The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (1999)
Phoenix, AZ, USA
Mar. 15, 1999 to Mar. 19, 1999
ISBN: 0-7803-5041-3
TABLE OF CONTENTS

Analysis by synthesis speech coding with generalized pitch prediction (Abstract)

P. Mermelstein , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 1-4

A 6.1 to 13.3-kb/s variable rate CELP codec (VR-CELP) for AMR speech coding (Abstract)

S. Heinen , Inst. of Commun. Syst. & Data Process, Aachen Univ. of Technol., Germany
pp. 9-12

CELP speech coding based on an adaptive pulse position codebook (Abstract)

T. Amada , Kansai Res. Lab., Toshiba Corp., Kobe, Japan
pp. 13-16

A multistage search of algebraic CELP codebooks (Abstract)

M.A. Ramirez , Escola Politecnica, Sao Paulo Univ., Brazil
pp. 17-20

A fast search method of algebraic codebook by reordering search sequence (Abstract)

M. Gerken , Inf. Process. Sector, Samsung Adv. Inst. of Technol., Kyungki, South Korea
pp. 21-24

An 8 kbit/s ACELP coder with improved background noise performance (Abstract)

R. Hagen , Audio & Visual Technol. Res., Ericsson Radar Syst. AB, Stockholm, Sweden
pp. 25-28

On phase perception in speech (Abstract)

H. Pobloth , Dept. of Speech Music & Hearing, R. Inst. of Technol., Stockholm, Sweden
pp. 29-32

Large vocabulary speech recognition in French (Abstract)

M. Adda-Decker , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 45-48

Real-time telephone-based speech recognition in the Jupiter domain (Abstract)

J.R. Glass , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
pp. 61-64

Template-driven generation of prosodic information for Chinese concatenative synthesis (Abstract)

Chung-Hsien Hu , Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan
pp. 65-68

Enhancement of esophageal speech using formant synthesis (Abstract)

K. Matsui , Central Res. Lab., Matsushita Electr. Ind. Co. Ltd., Seika, Japan
pp. 81-84

Noise suppression using a time-varying, analysis/synthesis gamma chirp filterbank (Abstract)

T. Irino , ATR Human Inf. Process. Res. Lab., Kyoto, Japan
pp. 97-100

Author Index (Abstract)

pp. a1-a13

Experimental comparison of signal subspace based noise reduction methods (Abstract)

P.S.K. Hansen , Dept. of Math. Modelling, Tech. Univ., Lyngby, Denmark
pp. 101-104

Initial evaluation of hidden dynamic models on conversational speech (Abstract)

J. Picone , Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA
pp. 109-112

Convolutional density estimation in hidden Markov models for speech recognition (Abstract)

S. Matsoukas , BBN Technol./GTE Internetworking, Cambridge, UK
pp. 113-116

Automatic clustering and generation of contextual questions for tied states in hidden Markov models (Abstract)

R. Singh , Sch. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 117-120

Hidden Markov models with divergence based vector quantized variances (Abstract)

J. Kim , Philips Consumer Commun., Piscataway, NJ, USA
pp. 125-128

HMM training based on quality measurement (Abstract)

Yuqing Gao , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 129-132

Voice recognition focusing on vowel strings on a fixed-point 20-MIPS DSP board (Abstract)

Y. Nishida , Speech & Acoust. Lab., NTT Human Interface Labs., Kanagawa, Japan
pp. 137-140

Speech interface VLSI for car applications (Abstract)

M. Shozakai , LSI Labs., Asahi Chem. Ind. Co. Ltd., Kanagawa, Japan
pp. 141-144

Recognizing connected digits in a natural spoken dialog (Abstract)

M. Rahim , AT&T Labs.-Res., Florham Park, NJ, USA
pp. 153-156

Telephone speech recognition using neural networks and hidden Markov models (Abstract)

DongSuk Yuk , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
pp. 157-160

An new method used in HMM for modeling frame correlation (Abstract)

Guo Qing , Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
pp. 169-172

N-best based supervised and unsupervised adaptation for native and non-native speakers in cars (Abstract)

P. Nguyen , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
pp. 173-176

TTS based very low bit rate speech coder (Abstract)

Ki-Seung Lee , AT&T Labs.-Res., Florham Park, NJ, USA
pp. 181-184

Wideband speech coding with toll quality based on IA-model (Abstract)

R.V. Cox , Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
pp. 185-188

4 kb/s multi-pulse based CELP speech coding using excitation switching (Abstract)

K. Ozawa , C&C Media Res. Labs., NEC Corp., Kanagawa, Japan
pp. 189-192

On speech coding in a perceptual domain (Abstract)

G. Kubin , Tech. Univ. Wien, Austria
pp. 205-208

Modelling energy flow in the vocal tract with applications to glottal closure and opening detection (Abstract)

D.M. Brookes , Dept. of Electr. & Electron. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
pp. 213-216

Fitting the Mel scale (Abstract)

S. Umesh , Dept. of Electr. Eng., Indian Inst. of Technol., Kanpur, India
pp. 217-220

Fast accent identification and accented speech recognition (Abstract)

D. Nelson , Dept. of Electr. & Electron. Eng., Univ. of Sci. & Technol. of China, Hefei, China
pp. 221-224

Relevancy of time-frequency features for phonetic classification measured by mutual information (Abstract)

H. Yang , Dept. of Comput. Sci. & Eng., Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
pp. 225-228

An algorithm for glottal volume velocity estimation (Abstract)

A. Alkhairy , MIT, Cambridge, MA, USA
pp. 233-236

Frame level noise classification in mobile environments (Abstract)

K. El-Maleh , Dept. of Electr. & Comput. Eng., McGill Univ., Montreal, Que., Canada
pp. 237-240

An improved mixed excitation linear prediction (MELP) coder (Abstract)

T. Unno , Center for Signal & Image Process., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 245-248

Split band LPC based adaptive multi-rate GSM candidate (Abstract)

S. Villette , Centre for Commun. Syst. Res., Surrey Univ., Guildford, UK
pp. 249-252

Robust closed-loop pitch estimation for harmonic coders by time scale modification (Abstract)

Chunyan Li , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
pp. 257-260

Phase adjustment in waveform interpolation (Abstract)

Hong-Goo Kang , AT&T Labs.-Res., Florham Park, NJ, USA
pp. 261-264

Dispersion phase vector quantization for enhancement of waveform interpolative coder (Abstract)

O. Gottesmann , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
pp. 269-272

The Teager energy based feature parameters for robust speech recognition in car noise (Abstract)

F. Jabloun , Dept. of Electr. Eng., Bilkent Univ., Ankara, Turkey
pp. 273-276

Avoiding distortions due to speech coding and transmission errors in GSM ASR tasks (Abstract)

A. Gallardo-Antolin , Dept. de Tecnologias de las Commun., Univ. Carlos III de Madrid, Spain
pp. 277-280

Speaker normalized spectral subband parameters for noise robust speech recognition (Abstract)

S. Tsuge , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
pp. 285-288

Temporal patterns (TRAPs) in ASR of noisy speech (Abstract)

H. Hermansky , Graduate Inst. of Sci. & Technol., Portland, OR, USA
pp. 289-292

Signal modeling for isolated word recognition (Abstract)

M. Karnjanadecha , Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
pp. 293-296

Transforming HMMs for speaker-independent hands-free speech recognition in the car (Abstract)

Y. Gong , Speech Res., Media Technols. Lab., Texas Instrum. Inc., Dallas, TX, USA
pp. 297-300

Channel and noise adaptation via HMM mixture mean transform and stochastic matching (Abstract)

J.J. Godfrey , Dept. of Electr. & Electron. Eng., Hong Kong Univ. of Sci. & Technol., Clearwater Bay, Hong Kong
pp. 301-304

Speaker verification performance and the length of test sentence (Abstract)

Jialong He , Dept. of Spech & Hearing Sci., Arizona State Univ., Tempe, AZ, USA
pp. 305-308

A hybrid score measurement for HMM-based speaker verification (Abstract)

Yong Gu , Vocalis Ltd., Cambridge, UK
pp. 317-320

Polynomial classifier techniques for speaker verification (Abstract)

W.M. Campbell , SSG, Motorola Inc., Scottsdale, AZ, USA
pp. 321-324

Discriminative mixture weight estimation for large Gaussian mixture models (Abstract)

F. Beaufays , Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA
pp. 337-340

Modeling disfluency and background events in ASR for a natural language understanding task (Abstract)

R.C. Rose , Res. Dept., AT&T Bell Labs., Florham Park, NJ, USA
pp. 341-344

Decision tree state tying based on penalized Bayesian information criterion (Abstract)

Wu Chou , Lucent Technols., Bell Labs., Murray Hill, NJ, USA
pp. 345-348

A 2D extended HMM for speech recognition (Abstract)

Jiayu Li , Dept. of Stat., Chicago Univ., IL, USA
pp. 349-352

Probabilistic classification of HMM states for large vocabulary continuous speech recognition (Abstract)

Xiaoqiang Luo , Dept. of Electr. & Comput. Eng., Johns Hopkins Univ., Baltimore, MD, USA
pp. 353-356

The HDM: a segmental hidden dynamic model of coarticulation (Abstract)

H.B. Richards , Dragon Syst. UK, Cheltenham, UK
pp. 357-360

Maximum likelihood estimates for exponential type density families (Abstract)

S. Basu , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 361-364

On the limits of speech recognition in noise (Abstract)

S.D. Peters , Nortel Technol., Montreal, Que., Canada
pp. 365-368

Recognition of spectrally degraded speech in noise with nonlinear amplitude mapping (Abstract)

Qian-Jie Fu , Dept. of Auditory Implants & Perception, House Ear Inst., Los Angeles, CA, USA
pp. 369-372

Shape invariant time-scale modification of speech using a harmonic model (Abstract)

D. O'Brien , Sch. of Comput. Applications, Dublin City Univ., Ireland
pp. 381-384

Using a sigmoid transformation for improved modeling of phoneme duration (Abstract)

K.E.A. Silverman , Spoken Language Group, Apple Comput. Inc., Cupertino, CA, USA
pp. 385-388

Nonlinear dynamic modeling of the voiced excitation for improved speech synthesis (Abstract)

K. Narasimhan , Comput. Neuroeng. Lab., Florida Univ., Gainesville, FL, USA
pp. 389-392

Results on perceptual invariants to transformations on speech (Abstract)

A. Robert , Dept. of Electr. Eng., Fed. Inst. of Technol., Lausanne, Switzerland
pp. 393-396

Investigations on inter-speaker variability in the feature space (Abstract)

R. Haeb-Umbach , Philips Res. Lab., Aachen, Germany
pp. 397-400

Two-dimensional multi-resolution analysis of speech signals and its application to speech recognition (Abstract)

C.P. Chan , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, Hong Kong
pp. 405-408

Hierarchical subband linear predictive cepstral (HSLPC) features for HMM-based speech recognition (Abstract)

R. Chengalvarayan , Speech Process. Group, Lucent Technol., Naperville, IL, USA
pp. 409-412

Towards a robust/fast continuous speech recognition system using a voiced-unvoiced decision (Abstract)

D. O'Shaughnessy , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 413-416

A C/V segmentation algorithm for Mandarin speech signal based on wavelet transforms (Abstract)

H. Tolba , Dept. of Electr. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan
pp. 417-420

Feature extraction for speech recognition based on orthogonal acoustic-feature planes and LDA (Abstract)

T. Nitta , Multimeda Eng. Lab., Toshiba Corp., Kawasaki, Japan
pp. 421-424

Distinctive feature detection using support vector machines (Abstract)

P. Niyogi , Bell Labs., Lucent Technol., USA
pp. 425-428

Time-varying noise compensation using multiple Kalman filters (Abstract)

P. Ramesh , Dept. of Electr. Eng., Seoul Nat. Univ., South Korea
pp. 429-432

A segment-based C/sub 0/ adaptation scheme for PMC-based noisy Mandarin speech recognition (Abstract)

Wei-Tyng Hong , Dept. of Commun. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
pp. 433-436

Speech recognition and enhancement by a nonstationary AR HMM with gain adaptation under unknown noise (Abstract)

G. Ruske , Inst. for Human-Machine-Commun., Munich Univ. of Technol., Germany
pp. 441-444

Training of HMM with filtered speech material for hands-free recognition (Abstract)

D. Giuliani , ITC-IRST, Centro per la Ricerca Sci. e Technol., Trento, Italy
pp. 449-452

Incremental enrolment of speech recognizers (Abstract)

C. Mokbel , CNET, Lannion, France
pp. 453-456

Automatic speech recognition: a communication perspective (Abstract)

B.S. Atal , AT&T Labs., Florham Park, NJ, USA
pp. 457-460

Split band CELP (SB-CELP) speech coder (Abstract)

M.R. Nakhai , Dept. of Electron. & Electr. Eng., King's Coll., London, UK
pp. 461-464

Log amplitude modeling of sinusoids in voiced speech (Abstract)

N. Malik , Sch. of Electr. & Telecommun. Eng., New South Wales Univ., Sydney, NSW, Australia
pp. 465-468

1.2 kbit/s harmonic coder using auditory filters (Abstract)

M. Kohata , Chiba Inst. of Technol., Narashino, Japan
pp. 469-472

Exponential sinusoidal modeling of transitional speech segments (Abstract)

J. Jensen , Center for PeronKommunikaion, Aalborg Univ., Denmark
pp. 473-476

Harmonic+noise coding using improved V/UV mixing and efficient spectral quantization (Abstract)

E.W.M. Yu , Dept. of Electron. Eng., City Univ. of Hong Kong, Kowloon, Hong Kong
pp. 477-480

A 4 kb/s toll quality harmonic excitation linear predictive speech coder (Abstract)

S. Yeldener , COMSAT Lab., Clarksburg, MD, USA
pp. 481-484

High quality MELP coding at bit-rates around 4 kb/s (Abstract)

J. Stachurski , Texas Instrum. Inc., Dallas, TX, USA
pp. 485-488

Pitch quantization in low bit-rate speech coding (Abstract)

T. Eriksson , AT&T Labs. Res., Florham Park, NJ, USA
pp. 489-492

HMM and neural network based speech act detection (Abstract)

K. Ries , Language Tech. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 497-500

Improving the suitability of imperfect transcriptions for information retrieval from spoken documents (Abstract)

M. Siegler , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 505-508

Automatic topic identification for two-level call routing (Abstract)

J. Golden , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 509-512

Named entity tagged language models (Abstract)

Y. Gotoh , Dept. of Comput. Sci., Sheffield Univ., UK
pp. 513-516

Speech translation: coupling of recognition and translation (Abstract)

H. Ney , Lehrstuhl fur Inf. VI, Tech. Hochschule Aachen, Germany
pp. 517-520

Probabilistic models for topic detection and tracking (Abstract)

F. Walls , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 521-524

Combination of words and word categories in varigram histories (Abstract)

R. Blasig , Philips Res. Lab., Aachen, Germany
pp. 529-532

Multi-class composite N-gram based on connection direction (Abstract)

H. Yamamoto , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
pp. 533-536

Smoothing methods in maximum entropy language modeling (Abstract)

S.C. Martin , Lehrstuhl fur Inf., Tech. Hochschule Aachen, Germany
pp. 545-548

Efficient sampling and feature selection in whole sentence maximum entropy language models (Abstract)

S.F. Chen , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 549-552

A maximum entropy language model integrating N-grams and topic dependencies for conversational speech recognition (Abstract)

S. Khudanpur , Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA
pp. 553-556
96 ms
(Ver 3.1 (10032016))