonological Rules for Enhancing Acoustic Enrollment of Unknown
Words
Ramabhadran, B Ittycheriah, A
IBM T.J. Watson Research Center, USA
Tu5R14
Recognition-Based Word Counting for Reliable Barge-in and Early
Endpoint Detection in Continuous Speech Recognition
Setlur, A R Sukkar, R A
Lucent Technologies, USA
Tu5R15
Linear Discriminant - A New Criterion for Speaker Normalization
Westphal, M Schultz, T Waibel, A
Carnegie Mellon University, USA
Tu5R16
Confidence Measures Derived from an Acceptor HMM
Williams, G Renals, S
Sheffield University, UNITED KINGDOM
Tu5R17
Telephone Speech Multi-Keyword Spotting Using Fuzzy Search
Algorithm and Prosodic Verification
Wu, C-H Chen, Y-J Hung, Y-C
National Cheng Kung University, TAIWAN R.O.C.
Tu5R18
Topic Recognition for News Speech Based on Keyword Spotting
Yamashita, Y Tsunekawa, T Mizoguchi, R
Ritsumeikan University, JAPAN
Tu6A - Text-To-Speech Synthesis 2
Time & Place: 1700 - 1800, Antechinus Room
Chair: Susan Hertz
1700
Tu6A1
Prosody Prediction for Speech Synthesis using Transformational
Rule-based Learning
Fordyce, C Ostendorf, M
Lernout & Hauspie Speech Products, USA
1715
Tu6A2
Representing the environments for phonological processes in an
accent-independent lexicon for synthesis of English
Fitt, S Isard, S
University of Edinburgh, UNITED KINGDOM
1730
Tu6A3
Efficient Lexical Retrieval for English Text-to-Speech Synthesis
Faulkner, D Bryant, C
Aculab Plc, UNITED KINGDOM
Tu6B - Spoken Language Models and Dialog 4
Time & Place: 1700 - 1800, Bandicoot Room
Chair: James Glass
1700
Tu6B1
SQEL: A Multilingual and Multifunctional Dialog System
Aretoulaki, M Harbeck, S Gallwitz, F Noeth, E Niemann, H Ivanecky, J
Ipsic, I Pavesic, N Matousek, V
University of Erlangen, GERMANY
1715
Tu6B2
Semi-automated incremental prototyping of spoken dialog systems
Kaspar, S Hoffmann, A
University of New South Wales, AUSTRALIA
1730
Tu6B3
Beyond Structured Dialogues: Factoring out Grounding
Heeman, P Johnston, M Denney, J Kaiser, E
Oregon Graduate Institute, USA
Tu6D - Human Speech Perception 1
Time & Place: 1700 - 1800, Dingo Room
Chair: Anne Cutler
1700
Tu6D1
Heads and tails in word perception: Evidence for 'Early-to-Late'
Processing in listening and reading
Nooteboom, S G Van Dijk, M
Utrecht University, THE NETHERLANDS
1715
Tu6D2
Evidence for Early Effects of Sentence Context on Word Segmentation
te Riele, S M M Quené, H
Utrecht University, THE NETHERLANDS
1730
Tu6D3
Assimilation and anticipation in word perception
Quené, H van Rossum, M van Wijck, M
Utrecht University, THE NETHERLANDS
1745
Tu6D4
Lexical activation by assimilated and reduced tokens
Kelly, M L Bard, E G Sotillo, C
University of Edinburgh, UNITED KINGDOM
Wednesday 2 December, 1998
We1A - Robust Speech Processing in Adverse
Environments 3
Time & Place: 0900 - 1000, Antechinus Room
Chair: Douglas Reynolds
0900
We1A1
Linear and Nonlinear Speech Feature Analysis for Stress Classification
Zhou, G Hansen, J H L Kaiser, J F
Robust Speech Processing Laboratory, USA
0915
We1A2
Speech Feature Modeling for Robust Stressed Speech Recognition
Bou-Ghazale, S E Hansen, J H L
Robust Speech Processing Laboratory, USA
0930
We1A3
Combining Articulatory and Acoustic Information for Speech Recognition
in Noisy and Reverberant Environments
Kirchhoff, K
University of Bielefeld, GERMANY
0945
We1A4
Improving Speaker Identification Performance in Reverberant
Conditions using Lip Information
Wark, T Sridharan, S
Queensland University of Technology, AUSTRALIA
We1B - Speech and Hearing Disorders 1
Time & Place: 0900 - 1000, Bandicoot Room
Chair: Florien Koopmans-van-Bienum
0900
We1B1
Adults with a severe-to-profound hearing impairment. Investigating the
effects of linguistic context on speech perception.
Flynn, M Dowell, R Clark, G
University of Melbourne, AUSTRALIA
0915
We1B2
Speech Perception in Dyslexia: Measurements from Birth Onwards
Koopmans-van Beinum, F J Schwippert, C Kuijpers, C T L
University of Amsterdam, THE NETHERLANDS
0930
We1B3
An Acoustic Analysis of Vowel Production Across Tasks in a Case of
Non-fluent Progressive Aphasia
Croot, K
University of Sydney / Macquarie University, AUSTRALIA
0945
We1B4
Speech technology in clinical environments:
van Doorn, J McLeod, S Baker, E Purcell, A Thorpe, W
The University of Sydney (Cumberland Campus), AUSTRALIA
We1C - Prosody and Emotion 3
Time & Place: 0900 - 1000, Currawong Room
Chair: Mark Swerts
0900
We1C1
What Spreads, and How? Tonal Rightward Spreading On Shanghai
Disyllabic Compounds
Zhu, X S
Australian National University, AUSTRALIA
0915
We1C2
Tonal Complexity as a Dialectal Feature: 25 Different Citation Tones from
Four Zhejiang Wu Dialects
Zhu, S X Rose, P
Australian National University, AUSTRALIA
0930
We1C3
Emotional Speech Synthesis: from speech database to TTS
Montero, J M Gutierrez-Arriola, J Palazuelos, S Enriquez, E Aguilera, S
Pardo, J M
GTH-IEL-UPM, SPAIN
0945
We1C4
Some Acoustic Characteristics of Emotion
Pereira, C Watson, C
SHLRC, Macquarie University, AUSTRALIA
We1D - Spoken Language Understanding Systems 1
Time & Place: 0900 - 1000, Dingo Room
Chair: David Grayden
0900
We1D1
Galaxy-II: A Reference Architecture for Conversational System
Development
Seneff, S Hurley, E Lau, R Pao, C Schmid, P Zue, V
MIT, USA
0915
We1D2
Improvements in Speech Understanding Accuracy Through the
Integration of Hierarchical Linguistic, Prosodic, and Phonological
Constraints in the Jupiter Domain
Chung, G Seneff, S
MIT Laboratory for Computer Science, USA
0930
We1D3
Towards Robust Methods for Spoken Document Retrieval
Ng, K
MIT, USA
We1P - Signal Processing and Speech Analysis 1
Time & Place: 0900 - 1130, Platypus Room
Chair: Aaron Rosenberg
We1P1
Maximum a Posteriori Pitch Tracking
Droppo, J Acero, A
Microsoft Corporation, USA
We1P2
Vowel Separation Using the Reassigned Amplitude-Modulation Spectrum
Yang, D Meyer, G F Ainsworth, W A
Keele University, UNITED KINGDOM
We1P3
Feature Decorrelation Methods in Speech Recognition. A Comparative
Study
Batlle, E Nadeu, C Fonollosa, J A R
Polytechnical University of Catalonia, SPAIN
We1P4
Multi-resolution for Speech Analysis
Caraty, M-J Montacie, C
Universite Pierre Et Marie Curie, FRANCE
We1P5
Dynamic features in Children's Vowels
Cassidy, S Watson, C
Macquarie University, AUSTRALIA
We1P6
Effectiveness of phase-corrected RASTA for continuous speech
recognition
de Veth, J Boves, L
University of Nijmegen, THE NETHERLANDS
We1P7
Techniques for capturing temporal variations in speech signals with
fixed-rate processing
Dharanipragada, S Gopinath, R Rao, B
IBM T. J. Watson Research Center, USA
We1P8
Automatic Detection of Landmark for Nasal Consonants from Speech
Waveform
Du, L Stevens, K N
Chinese Academy of Sciences, P.R. CHINA
We1P9
Plug and Play Software for Designing High-Level Speech Processing
Systems
Dutoit, T Schroeter, J
Faculte Polytechnique De Mons, BELGIUM
We1P10
Creating speaker independent HMM models for restricted database using
STRAIGHT-TEMPO morphing
Girardi, A Shikano, K Nakamura, S
Nara Institute of Science and Technology, JAPAN
We1P11
Restoration of hyperbaric speech by correction of the formants and the
pitch
Charonnat, L Guitton, M Crestel, J Allee, J
ENSSAT, FRANCE
We1P12
Voice Conversion based on parameter transformation
Gutiérrez-Arriola, J M Hsiao, Y S Montero, J M
Pardo, J M Childers, D G
GTH-IEL-UPM, SPAIN
We1P13
Noise Robust Two-Stream Auditory Feature Extraction Method for
Speech Recognition
Tian, J Hariharan, R Laurila, K
Nokia Research Center, FINLAND
We1P14
Heterogeneous Measurements and Multiple Classifiers for Speech
Recognition
Halberstadt, A K Glass, J R
MIT, USA
We1P15
Joint Recognition and Segmentation using Phonetically Derived Features
and a Hybrid Phoneme Model
Harte, N Vaseghi, S Milner, B
Queen's University of Belfast, UNITED KINGDOM
We1P16
TRAPS - Classifiers of Temporal Patterns
Hermansky, H Sharma, S
Oregon Graduate Institute, USA
We1P17
Robust measurement of fundamental frequency and degree of voicing
Holmes, J N
UNITED KINGDOM
We1P18
Micropower Electro-Magnetic Sensors for Speech Characterization,
Recognition, Verification, and Other Applications
Holzrichter, J F Burnett, G C Gable, T J Ng, L C
Lawrence Livermore National Laboratory, USA
We1P19
Robust Entropy-based Endpoint Detection for Speech Recognition in
Noisy Environments
Shen, J-L Hung, J-W Lee, L-S
Academia Sinica, TAIWAN R.O.C.
We1P20
Statistical Integration of Temporal Filter Banks for Robust Speech
Recognition Using Linear Discriminant Analysis (LDA)
Shen, J-L Hwang, W-L
Academia Sinica, TAIWAN R.O.C.
We1P21
Feature-Based Approach to Speech Recognition
Iskra, D J Edmondson, W H
University of Birmingham, UNITED KINGDOM
We1P22
Periodicity Emphasis of Voice Wave using Nonlinear IIR Digital Filters
and Its Applications
Kamata, H Kaneko, A Ishida, Y
Meiji University, JAPAN
We1P23
Speech recognition via phonetically featured syllables
King, S Stephenson, T Isard, S Taylor, P Strachan, A
CSTR, University of Edinburgh, UNITED KINGDOM
We1P24
Do Phonetic Features Help to Improve Consonant Identification in ASR?
Koreman, J Andreeva, B Barry, W J
University of the Saarland, GERMANY
We1P25
Perceptual and acoustic properties of phonemes in continuous speech for
different speaking rate
Kuwabara, H
Teikyo University of Science & Technology, JAPAN
We1P26
On Robust Sequential Estimator Based on t-distribution with Forgetting
Factor for Speech Analysis
Lee, J Lee, K Y
Dong-Ah Broadcasting College, KOREA
We1P27
Discriminant Wavelet Basis Construction for Speech Recognition
Long, C Datta, S
Loughborough University, UNITED KINGDOM
We1P28
An Efficient Mel-LPC Analysis Method for Speech Recognition
Matsumoto, H Nakatoh, Y Furuhata, Y
Shinshu University, JAPAN
We1P29
Discriminative Weighting of Multi-resolution Sub-band Cepstral
Features for Speech Recognition
McMahon, P McCourt, P Vaseghi, S
Queens University of Belfast, NORTHERN IRELAND
We1P30
Separation of Singing and Piano Sounds
Meron, Y Hirose, K
Tokyo University, JAPAN
We1P31
Modeling of Variations in Cepstral Coefficients Caused by F0 Changes
and its Application to Speech Processing
Minematsu, N Nakagawa, S
Toyohashi University of Technology, JAPAN
We1P32
A Detection Framework for Locating Phonetic Events
Niyogi, P Mitra, P P Sondhi, M M
Bell Laboratories, Lucent Technologies, USA
We1P33
On Frequency Averaging for Spectral Analysis in Speech Recognition
Nadeu, C Galindo, F Padrell, J
Polytechnical University of Catalonia, SPAIN
We1P34
Wavelet transform domain blind equalization and its application to
speech analysis
Namba, M Ishida, Y
Meiji University, JAPAN
We1P35
A Novel Method of Formant Analysis and Glottal Inverse Filtering
Pearson, S
Speech Technology Lab/Panasonic Technologies Inc., USA
We1P36
Vector Quantizer Acceleration for an Automatic Speech Recognition
Application
Araújo, A Pera, V Souza, M
FEUP, PORTUGAL
We1P37
Local Speech Rate as a Combination of Syllable and Phone Rate
Pfitzinger, H R
University of Munich, GERMANY
We1P38
Recovering gestures from speech signals: a preliminary study for nasal
vowels
Rossato, S Feng, G Laboissière, R
Institut De La Communication Parlee, FRANCE
We1P39
Extended Linear Discriminant Analysis (ELDA) for Speech Recognition
Ruske, G Faltlhauser, R Pfau, T
Technical University of Munich, GERMANY
We1P40
Speech, Silence, Music and Noise Classification of TV Broadcast Material
Samouelian, A Robert-Ribes, J Plumpe, M
University of Wollongong, AUSTRALIA
We1P41
The relation between vocal tract shape and formant frequencies can be
described by means of a system of coupled differential equations
Schoentgen, J Soquet, A Lecuit, V Ciocea, S
Universite Libre De Bruxelles, BELGIUM
We1P42
Improving speech recognizer by broader acoustic-phonetic group
classification
Suh, Y Hwang, K Kwon, O Park, J
ETRI, KOREA
We1P43
Separation of speech source and filter by time-domain deconvolution
Thorpe, C W
National Voice Centre, Australia, AUSTRALIA
We1P44
On the Application of the AM-FM Model for the Recovery of Missing
Frequency Bands of Telephone Speech
Tolba, H O'Shaughnessy, D
INRS-Telecommunications, CANADA
We1P45
Estimation of Voice Source and Vocal Tract Parameters Using Combined
Subspace-based and Amplitude Spectrum-based Algorithm
Yang, C-S Kasuya, H
Utsunomiya University, JAPAN
We1P46
The Distance Measure for Line Spectrum Pairs Applied to Speech
Recognition
Zheng, F Song, Z-J Li, L Yu, W-J Zheng, F-Z Wu, W-H
Tsinghua University, P.R. CHINA
We1Q - Spoken Language Generation and Translation 1
Time & Place: 0900 - 1130, Quokka Room
Chair: Yoshinori Sagisaka
We1Q1
The Modeling and Realization of Natural Speech Generation System
Chen, F Yuan, B
Northern Jiaotong University, P.R. CHINA
We1Q2
'Ko Tok Ples Ensin bilong Tok Pisin' or the TP-CLE: A first report from
a pilot speech-to-speech translation project from Swedish to Tok Pisin
Eklund, R
Telia Research AB, SWEDEN
We1Q3
An Iterative, DP-based Search Algorithm for Statistical Machine
Translation
Garcia-Varea, I Casacuberta, F Ney, H
Universidad Politecnic De Valencia, SPAIN
We1Q4
Information extraction and text generation of news reports for a
Swedish-English bilingual spoken dialogue system
Gawronska, B House, D
University of Skovde, SWEDEN
We1Q5
Utterance Generation for Transaction Dialogues
Hulstijn, J Van Hessen, A
University of Twente, THE NETHERLANDS
We1Q6
Example-Based Error Recovery Method for Speech Translation:
Repairing Sub-Trees According to the Semantic Distance
Ishikawa, K Sumita, E Iida, H
ATR Interpreting Telecommunications Research Laboratories, JAPAN
We1Q7
Context Sensitive Generation of Descriptions
Krahmer, E Theune, M
IPO Center for Research On User-System Interaction, THE NETHERLANDS
We1Q8
An Interlingua Based on Domain Actions for Machine Translation of
Task-Oriented Dialogues
Levin, L Gates, D Lavie, A Waibel, A
Carnegie Mellon University, USA
We1Q9
Generating Pitch Accents in a Concept-To-Speech System using a
Knowledge Base
Williams, S H
Microsoft Research Institute, Macquarie University, AUSTRALIA
We1Q10
Making the most of multiplicity: a multi-parser, multi-strategy
architecture for the robust processing of spoken language
Ruland, T Rupp, C J Spilker, J Weber, H Worm, K L
Siemens AG / University of the Saarland, GERMANY
We1Q11
Natural-Sounding Speech Synthesis Using Variable-Length Units
Yi, J R W Glass, J R
MIT, USA
We1R - Spoken Language Models and Dialog 5
Time & Place: 0900 - 1130, Rosella Room
Chair: Pietro Laface
We1R1
A robust dialogue model for spoken dialogue processing
Araki, M Doshita, S
Kyoto University, JAPAN
We1R2
The REWARD Service Creation Environment. An Overview
Brøndsted, T Bai, B Olsen, J
Aalborg University, DENMARK
We1R3
An Analysis of the Timing of Turn-Taking in a Corpus of Goal-Oriented
Dialogue
Bull, M C Aylett, M
University of Edinburgh, UNITED KINGDOM
We1R4
The provision of corrective feedback in a spoken dialogue CALL system
Davies, S Poesio, M
University of Edinburgh, HCRC, UNITED KINGDOM
We1R5
Evaluation of dialog strategies for a tourist information retrieval system
Devillers, L Bonneau-Maynard, H
LIMSI/CNRS, FRANCE
We1R6
Designing a Multimodal Dialogue System for Information Retrieval
Furui, S Yamaguchi, K
Tokyo Institute of Technology, JAPAN
We1R7
The Research Project of Man-Computer dialogue System in Chinese
Guan, D Chu, M Zhang, Q Liu, J Zhang, H
Chinese Academy of Sciences, P.R. CHINA
We1R8
Interfaces for Speech Recognition Systems: The Impact of Vocabulary
Constraints and Syntax on Performance
Hone, K Golightly, D
ICL Institute of Information Technology, UNITED KINGDOM
We1R9
Pacing Spoken Directions to Suit the Listener
Iwase, T Ward, N
University of Tokyo, JAPAN
We1R10
A Spoken Dialogue System Utilizing Spatial Information
Flycht-Eriksson, A Jonsson, A
Linkoping University, SWEDEN
We1R11
From Novice to Expert: The Effect of Tutorials on User Expertise with
Spoken Language Dialogue Systems - An Empirical Analysis of the Efficacy
of Tutorial Dialogues
Kamm, C A Litman, D J Walker, M A
AT&T Labs Research, USA
We1R12
Emergent Computational Dialogue Management Architecture for
Task-Oriented Spoken Dialogue Systems
Kawabata, T
NTT Basic Research Labs, JAPAN
We1R13
An Analysis of Dialogues with Our Dialogue System through a WWW
page
Kumamoto, T Ito, A
Communications Research Laboratory, JAPAN
We1R14
Modelling spoken dialogues with state transition diagrams: experiences of
the CSLU toolkit
McTear, M
University of Ulster, UNITED KINGDOM
We1R15
Situated Dialogue Coordination for Spoken Dialogue Systems
Okada, M Suzuki, N Terken, J
ATR MI & C Research Laboratories, JAPAN
We1R16
Robust spoken dialogue systems for consumer products: a concrete
application
Pouteau, X Arevalo, L
IPO, Center for Research On User-System Interaction, THE NETHERLANDS
We1R17
A German Dialogue System for Scheduling Dates and Meetings by
Naturally Spoken Continuous Speech
Willett, D Roemer, A Rottland, J Rigoll, G
Duisburg University, GERMANY
We1R18
Spoken Dialogue System Using Corpus-Based Hidden Markov Model
Wu, C-H Yan, G-L Lin, C-L
National Cheng Kung University, TAIWAN R.O.C.
We1R19
A Realistic Wizard of Oz simulation of a Multimodal Spoken Language
System
Wyard, P Churcher, G
BT Laboratories, UNITED KINGDOM
We1R20
A Syllable-Based Chinese Spoken Dialogue System for Telephone
Directory Services Primarily Trained with a Corpus
Yang, Y-J Lee, L-S
National Taiwan University, TAIWAN R.O.C.
We1R21
How disagreement expressions are used in cooperative tasks
Yano, H Ito, A
Communications Research Laboratory, JAPAN
We2A - Segmentation, Labelling and Speech Corpora 1
Time & Place: 1030 - 1130, Antechinus Room
Chair: Bill Barry
1030
We2A1
Acoustic Indicators of Topic Segmentation
Hirschberg, J Nakatani, C
AT & T Labs - Research, USA
1045
We2A2
IViE - A Comparative Transcription system for Intonational Variation in
English
Grabe, E Nolan, F Farrar, K J
University of Cambridge, UNITED KINGDOM
1100
We2A3
Automatic Segmental and Prosodic Labeling of Mandarin Speech
Database
Chou, F-C Tseng, C-Y Lee, L-S
National Taiwan University, TAIWAN R.O.C.
1115
We2A4
Automatic Labelling of German Prosody
Rapp, S
Sony International (Europe) GmbH, GERMANY
We2B - Multimodal Spoken Language Processing 2
Time & Place: 1030 - 1130, Bandicoot Room
Chair: Dominic Massaro
1030
We2B1
Speech Driven 3-D Face Point Trajectory Synthesis Algorithm
Arslan, L M Talkin, D
Entropic Research Lab, USA
1045
We2B2
Speech-to-Lip Movement Synthesis based on the EM Algorithm using
Audio-Visual HMMs
Yamamoto, E Nakamura, S Shikano, K
Nara Institute of Science and Technology, JAPAN
1100
We2B3
Learning Words from Natural Audio-Visual Input
Roy, D Pentland, A
MIT Media Laboratory, USA
1115
We2B4
Using the Multi-Stream Approach for Continuous Audio-Visual Speech
Recognition: Experiments on the M2VTS Database
Dupont, S Luettin, J
Faculte Polytechnique De Mons, BELGIUM
We2C - Prosody and Emotion 4
Time & Place: 1030 - 1130, Currawong Room
Chair: Hiroya Fujisaki
1030
We2C1
Intonative structure as a determinant of word order variation in Dutch
verbal endgroups
Swerts, M
IPO, Center for Research On User-System Interaction, THE NETHERLANDS
1045
We2C2
Experiments on the Meaning of Two Pitch Accent Types: The 'Pointed
Hat' Versus the Accent-Lending Fall in Dutch
Caspers, J
Holland Institute of Generative Linguistics, NETHERLANDS
1100
We2C3
Phonetic and Phonological Markers of Contrastive Focus in Korean
Jun, S-A Lee, H-J
UCLA, USA
1115
We2C4
Reconciling two competing views on contrastiveness
Krahmer, E Swerts, M
IPO, Center for Research On User-System Interaction, THE NETHERLANDS
We2D - Neural Networks, Fuzzy and Evolutionary
Methods 2
Time & Place: 1030 - 1130, Dingo Room
Chair: Tuan Pham
1030
We2D1
Modular Neural Networks for Low-Complex Phoneme Recognition
Glaeser, A
Ascom Systec Ltd, SWITZERLAND
1045
We2D2
Global Optimisation of Neural Network Models Via Sequential
Sampling-Importance Resampling
de Freitas, N Johnson, S Niranjan, M Gee, A
Cambridge University, UNITED KINGDOM
1100
We2D3
Efficient computation of MMI neural networks for large vocabulary
speech recognition systems
Rottland, J Luedecke, A Rigoll, G
Duisburg University, GERMANY
1115
We2D4
Modular Connectionist Systems for Identifying Complex Arabic Phonetic
Features
Selouani, S A Caelen, J
HB University, ALGERIA
Plenary Session
We3A - Plenary Panel Discussion
Title: Automatic Speech Recognition Is A Solved Problem:
A Fact Or Convenient Fiction?
Time & Place: 1135 - 1235, Antechinus Room
Chair: Roberto Togneri
Moderator: Roger Moore
Panelists:
Hynek Hermansky (Oregon Graduate Institute)
Sadaoki Furui (Tokyo Institute of Technology)
Chin-Hui Lee (Bell Laboratories)
Clive Summerfield (Syrinx Speech Systems)
We4A - Large Vocabulary Continuous Speech
Recognition 1
Time & Place: 1330 - 1500, Antechinus Room
Chair: Sadaoki Furui
1330
We4A1
Real-Time Recognition of Broadcast News
Cook, G Robinson, T Christie, J
Cambridge University, UNITED KINGDOM
1345
We4A2
Automatic Recognition of Korean Broadcast News Speech
Yu, H-J Kim, H Choi, J-S Hong, J-M Park, K-S Lee, J-S Lee, Y-G Lee, H-Y
LG Corporate Institute of Technology, KOREA
1400
We4A3
Telephone-Based Conversational Speech Recognition in the JUPITER
Domain
Glass, J R Hazen, T J
MIT, USA
1415
We4A4
Japanese Large-Vocabulary Continuous Speech Recognition System
Based on Microsoft Whisper
Hon, H Ju, Y Otani, K
Microsoft Research, USA
1430
We4A5
Partitioning and Transcription of Broadcast News Data
Gauvain, J-L Lamel, L Adda, G
LIMSI-CNRS, FRANCE
We4B - Speaker and Language Recognition 2
Time & Place: 1330 - 1500, Bandicoot Room
Chair: Marc Zissman
1330
We4B1
Speaker Detection in Broadcast Speech Databases
Rosenberg, A E Magrin-Chagnolleau, I Parthsarathy, S Huang, Q
AT&T Labs-Research, USA
1345
We4B2
Multilateral Techniques for Speaker Recognition
Parris, E S Carey, M J
Ensigma, UNITED KINGDOM
1400
We4B3
Real Time Speaker Indexing based on subspace method - Application to
TV News Articles and Debate -
Nishida, M Ariki, Y
Ryukoku University, JAPAN
1415
We4B4
SHEEP, GOATS, LAMBS and WOLVES: A Statistical Analysis of
Speaker Performance in the NIST 1998 Speaker Recognition Evaluation
Doddington, G Liggett, W Martin, A Przybocki, M Reynolds, D
MIT Lincoln Laboratory, USA
1430
We4B5
Progress in Speaker Recognition at Dragon Systems
Corrada-Emmanuel, A Newman, M Peskin, B Gillick, L Roth, R
Dragon Systems, USA
1445
We4B6
A Comparative Study of Speaker Verification Systems using the Polycost
Database
Nordström, T Melin, H Lindberg, J
KTH, SWEDEN
We4C - Signal Processing and Speech Analysis 2
Time & Place: 1330 - 1500, Currawong Room
Chair: Kazuyo Tanaka
1300
We4C1
Improving Pitch Estimation with Short Duration Speech Samples
Ainsworth, W A Day, C R Meyer, G F
Keele University, UNITED KINGDOM
1345
We4C2
An instantaneous-frequency-based pitch extraction method for
high-quality speech transformation: revised TEMPO in the STRAIGHT-suite
Kawahara, H de Cheveigne, A Patterson, R
Wakayama University, JAPAN
1400
We4C3
Speaker-Independent Speech Recognition using Micro Segment Spectrum
Integration
Aikawa, K
NTT Human Interface Laboratories, JAPAN
1415
We4C4
On Robust Speech Analysis Based on Time-Varying Complex AR Model
Funaki, K Miyanaga, Y Tochinai, K
Hokkaido University, JAPAN
1430
We4C5
Spectral Basis Functions from Discriminant Analysis
Hermansky, H Malayath, N
Oregon Graduate Institute, USA
We4D - Prosody and Emotion 5
Time & Place: 1330 - 1500, Dingo Room
Chair: Daniel Hirst
1330
We4D1
The Tilt Intonation Model
Taylor, P
University of Edinburgh, UNITED KINGDOM
1345
We4D2
Analysis of Occurrences of Pauses and Their Durations in Japanese Text
Reading
Fujisaki, H Ohno, S Yamada, S
Science University of Tokyo, JAPAN
1400
We4D3
A statistical study of pitch target points in five languages
Campione, E Véronis, J
Université De Provence, FRANCE
1415
We4D4
Fully Automatic Prosody Generator for Text-to-Speech
Malfrere, F Dutoit, T Mertens, P
Faculte Polytechnique De Mons, BELGIUM
1430
We4D5
Automatic Prosodic Labeling of 6 Languages
Vereecken, H Martens, J-P Grover, C Fackrell, J Van Coile, B
Elis-University of Ghent, BELGIUM
1445
We4D6
Automatic Utterance Type Detection Using Suprasegmental Features
Wright, H
The University of Edinburgh, UNITED KINGDOM
We4P- Robust Speech Processing in Adverse
Environments 4
Time & Place: 1330 - 1700, Platypus Room
Chair: Keikichi Hirose
We4P1
Spectral Sequence Compensation based on Continuity of Spectral
Sequence
Akagi, M Iwaki, M Sakaguchi, N
Japan Advanced Institute of Science and Technology, JAPAN
We4P2
Robust Features for Speech Recognition Systems
Bayya, A Yegnanarayana, B
Rockwell Semiconductor Systems, USA
We4P3
Interfacing of CASA and Partial Recognition Based on a Multistream
Technique
Berthommier, F Glotin, H Tessier, E Bourlard, H
Institut De La Communication Parlee, FRANCE
We4P4
An RNN-based compensation method for Mandarin telephone speech
recognition
Chang, S-C Chien, S-C Kuo, C-C
Industrial Technology Research Institute, TAIWAN R.O.C.
We4P5
Robust Speech Recognition Using Discriminative Stream Weighting and
Parameter Interpolation
Chu, S Zhao, Y
University of Illinois, USA
We4P6
Acoustic backing-off in the local distance computation for robust
automatic speech recognition
de Veth, J Cranen, B Boves, L
University of Nijmegen, THE NETHERLANDS
We4P7
Noise Model Selection for Robust Speech Recognition
Docio-Fernandez,L Garcia-Mateo,C
University of Vigo, SPAIN
We4P8
A novel iterative signal enhancement algorithm for noise reduction in
speech
Doclo, S Dologlou, I Moonen, M
KU Leuven - ESAT/SISTA, BELGIUM
We4P9
Missing Data Reconstruction for Robust Automatic Speech Recognition
in the Framework of Hybrid HMM/ANN Systems
Dupont, S
Faculte Polytechnique De Mons, BELGIUM
We4P10
Recognition from GSM Digital Speech
Gallardo-Antolin, A Diaz-de-Maria, F Valverde-Albacete, F
Universidad Carlos III De Madrid, SPAIN
We4P11
Conversational Speech Systems for On-Board Car Navigation and
Assistance
Geutner, P Denecke, M Meier, U Westphal, M Waibel, A
Universitaet Karlsruhe, GERMANY
We4P12
A signal processing system for having the sound "pop-out"
in noise thanks to the image of the speaker’s lips: New advances using Multi-Layer Perceptrons
Girin, L Varin, L Feng, G Schwartz, J L
Institut De La Communication Parlée, FRANCE
We4P13
Robust Speech Activity Detection in the Presence of Noise
Sarikaya, R Hansen, J H L
Robust Speech Processing Laboratory, USA
We4P14
Robust Automatic Speech Recognition by the Application of a
Temporal-Correlation-Based Recurrent Multilayer Neural Network to
the Mel-based Cepstral Coefficients
Heon, M Tolba, H O'Shaughnessy, D
INRS-Telecommunication, CANADA
We4P15
Speech Recognition from GSM Codec Parameters
Huerta, J M Stern, R M
Carnegie Mellon University, USA
We4P16
Improved Parallel Model Combination Based on Better Domain
Transformation for Speech Recognition Under Noisy Environments
Hung, J W Shen, J L Lee, L S
Academia Sinica, TAIWAN R.O.C.
We4P17
Robust Speech/Non-Speech Detection in Adverse Conditions Based on
Noise and Speech Statistics
Karray, L Monne, J
France Telecom - CNET, FRANCE
We4P18
Speech Recognition in Car Noise Environments using Multiple Models
According to Noise Masking Levels
Song, M G Jung, H I Shim, K-J Kim, H S
Pusan National University, KOREA
We4P19
Spectral Noise Subtraction with Recursive Gain Curves
Linhard, K Haulick, T
Daimler Benz AG, GERMANY
We4P20
A Novel Robust Speech Recognition Algorithm Based on Multi-models
and Integrated Decision Method
Pan, S Liu, J Jiang, J-T Wang, Z-Y Lu, D-J
Tsinghua University, P.R. CHINA
We4P21
On the Interaction Between Time and Frequency Filtering of Speech
Parameters for Robust Speech Recognition
Macho, D Nadeu, C
Polytechnical University of Catalonia, SPAIN
We4P22
Inference of Missing Spectrographic Features for Robust Speech Recognition
Raj, B Singh, R Stern, R M
Carnegie Mellon University, USA
We4P23
SNR-dependent flooring and noise overestimation for joint application of
spectral subtraction and model combination
Schless, V Class, F
Daimler-Benz AG, GERMANY
We4P24
Improved Robust Speech Recognition Considering Signal Correlation
Approximated by Taylor Series
Shen, J-L Hung, J-W Lee, L-S
Academia Sinica, TAIWAN R.O.C.
We4P25
Speech Recognition in Noisy Environment Using Weighted
Projection-Based Likelihood Measure
Shin, W H Kim, W G Lee, C Cha, I W
Yonsei University, KOREA
We4P26
Evaluation of Model Adaptation by HMM Decomposition on Telephone
Speech Recognition
Takiguchi, T Nakamura, S Shikano, K Morishima, M Isobe, T
Nara Institute of Science and Technology, JAPAN
We4P27
Comparative Experiments to Evaluate a Voiced-Unvoiced-Based
Pre-Processing Approach to Robust Automatic Speech Recognition in
Low-SNR Environments
Tolba, H O'Shaughnessy, D
INRS-Telecommunications, CANADA
We4P28
Signal Extraction from Noisy Signal based on Auditory Scene Analysis
Unoki, M Akagi, M
Japan Advanced Institute of Science and Technology, JAPAN
We4P29
Frequency domain binaural model as the front end of speech recognition
system
Usagawa, T Sakai, K Ebata, M
Kumamoto University, JAPAN
We4P30
A Study on the Recognition of Low Bit-Rate Encoded Speech
Yu, A-T Wang, H-C
National Tsing Hua University, TAIWAN R.O.C.
We4P31
Weighted Parallel Model Combination for Noisy Speech Recognition
Hwang, T-H Wang, H-C
National Tsing-Hua University, TAIWAN R.O.C.
We4P32
Favourable and Unfavourable Short Duration Segments of Speech in
Noise
Woo, D
The University of New South Wales, AUSTRALIA
We4Q - Segmentation, Labelling and Speech Corpora 2
Time & Place: 1330 - 1700, Quokka Room
Chair: Paul Dalsgaard
We4Q1
An Efficient Labeling Tool for the QuickSig Speech Database
Karjalainen, M Altosaar, T Huttunen, M
Helsinki University of Technology, FINLAND
We4Q2
Collection and Detailed Transcription of a Speech Database for
Development of Language Learning Technologies
Bratt, H Neumeyer, L Shriberg, E Franco, H
SRI International, USA
We4Q3
Resegmentation of SWITCHBOARD
Deshmukh, N Ganapathiraju, A Gleeson, A Hamaker, J Picone, J
Mississippi State University, USA
We4Q4
Automatic Generation of Visual Scenarios for Spoken Corpora
Acquisition
Aiello, D Delogu, C De Mori, R Di Carlo, A Nisi, M Tummeacciu, S
Fondazione Ugo Bordoni, ITALY
We4Q5
Automatic Detection of Semantic Boundaries based on Acoustic and
Lexical Knowledge
Cettolo, M Falavigna, D
ITC-IRST, ITALY
We4Q6
A New Fast Algorithm for Automatic Segmentation of Continuous Speech
Gholampour, I Nayebi, K
Sharif University of Technology, IRAN
We4Q7
Acoustic Nature and Perceptual Testing of Corpora of Emotional Speech
Iida, A Campbell, W N Iga, S Higuchi, F Yasumura, M
Keio University, JAPAN
We4Q8
Korean Prosodic Break Index Labelling by a new Mixed Method of LDA
and VQ
Kang, P S Kang, J Y Kim, J Y
Chonnam National University, KOREA
We4Q9
MOOSE: Management of Otago Speech Environment
Laws, M R Kilgour, R I
University of Otago, NEW ZEALAND
We4Q10
Phonetic Alignment: Speech Synthesis Based vs. Hybrid HMM/ANN
Malfrere, F Deroo, O Dutoit, T
Faculte Polytechnique De Mons, BELGIUM
We4Q11
Customisation and Quality Assessment of Spoken Language Description
Millar, J B
Australian National University, AUSTRALIA
We4Q12
A Silence/Noise/Music/Speech Splitting Algorithm
Montacie, C Caraty, M-J
Universite Pierre Et Marie Curie, FRANCE
We4Q13
Audio-Visual Segmentation for Content-based Retrieval
Pye, D Hollinghurst, N Mills, T Wood, K
Oracle & Olivetti Research Laboratory, UNITED KINGDOM
We4Q14
Same News is Good News: Automatically Collecting Reoccuring Radio
News Stories
Rapp, S Dogil, G
Sony International (Europe) GmbH, GERMANY
We4Q15
An annotation system for melodic aspects of German spontaneous speech
Brindoepke, C Schaffranietz, B
University Bielefeld, GERMANY
We4Q16
Additional use of phoneme duration hypotheses in automatic speech
segmentation
Stöber, K Hess, W
Bonn University, GERMANY
We4Q17
Towards a minimal standard for dialogue transcripts:A new SGML
architecture for the HCRC Map Task Corpus
Isard, A McKelvie, D Thompson, H S
University of Edinburgh, UNITED KINGDOM
We4R - Speech Technology Applications and Human-
Machine Interface 1
Time & Place: 1330 - 1700, Rosella Room
Chair: Jordi Robert-Ribes
We4R1
Steps toward the integration of speaker recognition in real-world telecom
applications
Glaeser, A Bimbot, F
Ascom Systec Ltd, SWITZERLAND
We4R2
A Bimodal Korean Address Entry/Retrieval System
Chung, H Y Hwang, C J Lee, S W
Yeungnam University, KOREA
We4R3
Usability Evaluation of IVR systems with DTMF and ASR
Delogu, C Di Carlo, A Rotundi, P Sartori, D
Fondazione Ugo Bordoni, ITALY
We4R4
SALSA Version 1.0: A Speech-based Web Browser for Hong Kong
English
Fung, P Cheung, C S Lam, K L Liu, W K Lo, Y Y
University of Science & Technology, HONG KONG
We4R5
A Language for Creating Speech Applications
Pargellis, A Zhou, Q Saad, A Lee, C-H
Bell Labs, Lucent Technologies
We4R6
The use of automatic speech recognition to reduce the interference
between concurrent tasks of driving and phoning
Graham, R Carter, C Mellor, B
Loughborough University, UNITED KINGDOM
We4R7
Interactive Listening to Structured Speech Content on the Internet
Hirayama, M J Sugahara, T Peng, Z Yamazaki, J
Hewlett Packard Laboratories Japan, JAPAN
We4R8
MSF Format for the Representation of Speech Synchronized Moving
Image
Jo, C W
Changwon National University, KOREA
We4R9
Effects of Using Speech in Timetable Information Systems for WWW
Qvarfordt, P Jönsson, A
Linkoping University, SWEDEN
We4R10
The Interactive Systems Labs View4You video indexing system
Kemp, T Geutner, P Schmidt, M Tomaz, B Weber, M Westphal, M
Waibel, A
University of Karlsruhe, GERMANY
We4R11
SEMOLE: A Robust Framework for Gathering Information from the
World Wide Web
Kim, H J Hetherington, L
MIT Spoken Language Systems, USA
We4R12
Enhancing a WIMP Based Interface with Speech, Gaze Tracking and
Agents
Bakman, L Blidegn, M Wittrup, M Larsen, L B Moeslund, T B
Aalborg University, DENMARK
We4R13
Now You Hear It, Now You Don't: Empirical Studies of Audio Browsing
Behavior
Nakatani, C Whittaker, S Hirschberg, J
AT & T Labs - Research, USA
We4R14
A Voice Verifier for Face/Voice Based Person Verification System
Qiao, R-Y Choi, Y Agbinya, J I
CSIRO, Australia, AUSTRALIA
We4R15
On the use of automatic speech recognition for TV captioning
Robert-Ribes, J
CSIRO-MIS, AUSTRALIA
We4R16
An Undergraduate Course on Speech Recognition Based on the CSLU
Toolkit
Serridge, B
Universidad De Las Americas, MEXICO
We4R17
Real time voice alteration based on Linear Prediction
Yang, P-F Stylianou, Y
AT&T Labs - Research, USA
We4R18
Evaluation and Implementation of a Voice-Activated Dialing System with
Utterance Verification
Tan, B T Gu, Y Thomas, T
Vocalis Ltd, UNITED KINGDOM
We4R19
Towards A Mandarin Voice Memo System
Wang, H-M Lin, B-S Chen, B Bai, B-R
Academia Sinica, TAIWAN R.O.C.
We5A - Large Vocabulary Continuous Speech
Recognition 2
Time & Place: 1530 - 1700, Antechinus Room
Chair: Gary Cook
1530
We5A1
Grammatical word graph re-generation for spontaneous speech
recognition
Tsukada, H Yamamoto, H Takezawa, T Sagisaka, Y
ATR Interpreting Telecommunications Research Laboratories, JAPAN
1545
We5A2
Compression Algorithm of Trigram Language Models based on
Maximum Likelihood Estimation
Yodo, N Shikano, K Nakamura, S
Nara Institute of Science and Technology, JAPAN
1600
We5A3
Morphological Modeling of Word Classes for Langauge Models
Uebler, U Niemann, H
Bavarian Research Center for Knowledge Based Systems (FORWISS),
GERMANY
1615
We5A4
A Comparative Study Between Polyclass and Multiclass Language
Models
Zitouni, I Smaili, K Haton, J-P Deligne, S Bimbot, F
LORIA/INRIA Lorraine, FRANCE
1630
We5A5
Log-Linear Interpolation of Language Models
Klakow, D
Philips Research Laboratories, GERMANY
1645
We5A6
The Applicability of Adaptive Language Modelling for the Broadcast
News Task
Clarkson, P R Robinson, A J
Cambridge University, UNITED KINGDOM
We5B - Text-To-Speech Synthesis 3
Time & Place: 1530 - 1700, Bandicoot Room
Chair: Nick Campbell
1530
We5B1
The IBM Trainable Speech Synthesis System
Donovan, R E Eide, E M
IBM, USA
1545
We5B2
ProSynth: An Integrated Prosodic Approach to Device-Independent,
Natural-Sounding Speech Synthesis
Hawkins, S House, J Huckvale, M Local, J K Ogden, R
University of Cambridge, UNITED KINGDOM
1600
We5B3
Total Quality Evaluation of Speech Synthesis Systems
Zhang, J Dong, S Yu, G
Institute of Acoustics, P.R. CHINA
1615
We5B4
Comparative Evaluation of Synthetic Prosody with the PURR Method
Sonntag, G P Portele, T
IKP, University of Bonn, GERMANY
1630
We5B5
SABLE: A Standard for TTS Markup
Sproat, R Hunt, A Ostendorf, M Taylor, P Black, A Lenzo, K
Bell Laboratories / Lucent Technologies, USA
1645
We5B6
Prosodic vs. segmental contributions to naturalness in a diphone
synthesizer
Bunnell, H T Hoskins, S R Yarrington, D M
DuPont Hospital for Children / University of Delaware, USA
We5C - Language Acquisition 1
Time & Place: 1530 - 1700, Currawong Room
Chair: Jean Vroomen
1530
We5C1
Non-native productions of Japanese single stops that are too long for one
mora unit
Minagawa-Kawai, Y Kiritani, S
University of Tokyo, JAPAN
1545
We5C2
The Process of Generation and Development of Second Language
Japanese Accentuation
Yamada, N
Ibaraki University, JAPAN
1600
We5C3
Perceptual properties of Russians with Japanese fricatives
Funatsu, S Kiritani, S
Hiroshima Women's University, JAPAN
1615
We5C4
Assessment of Dutch pronunciation by means of automatic speech
recognition technology
Cucchiarini, C de Wet, F Strik, H Boves, L
University of Nijmegen, THE NETHERLANDS
1630
We5C5
Phonetic-level Mispronunciation Detection in non-native Swedish Speech
Langlais, P Öster, A-M Granström, B
Center for Speech Technology, TMH-KTH, SWEDEN
1645
We5C6
Computer-based second language production training by using
spectrographic representation and HMM-based speech recognition scores
Akahane-Yamada, R McDermott, E Adachi, T Kawahara, H Pruitt, J S
ATR Human Information Processing Research Laboratories, JAPAN
We5D - Acoustic Phonetics 1
Time & Place: 1530 - 1700, Dingo Room
Chair: Louis Pols
1530
We5D1
Assimilation of place in Japanese and Dutch
Cutler, A Otake, T
Max-Planck-Institute for Psycholinguistics, NETHERLANDS
1545
We5D2
Prosodic Constraint on V-to-V Coarticulation in Japanese
Kondo, Y Arai, Y
Musashino Art University, JAPAN
1600
We5D3
Postvocalic /r/-deletion in standard Dutch: how experimental phonology
can profit from ASR technology
Cucchiarini, C van den Heuvel, H
University of Nijmegen, THE NETHERLANDS
1615
We5D4
More evidence for the perceptual basis of sound change? Suprasegmental
effects in the development of distinctive nasalisation
Hajek, J Watson, I
University of Melbourne, AUSTRALIA
1630
We5D5
Speech production of vowel sequences using a physiological articulatory
model
Dang, J Honda, K
ATR Human Information Processing Research Labs,, JAPAN
We6A - Speaker Adaptation 2
Time & Place: 1700 - 1800, Antechinus Room
Chair: Frank Soong
1700
We6A1
Eigenvoices for Speaker Adaptation
Kuhn, R Nguyen, P Junqua, J-C Goldwasser, L Niedzielski, N Fincke, S
Field, K Contolini, M
Panasonic Technologies, Inc., USA
1715
We6A2
Speaker Clustering Using Direct Maximisation of the MLLR-Adapted
Likelihood
Johnson, S E Woodland, P C
Cambridge University, UNITED KINGDOM
1730
We6A3
Incremental On-line Speaker Adaptation in Adverse Conditions
Viikki, O Laurila, K
Nokia Research Center, FINLAND
1745
We6A4
Cluster Adaptive Training for Speech Recognition
Gales, M
IBM Almaden Research Center, USA
We6B - Speech Coding 2
Time & Place: 1700 - 1800, Bandicoot Room
Chair: Barry Cheetham
1700
We6B1
Towards a unified model for low bit-rate speech coding using a
recognition-synthesis approach
Holmes, W J
Defence Evaluation and Research Agency, UNITED KINGDOM
1715
We6B2
On the Significance of Temporal Masking in Speech Coding
Skoglund, J Kleijn, W B
Royal Insitute of Technology, SWEDEN
1730
We6B3
Waveform Interpolation Coding with Pitch-Spaced Subbands
Kleijn, W B Yang, H Deprettere, E F
Royal Insitute of Technology, SWEDEN
1745
We6B4
An improved Decomposition Method for WI using IIR Wavelet Filter
Banks
Chong, N R Burnett, I S Chicharo, J F
University of Wollongong, AUSTRALIA
We6C - Hidden Markov Model Techniques 2
Time & Place: 1700 - 1800, Currawong Room
Chair: Jeff Bilmes
1700
We6C1
Real -Time Probabilistic Segmentation for Segment-Based Speech
Recognition
Lee, S Glass, J
MIT, USA
1715
We6C2
Toward Markov random field modeling of speech
Gravier, G Sigelle, M Chollet, G
ENST/TSI and CNRS-URA 820, FRANCE
1730
We6C3
Hidden Markov Models for Trajectory Modeling
Iyer, R Gish, H Siu, M Zavaliagkos, G Matsoukas, S
GTE/BBN Technologies, USA
We6D - Multilingual Perception and Recognition 1
Time & Place: 1700 - 1800, Dingo Room
Chair: Valerie Hazan
1700
We6D1
Bilingual and Dialectal Adaptation and Retraining
Uebler, U Schuessler, M Niemann, H
Bavarian Research Center for Knowledge Based Systems (FORWISS),
GERMANY
1715
We6D2
Language Independent and Language Adaptive Large Vocabulary
Speech Recognition
Schultz, T Waibel, A
Interactive Systems Laboratories, GERMANY
1730
We6D3
A method for measuring the intelligibility and nonnativeness of phone
quality in foreign language pronunciation training
Kawai, G Hirose, K
University of Tokyo, JAPAN
Thursday 3 December, 1998
Th1A - Large Vocabulary Continuous Speech
Recognition 3
Time & Place: 0900 - 1030, Antechinus Room
Chair: Michael Wagner
0900
Th1A1
The BBN Single-Phonetic-Tree Fast-Match Algorithm
Nguyen, L Schwartz, R
BBN Technologies, USA
0915
Th1A2
An Efficient Two-pass Search Algorithm using Word Trellis Index
Lee, A Kawahara, T Shuji, D
Kyoto University, JAPAN
0930
Th1A3
Nozomi - a fast, memory-efficient stack decoder for LVCSR
Schuster, M
ATR Interpreting Telecommunications Research Laboratories, JAPAN
0945
Th1A4
Reducing the OOV Rate in Broadcast News Speech Recognition
Kemp, T Waibel, A
University of Karlsruhe, GERMANY
1000
Th1A5
Using Automatic-Derived Acoustic Sub-Word Units in Large Vocabulary
Speech Recognition
Bacchiani, M Ostendorf, M
Boston University, USA
1015
Th1A6
Fabricating conversational speech data with acoustic models: a program
to examine model-data mismatch
McAllaster, D Gillick, L Scattone, F Newman, M
Dragon Systems Inc, USA
Th1B - Articulatory Modelling 3
Time & Place: 0900 - 1030, Bandicoot Room
Chair: Philip Hoole
0900
Th1B1
An electropalatographic, kinematic, and acoustic analysis of
supralaryngeal correlates of word-level prominence contrasts in English
Harrington, J Beckman, M E Fletcher, J Palethorpe, S
Macquarie University, AUSTRALIA
0915
Th1B2
Consistencies and inconsistencies between EPG and locus equation data
on coarticulation
Tabain, M
Macquarie University, AUSTRALIA
0930
Th1B3
Synergy Between Jaw and Lips/ Tongue Movements : Consequences in
Articulatory Modelling
Bailly, G Badin, P Vilain, A
Institut Communication Parlee, FRANCE
0945
Th1B4
Modelling tongue configuration in German vowel production
Hoole, P
Munich University, GERMANY
1000
Th1B5
Optopalatograph: Real-time feedback of tongue movement in 3D
Wrench, A McIntosh, A D Watson, C Hardcastle, W J
Queen Margaret College, UNITED KINGDOM
1015
Th1B6
Effects of contrastive focal accent on linguopalatal articulation and
coarticulation in the French [kskl] Cluster
Meynadier, Y Pitermann, M Marchal, A
Institut De Phonetique - Laboratoire Parole Et Langage, CNRS, FRANCE
Th1C - Language Acquisition 2
Time & Place: 0900 - 1030, Currawong Room
Chair: Shigeru Kiritani
0900
Th1C1
Spoken Word Identification by Native and Nonnative Speakers of
English: Effects of training, modality, context and phonetic environment
Hardison, D M
University of California, Davis, USA
0915
Th1C2
The Effect of Background Knowledge on First and Second Language
Comprehension Difficulty
Tyler, M D
University of New South Wales, AUSTRALIA
0930
Th1C3
Comparsion of Cross-language Coarticulation: English, Japanese and
Japanese-accented English
Tsukada, K
Macquarie University, AUSTRALIA
0945
Th1C4
Plasticity of non-native phonetic perception and production: A training
study
Imaizumi, S Itoh, H Tamekawa, Y Deguchi, T Mori, K
University of Tokyo, JAPAN
1000
Th1C5
The Relation Between Perceptual and Production Categories in
Acquisition
Watson, I
University of Oxford, UNITED KINGDOM
1015
Th1C6
The development of perceptual cue-weighting in children aged 6 to 12
Hazan, V Barrett, S
Department of Phonetics and Linguistics, UCL, UNITED KINGDOM
Th1D - Speaker and Language Recognition 3
Time & Place: 0900 - 1030, Dingo Room
Chair: Ara Samoulian
0900
Th1D1
Robust speaker verification insensitive to session-dependent utterance
variation and handset-dependent distortion
Matsui, T Aikawa, K
NTT Human Interface Labs, JAPAN
0915
Th1D2
A Comparative Evaluation of Variance Flooring Techniques in
HMM-based Speaker Verification
Melin, H Koolwaaij, J Lindberg, J Bimbot, F
KTH, SWEDEN
0930
Th1D3
Text-Independent Speaker Verification Using Automatically Labelled
Acoustic Segments
Petrovska Delacretaz, D Cernocky, J Henneber, J Chollet, G
Institute of Radioelectronics, CZECH REPUBLIC
0945
Th1D4
A Fast Decoding Algorithm Based on Sequential Detection of the Changes
in Distribution
Li, Q
Bell Labs, Lucent Technologies, USA
1000
Th1D5
Speaker verification with ensemble classifiers based on linear speech
transforms
Olsen, J
Aalborg University, DENMARK
1015
Th1D6
Speaker recognition based on discriminative projection models
Olsen, J
Aalborg University, DENMARK
Th1P - Text-To-Speech Synthesis 4
Time & Place: 0900 - 1230, Platypus Room
Chair: Robert Mannell
Th1P1
A Mixed-Excitation Frequency Domain Model for Time-Scale Pitch-Scale
Modification of Speech
Acero, A
Microsoft Corporation, USA
Th1P2
Analytic Generation of Synthesis Units by Closed Loop Training for
Totally Speaker Driven Text to Speech System (TOS Drive TTS)
Akamine, M Kagoshima, T
Toshiba Kansai Laboratory, JAPAN
Th1P3
Modeling the Microprosody of Pitch and Loudness for Speech Synthesis
with Neural Networks
Vainio, M Altosaar, T
Helsinki University of Technology, FINLAND
Th1P4
Spectral Smoothing for Concatenative Speech Synthesis
Chappell, D T Hansen, J H L H
Robust Speech Processing Laboratory, USA
Th1P5
Mimic: A Voice-Adaptive Phonetic-Tree Speech Synthesiser
Chen, A Vaseghi, S Ho, C
Queen's University of Belfast, UNITED KINGDOM
Th1P6
Automatic Generation of Korean Pronunciation Variants by Multistage
Applications of Phonological Rules
Jeon, J Cha, S Chung, M Park, J Hwang, K
Sogang University, KOREA
Th1P7
Techniques for accurate automatic annotation of speech waveforms
Cox, S Brady, R Jackson, P
University of East Anglia, UNITED KINGDOM
Th1P8
Optimized Stopping Criteria for Tree-Based Unit Selection in
Concatenative Synthesis
Cronk, A Macon, M
Oregon Graduate Institute, USA
Th1P9
Automatic transcription of intonation using an identified prosodic
alphabet
de Tournemire, S
France Telecom, CNET, FRANCE
Th1P10
Frequency Analysis of Phonetic Units for Concatenative Synthesis in
Catalan
Esquerra, I Febrer, A Nadeu, C
Polytechnical University of Catalonia, SPAIN
Th1P11
Investigating the Syntactic Characteristics of English Tone Units
Fang, A C House, J Huckvale, M
University College London, UNITED KINGDOM
Th1P12
The UPC Text-to-Speech System for Spanish and Catalan
Bonafonte, A Esquerra, I Febrer, A Fonollosa, J A R Vallverdu, F
Polytechnical University of Catalonia, SPAIN
Th1P13
The New Version of the ROMVOX Text-To-Speech Synthesis System
Based on a Hybrid Time Domain-LPC Synthesis Technique
Ferencz, A Nagy, I Kovacs, T C S Ferencz, M Ratiu, T
Software ITC, ROMANIA
Th1P14
An F0 Contour Control Model for Totally Speaker Driven Text to Speech
System
Kagoshima, T Morita, M Seto, S Akamine, M
Toshiba Corporation, JAPAN
Th1P15
On the Relationship of Speech Rates with Prosodic Units in Dialogue
Speech
Hirose, K Kawanami, H
University of Tokyo, JAPAN
Th1P16
On the Reduction of Concatenation Artefacts in Diphone Synthesis
Klabbers, E Veldhuis, R
IPO, THE NETHERLANDS
Th1P17
Error Analysis and Confidence Measure of Chinese Word Segmentation
Kuo, C-C Ma, K-Y
Industrial Technology Research Institute, TAIWAN R.O.C.
Th1P18
Energy Contour Generation for a Sentence Using a Neural Network
Learning Method
Lee, J Kang, D Kim, S Sung, K-M
ETRI, KOREA
Th1P19
A computational algorithm for F0 contour generation in Korean
developed with prosodically labeled databases using K-ToBI system
Lee, Y-J Lee, S-H Kim, J-J Ho, H-J Kim, Y-I Kim, S-H Lee, J
Wonkwang University, KOREA
Th1P20
Rapid-Deployment Text-to-Speech in the DIPLOMAT System
Lenzo, K Hogan, C Allen, J
Carnegie Mellon University, USA
Th1P21
Formant diphone parameter extraction utilising a labelled single-speaker
database
Mannell, R
Macquarie University, AUSTRALIA
Th1P22
A New Synthetic Speech/Sound Control Language
Mizuno, O Nakajima, S
NTT Human Interface Labs, JAPAN
Th1P23
A study on the natural-sounding Japanese phonetic word synthesis by
using the VCV-balanced word database that consists of the words uttered
forcibly in two types of pitch accent
Mochizuki, R Arai, Y Honda, T
AVC Research Lab., CED, Matsushita Communication Industrial, JAPAN
Th1P24
Letter to Sound Rules for Accented Lexicon Compression
Pagel, V Lenzo, K Black, A W
Facultie Polytechnique of Mons, BELGIUM
Th1P25
A Name Announcement Algorithm With Memory Size and
Computational Power Constraints
Roth, Z Rosenhouse, J
DSP Semiconductors Ltd., ISRAEL
Th1P26
How a French TTS System Can Describe Loanwords
Sannier, F Belrhali, R Auberge, V
ICP - ESA 5009 CNRS, FRANCE
Th1P27
Improvements in Slovene Text-to-Speech Synthesis
Sef, T Dobnikar, A Gams, M
Jozef Stefan Institute, SLOVENIA
Th1P28
Automatic Rule Generation for Linguistic Features Analysis Using
Inductive Learning Technique - Linguistic Features Analysis in TOS
Drive TTS System
Seto, S Morita, M Kagoshima, T Akamine, M
Toshiba Corporation, JAPAN
Th1P29
Segmental Duration Control Based on an Articulatory Model
Shiga, Y Matsuura, H Nitta, T
Toshiba Corporation, JAPAN
Th1P30
Text Analysis for the Bell Labs French Text-to-Speech System
Tzoukermann, E
Bell Labs - Lucent Technologies, USA
Th1P31
Modeling vowel duration for Japanese text-to-speech synthesis
Venditti, J J van Santen, J P H
Ohio State University / Bell Labs, USA
Th1P32
Towards a Chinese Text-to-Speech System with Higher Naturalness
Wang, R-H Liu, Q Teng, Y Xia, D
University of Science & Technology of China, P.R. CHINA
Th1Q - Spoken Language Understanding Systems 4
Time & Place: 0900 - 1230, Quokka Room
Chair: Robert Dale
Th1Q1
Grammar Fragment Acquisition using Syntactic and Semantic Clustering
Arai, K Wright, J Riccardi, G Gorin, A
NTT Human Interface Laboratories, JAPAN
Th1Q2
Non-Expert Access to Unification-based Speech Understanding
Brøndsted, T
Aalborg University, DENMARK
Th1Q3
Natural Language Call Routing: A Robust, Self-Organizing Approach
Carpenter, B Chu-Carroll, J
Lucent Technologies - Bell Labs, USA
Th1Q4
Automatic Grammar Induction from Semantic Parsing
Ghosh, D Goddeau, D
Nuance Communications, USA
Th1Q5
BTH: An efficient parsing algorithm for word-spotting
Kono, Y Yano, T Sasajima, M
Toshiba Corporation, JAPAN
Th1Q6
Syntax Coordination: Interaction of Discourse and Extrapositions
Kronenberg, S C Kummert, F
University of Bielefeld, GERMANY
Th1Q7
Hierarchical Tag-Graph Search for Spontaneous Speech Understanding
in Spoken Dialog Systems
Lin, B-S Chen, B Wang, H-M Lee, L-S
National Taiwan University, TAIWAN R.O.C.
Th1Q8
Extraction of the dialog act and the topic from utterances in a spoken
dialog system
Niimi, Y Takinaga, N Nishimoto, T
Kyoto Institute of Technology, JAPAN
Th1Q9
Fast Computation of Maximum Entropy / Minimum Divergence Feature
Gain
Printz, H
Carnegie Mellon University, USA
Th1Q10
Stochastic Language Models for Speech Recognition and Understanding
Riccardi, G Gorin, A L
AT&T Labs-Research, USA
Th1Q11
Linguistically Engineered Tools for Speech Recognition Error Analysis
Van Ess-Dykema, C Ries, K
U.S. Department of Defense, USA
Th1Q12
Estimating Entropy of a Language from Optimal Word Insertion Penalty
Takeda, K Ogawa, A Itakura, F
Nagoya University, JAPAN
Th1Q13
A Linguistic Analysis of Repair Signals in Co-operative Spoken Dialogues
Tseng, S-C
University of Bielefeld, GERMANY
Th1Q14
A Hierarchical Language Model for CSR
Valverde-Albacete, F J Pardo, J M
Universidad Carlos III De Madrid, SPAIN
Th1Q15
Spoken Language Understanding Within Dialogues Using a Graphical
Model of Task Structure
Wright, J H Gorin, A L Abella, A
AT&T Labs - Research, USA
Th1Q16
Keyword Extraction of Radio News using Domain Identification based on
Categories of an Encyclopedia
Suzuki, Y Fukumoto, F Sekiguchi, Y
Yamanashi University, JAPAN
Th1R - Human Speech Perception 2
Time & Place: 0900 - 1230, Rosella Room
Chair: Kerrie Lee
Th1R1
Fundamental frequency flunctuation in continuous vowel utterance and
its perception
Akagi, M Iwaki, M Minakawa, T
Japan Advanced Institute of Science and Technology, JAPAN
Th1R2
Estimation of Mental Lexicon Size with Word Familiarity Database
Amano, S Kondo, T
NTT Basic Research Laboratories, JAPAN
Th1R3
Vowel Quality in Spontaneous Speech: What Makes a Good Vowel?
Aylett, M P Turk, A
University of Edinburgh, UNITED KINGDOM
Th1R4
Cooperation and Competition of Burst and Formant Transitions for the
Perception and the Identification of French Stops
Neagu, A Bailly, G
Institut Communication Parlee, FRANCE
Th1R5
The effect of modifying formant amplitudes on the perception of French
vowels generated by copy synthesis
Bonneau, A Laprie, Y
Loria & CNRS, FRANCE
Th1R6
Segmental and tonal processing in Cantonese
Chen, H-C Yip, M Wong, S-Y
Chinese University of Hong Kong, HONG KONG
Th1R7
Phonological similarity effects in Cantonese spoken-word processing
Yip, M Leung, P-Y Chen, H-C
Chinese University of Hong Kong, HONG KONG
Th1R8
On the learnability of the voicing contrast for initial stops
Damper, R I Gunn, S R
University of Southampton, UNITED KINGDOM
Th1R9
Acoustic and Perceptual Characteristics of Italian Stop Consonants
Cerrato, L Falcone, M
Fondazione Ugo Bordoni, ITALY
Th1R10
Acoustic cues for the auditory identification of the Spanish fricative /f/
Fernandez, S Feijoo, S Balsa, R Barros, N
Universidad de Santiago, SPAIN
Th1R11
Recognition of vowels in fricative context
Fernandez, S Feijoo, S Balsa, R Barros, N
Universidad De Santiago, SPAIN
Th1R12
Voicing affects perceived manner of articulation
Fernandez, S Feijoo, S Almeida, P
Universidad De Santiago, SPAIN
Th1R13
Enhancement techniques to improve the intelligibility of consonants in
noise: Speaker and listener effects
Hazan, V Simpson, A Huckvale, M
Department of Phonetics and Linguistics, UCL, UNITED KINGDOM
Th1R14
Boundaries of Perception of Long Tones in Taiwanese Speech
Jian F
University of Reading, UNITED KINGDOM
Th1R15
Effects of phonetic quality and duration on perceptual acceptability of
temporal changes in speech
Kato, H Tsuzaki, M Sagisaka, Y
ATR Human Information Processing Research Labs, JAPAN
Th1R16
Dynamic vs. Static Spectral Detail in the Perception of Gated Stops
Kiefte, M Neary, T M
University of Alberta, CANADA
Th1R17
Phonological Units in Speech Segmentation and Phonological Awareness
Otake, T Yoneyama, K
Dokkyo University, JAPAN
Th1R18
How Far Do Speakers Back Up in Repairs? A Quantitative Model
Shriberg, E Stolcke, A
SRI International, USA
Th1R19
Don’t blame it (all) on the pause: Further ERP evidence for a
prosody-induced garden-path in running speech
Steinhauer, K Alter, K Friederici, A D
Max-Planck-Institute of Cognitive Neuroscience, GERMANY
Th1R20
The role of stress for lexical selection in Dutch
Vroomen, J de Gelder, B
University of Tilburg, THE NETHERLANDS
Th1R21
The perception of stressed syllables in Finnish
Tuomainen, J Vroomen, J de Gelder, B
University of Tilburg, THE NETHERLANDS
Th1R22
The perception of the morae with devocalized vowels in Japanese
language
Yamakawa, K Baba, R
Prefectural University of Kumamoto, JAPAN
Th2A - Large Vocabulary Continuous Speech
Recognition 4
Time & Place: 1100 - 1230, Antechinus Room
Chair: Richard Stern
1100
Th2A1
High Resolution Decision Tree based Acoustic Modeling beyond CART
Chou, W Reichl, W
Bell Labs, Lucent Technologies, USA
1115
Th2A2
Unsupervised Training of a Speech Recognizer Using TV Broadcasts
Kemp, T Waibel, A
University of Karlsruhe, GERMANY
1130
Th2A3
A New Method to Achieve Fast Acoustic Matching for Speech Recognition
Lee, C Z O'Shaughnessy, D
INRS-Telecommunications, CANADA
1145
Th2A4
Improved Parameter Tying for Efficient Acoustic Model Evaluation in
Large Vocabulary Continuous Speech Recognition
Duchateau, J Demuynck, K Van Compernolle, D Wambacq, P
Kath. Univ. Leuven - ESAT/PSI, BELGIUM
1200
Th2A5
A New Look at HMM Parameter Tying for Large Vocabulary Speech
Recognition
Sankar, A
SRI International, USA
1215
Th2A6
Factor Analysis Invariant to Linear Transformations of Data
Gopinath, R A Ramabhadran, B Dharanipragada, S
IBM T. J. Watson Research Center, USA
Th2B - Spoken Language Understanding Systems 2
Time & Place: 1100 - 1230, Bandicoot Room
Chair: Sandra Williams
1100
Th2B1
Automatic Ambiguity Detection
Sproat, R van Santen, J
Bell Laboratories / Lucent Technologies, USA
1115
Th2B2
Empowering Knowledge Based Speech Understanding through Statistics
Fischer, J Haas, J Noth, E Niemann, H Deinzer, P
University of Erlangen, GERMANY
1130
Th2B3
Concept-driven speech understanding incorporated with a statistic
language model
Nagai, A Ishikawa, Y
Mitsubishi Electric Corporation, JAPAN
1145
Th2B4
On the Limitations of Stochastic Conceptual Finite-State Language
Models for Speech Understanding
Colas, J Ferreiros, J Montero, J M Pastor, J Gallardo, A Pardo, J M
GTH-IEL-UPM, SPAIN
1200
Th2B5
Towards Speech Understanding across multiple languages
Ward, T Roukos, S Neti, C Gros, J Epstein, M Dharanipragada, S
IBM T.J. Watson Research Center, USA
1215
Th2B6
Automatic Detection of Sentence Boundaries and Disfluencies Based on
Recognized Words
Stolcke, A Shriberg, E Bates, R Ostendorf, M Hakkani, D Plauche, M Tur,
G Lu, Y
SRI International, USA
Th2C - Signal Processing and Speech Analysis 3
Time & Place: 1100 - 1230, Currawong Room
Chair: Wolfgang Hess
1100
Th2C1
Determination of articulator positions from speech acoustics by applying
dynamic articulatory constraints
Suzuki, S Okadome, T Honda, M
NTT Basic Research Laboratories, JAPAN
1115
Th2C2
Recognizing Emotions in Speech Using Short-term and Long-term
Features
Li, Y Zhao, Y
University of Illinois, USA
1130
Th2C3
PeriphEar : A Nonlinear Active Model of the Auditory Periphery
Robert, A R Eriksson, J L E
CIRC, EPFL, SWITZERLAND
1145
Th2C4
The Voicing Feature for Stop Consonants: Acoustic Phonetic Analyses
and Automatic Speech Recognition Experiments
Ramesh, P Niyogi, P
Lucent Technologies, USA
1200
Th2C5
Wavelet-based Energy Binning Cepstral Features for Automatic Speech
Recognition
Basu, S Maes, S
IBM T.J. Watson Research Center, USA
1215
Th2C6
Articulatory Analysis using a Codebook for Articulatory based Low
Bit-Rate Speech Coding
Silva, C Chennoukh, S
Universidade Do Minho, PORTUGAL
Th2D - Human Speech Perception 3
Time & Place: 1100 - 1215, Dingo Room
Chair: Philip Rubin
1100
Th2D1
Categorical perception: Important phenomenon or lasting myth?
Massaro, D W
University of California, Santa Cruz, USA
1115
Th2D2
Categorical Perception of Vowels
Gerrits, E Schouten, B
Utrecht University, THE NETHERLANDS
1130
Th2D3
Suprasegmental Cues for the Segmentation of Identical Vowel Sequences
in Japanese
Kakehi, K Hirose, Y
Nagoya University, JAPAN
1145
Th2D4
Perception of concurrent approximant-vowel syllables
Ainsworth, W A
Keele University, UNITED KINGDOM
1200
Th2D5
Perceived Swedish Vowel Quantity: Effects of Postvocalic Consonant
Duration
Behne, D M Czigler, P E Sullivan, K P H
Norwegian University of Science & Technology, SWEDEN
Th4A - Speaker Adaptation 3
Time & Place: 1330 - 1500, Antechinus Room
Chair: Jean-Claude Junqua
1330
Th4A1
On-line hierarchical transformation of hidden Markov models for
speaker adaptation
Chien, J-T
National Cheng Kung University, TAIWAN R.O.C.
1345
Th4A2
High-Speed Speaker Adaptation Using Phoneme-Dependent
Tree-Structured Speaker Clustering
Suzuki, M Abe, T Mori, H Makino, S Aso, H
Tohoku University, JAPAN
1400
Th4A3
The Use of Confidence Measures in Unsupervised Adaptation of Speech
Recognizers
Anastasakos, T Balakrishnan, S
Motorola, Lexicus Division, USA
1415
Th4A4
Speaker Normalization with All-Pass Transforms
McDonough, J Byrne, W Luo, X
Johns Hopkins University, USA
1430
Th4A5
The CHAM model of hyperarticulate adaptation during human-computer
error resolution
Oviatt, S L
Oregon Graduate Institute of Science & Technology, USA
Th4B - Spoken Language Understanding Systems 3
Time & Place: 1330 - 1500, Bandicoot Room
Chair: Richard Sproat
1330
Th4B1
Language Modeling for Content Extraction in Human-Computer
Dialog