The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (1996)
Atlanta, GA, USA
May 7, 1996 to May 10, 1996
ISBN: 0-7803-3192-3
TABLE OF CONTENTS

Feature parameter curve method for high performance NN-based speech recognition (Abstract)

Shan Zhu , Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
pp. 1-4

HMM-based speech recognition using state-dependent, linear transforms on Mel-warped DFT features (Abstract)

C. Rathinavelu , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
pp. 9-12

Mixed Malvar-wavelets for non-stationary signal representation (Abstract)

J.A. Thripuraneni , Sch. of Electr. Eng., Oklahoma Univ., Norman, OK, USA
pp. 13-16

Experiments on a parametric nonlinear spectral warping for an HMM-based speech recognizer (Abstract)

D.J. Mashao , Div. of Eng., Brown Univ., Providence, RI, USA
pp. 17-20

Robust distant-talking speech recognition (Abstract)

J. Pearson , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
pp. 21-24

Time-frequency representation based cepstral processing for speech recognition (Abstract)

A.B. Fineberg , Lexicus Div., Motorola Inc., Palo Alto, CA, USA
pp. 25-28

Knowledge-based parameters for HMM speech recognition (Abstract)

N.N. Bitar , Dept. of Electr. Comput. & Syst. Eng., Boston Univ., MA, USA
pp. 29-32

A phoneme-similarity based ASR front-end (Abstract)

T.H. Applebaum , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
pp. 33-36

A model of dynamic auditory perception and its application to robust speech recognition (Abstract)

B. Strope , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
pp. 37-40

Independent calculation of power parameters on PMC method (Abstract)

H. Yamamoto , Media Technol. Lab., Canon Inc., Kanagawa, Japan
pp. 41-44

Noisy speech recognition using variance adapted likelihood measure (Abstract)

Jen-Tzung Chien , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 45-48

Improved speech recognition via speaker stress directed classification (Abstract)

B.D. Womak , Robust Speech Process. Lab., Duke Univ., Durham, NC, USA
pp. 53-56

High-accuracy connected digit recognition for mobile applications (Abstract)

S.K. Gupta , Adv. Multi-Media Commun. Dept., AT&T Bell Labs., Middletown, NJ, USA
pp. 57-60

Noise and room acoustics distorted speech recognition by HMM composition (Abstract)

S. Nakamura , Graduate Sch. of Inf. Sch., Nara Inst. of Sci. & Technol., Japan
pp. 69-72

Developments in continuous speech dictation using the 1995 ARPA NAB news task (Abstract)

J.L. Gauvain , Lab. d'Inf. pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 73-76

Speaker background models for connected digit password speaker verification (Abstract)

A.E. Rosenberg , Speech Res. Dept., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 81-84

Cohort selection and word grammar effects for speaker recognition (Abstract)

J.M. Colombi , Air Force Inst. of Technol., Wright-Patterson AFB, OH, USA
pp. 85-88

Speaker identification via support vector classifiers (Abstract)

M. Schmidt , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 105-108

Speaker recognition in reverberant enclosures (Abstract)

P.J. Castellano , Signal Process. Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia
pp. 117-120

Decoding optimal state sequence with smooth state likelihoods (Abstract)

I. Zeljkovic , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 129-132

Minimizing search errors due to delayed bigrams in real-time speech recognition systems (Abstract)

M. Woszczyna , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 137-140

Efficient evaluation of the LVCSR search space using the NOWAY decoder (Abstract)

S. Renals , Dept. of Comput. Sci., Sheffield Univ., UK
pp. 149-152

Developments in large vocabulary, continuous speech recognition of German (Abstract)

L. Lamel , Lab. d'Inf. pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
M. Adda-Decker , Lab. d'Inf. pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
J.L. Gauvain , Lab. d'Inf. pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
G. Adda , Lab. d'Inf. pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 153-156

Speech recognition on Mandarin Call Home: a large-vocabulary, conversational, and telephone speech corpus (Abstract)

Fu-Hua Liu , Human Language Technol. Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P. Srinivasa , Human Language Technol. Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Picheny , Human Language Technol. Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Monkowski , Human Language Technol. Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
J. Chen , Human Language Technol. Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 157-160

Multilingual stochastic n-gram class language models (Abstract)

M. Jardino , Lab. d'Inf. pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 161-163

A variable-length category-based n-gram language model (Abstract)

T.R. Niesler , Dept. of Eng., Cambridge Univ., UK
P.C. Woodland , Dept. of Eng., Cambridge Univ., UK
pp. 164-167

Improving n-gram models by incorporating enhanced distributions (Abstract)

J. Ming , Sch. of Electr. Eng. & Comput. Sci., Queen's Univ., Belfast, UK
F.J. Smith , Sch. of Electr. Eng. & Comput. Sci., Queen's Univ., Belfast, UK
J. McMahon , Sch. of Electr. Eng. & Comput. Sci., Queen's Univ., Belfast, UK
P. O'Boyle , Sch. of Electr. Eng. & Comput. Sci., Queen's Univ., Belfast, UK
pp. 168-171

A novel word clustering algorithm based on latent semantic analysis (Abstract)

N.B. Coccaro , Interactive Media Group, Apple Comput. Inc., Cupertino, CA, USA
J.W. Butzberger , Interactive Media Group, Apple Comput. Inc., Cupertino, CA, USA
Yen-Lu Chow , Interactive Media Group, Apple Comput. Inc., Cupertino, CA, USA
J.R. Bellegarda , Interactive Media Group, Apple Comput. Inc., Cupertino, CA, USA
D. Naik , Interactive Media Group, Apple Comput. Inc., Cupertino, CA, USA
pp. 172-175

Statistical natural language understanding using hidden clumpings (Abstract)

S. Della Pietra , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Epstein , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
S. Roukos , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
T. Ward , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
K. Papineni , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 176-179

Clustering words for statistical language models based on contextual word similarity (Abstract)

D. O'Shaughnessy , INRS Telecommun., Ile des Soeurs, Que., Canada
A. Farhat , INRS Telecommun., Ile des Soeurs, Que., Canada
J.-F. Isabelle , INRS Telecommun., Ile des Soeurs, Que., Canada
pp. 180-183

Domain word translation by space-frequency analysis of context length histograms (Abstract)

P. Fung , Dept. of Comput. Sci., Columbia Univ., New York, NY, USA
pp. 184-187

Variable-order N-gram generation by word-class splitting and consecutive word grouping (Abstract)

Y. Sgisaka , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
H. Masataki , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
pp. 188-191

Back-off method for n-gram smoothing based on binomial posteriori distribution (Abstract)

M. Tamoto , NTT Basic Res. Labs., Atsugi, Japan
T. Kawabata , NTT Basic Res. Labs., Atsugi, Japan
pp. 192-195

Ergodic multigram HMM integrating word segmentation and class tagging for Chinese language modeling (Abstract)

Chorkin Chan , Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
M. Tamoto , Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
pp. 196-199

A 2.4 kbit/s MELP coder candidate for the new U.S. Federal Standard (Abstract)

V. Viswanathan , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Kwan Truong , Personal Syst. Lab., Texas Instrum. Inc., Dallas, TX, USA
A. McCree , Personal Syst. Lab., Texas Instrum. Inc., Dallas, TX, USA
T.P. Barnwell , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
E.B. George , Personal Syst. Lab., Texas Instrum. Inc., Dallas, TX, USA
pp. 200-203

Harmonic-stochastic excitation (HSX) speech coding below 4 kbit/s (Abstract)

R. Salami , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
J.-P. Adoul , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
C. Laflamme , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
R. Matmti , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
pp. 204-207

A high quality MBE-LPC-FE speech coder at 2.4 kbps and 1.2 kbps (Abstract)

Chongxi Feng , Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
Tian Wang , Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
Kun Tang , Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
pp. 208-211

A low-complexity waveform interpolation coder (Abstract)

W.B. Kleijn , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
R. Hagen , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
Y. Shoham , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
D. Sen , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 212-215

Mixed-domain coding of speech at 3 kb/s (Abstract)

J.C. De Martin , Dipartimento di Elettronica, Politecnico di Torino, Italy
A. Gersho , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 216-219

Source driven variable bit rate prototype interpolation coding (Abstract)

Binshi Cao , Speech Process. Group, Manchester Univ., UK
C. Xydeas , Speech Process. Group, Manchester Univ., UK
pp. 220-223

A new approach to very low-rate speech coding using temporal decomposition (Abstract)

S. Ghaemmaghami , Signal Process. Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia
M. Deriche , Signal Process. Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia
pp. 224-227

A variable frame pitch estimator and test results (Abstract)

Xiaoshu Qian , Dept. of Electr. Eng., Rhode Island Univ., Kingston, RI, USA
R. Kumaresan , Dept. of Electr. Eng., Rhode Island Univ., Kingston, RI, USA
pp. 228-231

Robust method of measurement of fundamental frequency by ACLOS: autocorrelation of log spectrum (Abstract)

N. Kunieda , Dept. of Inf. & Comput. Sci., Saitama Univ., Urawa, Japan
J. Suzuki , Dept. of Inf. & Comput. Sci., Saitama Univ., Urawa, Japan
T. Shimamura , Dept. of Inf. & Comput. Sci., Saitama Univ., Urawa, Japan
pp. 232-235

Lag-indexed VQ for pitch filter coding (Abstract)

S. McClellan , Dept. of Electr. & Comput. Eng., Alabama Univ., Birmingham, AL, USA
J.D. Gibson , Dept. of Inf. & Comput. Sci., Saitama Univ., Urawa, Japan
pp. 236-239

Embedded algebraic vector quantizers (EAVQ) with application to wideband speech coding (Abstract)

Minjie Xie , Dept. of Electr. & Comput. Eng., Sherbrooke Univ., Que., Canada
J.-P. Adoul , Dept. of Electr. & Comput. Eng., Sherbrooke Univ., Que., Canada
pp. 240-243

The two-dimensional discrete cosine transform applied to speech data (Abstract)

L. Baghai-Ravary , Dept. of Electron. & Electr. Eng., Sheffield Univ., UK
M.O. Tokhi , Dept. of Inf. & Comput. Sci., Saitama Univ., Urawa, Japan
S.W. Beet , Dept. of Electron. & Electr. Eng., Sheffield Univ., UK
pp. 244-247

Real-time high accurate cell loss recovery technique for speech over ATM networks (Abstract)

K. Matsumoto , Adv. LSI Lab., NTT LSI Labs., Kanagawa, Japan
pp. 248-250

16 kbit/s wideband speech coding based on unequal subbands (Abstract)

J. Schnitzler , Inst. of Commun. Syst. & Data Process., Tech. Hochschule Aachen, Germany
J.W. Paulus , Inst. of Commun. Syst. & Data Process., Tech. Hochschule Aachen, Germany
pp. 255-258

Low delay IIR QMF banks with high perceptive quality for speech processing (Abstract)

T. Kleinmann , Inst. fur Angewandte Phys., Frankfurt Univ., Germany
A. Lacroix , Inst. fur Angewandte Phys., Frankfurt Univ., Germany
pp. 259-262

Demodulators for AM-FM models of speech signals: a comparison (Abstract)

Shan Lu , Comsat, Clarksburg, MD, USA
P.C. Doerschuk , Inst. fur Angewandte Phys., Frankfurt Univ., Germany
pp. 263-266

Synthesis and coding of continuous speech with the nonlinear oscillator model (Abstract)

G. Kubin , Inst. of Commun. & High-Frequency Eng., Vienna Univ. of Technol., Austria
pp. 267-270

Variable frame rate parameter encoding via adaptive frame selection using dynamic programming (Abstract)

V.R. Viswanathan , Lab. of Personal Syst., Texas Instrum. Inc., Dallas, TX, USA
A.V. McCree , Lab. of Personal Syst., Texas Instrum. Inc., Dallas, TX, USA
E.B. George , Lab. of Personal Syst., Texas Instrum. Inc., Dallas, TX, USA
pp. 271-274

Transform predictive coding of wideband speech signals (Abstract)

Dongmei Wang , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
Juin-Hwey Chen , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 275-278

A system for unrestricted topic retrieval from radio news broadcasts (Abstract)

D.A. James , UBILAB, Union Bank of Switzerland, Zurich, Switzerland
pp. 279-282

Automated generation of N-best pronunciations of proper nouns (Abstract)

J. Picone , Mississippi State Univ., MS, USA
M. Weber , Mississippi State Univ., MS, USA
N. Deshmukh , Mississippi State Univ., MS, USA
pp. 283-286

An efficient voice retrieval system for very-large-vocabulary Chinese textual databases with a clustered language model (Abstract)

Keh-Jiann Chen , Mississippi State Univ., MS, USA
Lee-Feng Chien , Mississippi State Univ., MS, USA
Sung-Chien Lin , Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Lin-Shan Lee , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 287-290

Concept-based phrase spotting approach for spontaneous speech understanding (Abstract)

S. Doshita , Dept. of Inf. Sci., Kyoto Univ., Japan
N. Kitaoka , Dept. of Inf. Sci., Kyoto Univ., Japan
T. Kawahara , Dept. of Inf. Sci., Kyoto Univ., Japan
pp. 291-298

Keyword spotting for video soundtrack indexing (Abstract)

P. Gelin , Inst. Eurecom, Sophia Antipolis, France
C.J. Wellekens , Inst. Eurecom, Sophia Antipolis, France
pp. 299-302

Improvements in switchboard recognition and topic identification (Abstract)

S. Lowe , Dragon Syst. Inc., Newton, MA, USA
V. Nagesha , Dragon Syst. Inc., Newton, MA, USA
B. Peskin , Dragon Syst. Inc., Newton, MA, USA
L. Gillick , Dragon Syst. Inc., Newton, MA, USA
D. McAllaster , Dragon Syst. Inc., Newton, MA, USA
S. Connolly , Dragon Syst. Inc., Newton, MA, USA
pp. 303-306

Statistical models for topic identification using phoneme substrings (Abstract)

M.J. Carey , Ensigma Ltd., Chepstow, UK
E.S. Parris , Ensigma Ltd., Chepstow, UK
J.H. Wright , Ensigma Ltd., Chepstow, UK
pp. 307-310

Robust talker-independent audio document retrieval (Abstract)

K. Spark Jones , Ensigma Ltd., Chepstow, UK
J.T. Foote , Dept. of Eng., Cambridge Univ., UK
G.J.F. Jones , Dept. of Eng., Cambridge Univ., UK
S.J. Young , Dragon Syst. Inc., Newton, MA, USA
pp. 311-314

Unsupervised topic clustering of switchboard speech messages (Abstract)

B.A. Carlson , Lincoln Lab., MIT, Lexington, MA, USA
pp. 315-318

Speaker recognition and speaker normalization by projection to speaker subspace (Abstract)

Y. Ariki , Dept. of Electron. & Inf., Ryukoku Univ., Otsu, Japan
M. Nishijima , Dept. of Electron. & Inf., Ryukoku Univ., Otsu, Japan
S. Tagashira , Dept. of Electron. & Inf., Ryukoku Univ., Otsu, Japan
pp. 319-322

Compensated mel frequency cepstrum coefficients (Abstract)

R. Vergin , INRS Telecommun., Ile des Soeurs, Que., Canada
D. O'Shaughnessy , INRS Telecommun., Ile des Soeurs, Que., Canada
V. Gupta , INRS Telecommun., Ile des Soeurs, Que., Canada
pp. 323-326

Adaptation method based on HMM composition and EM algorithm (Abstract)

Y. Minami , NTT Human Interface Labs., Tokyo, Japan
S. Furui , NTT Human Interface Labs., Tokyo, Japan
pp. 327-330

SNR-normalisation for robust speech recognition (Abstract)

D. Van Compernolle , Katholieke Univ., Leuven, Heverlee, Belgium
T. Claes , Katholieke Univ., Leuven, Heverlee, Belgium
pp. 331-334

Towards robustness to fast speech in ASR (Abstract)

E. Fosler , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
N. Morgan , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
N. Mirghafori , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
pp. 335-338

Speaker normalization on conversational telephone speech (Abstract)

S. Wegmann , Dragon Syst. Inc., Newton, MA, USA
B. Peskin , Dragon Syst. Inc., Newton, MA, USA
J. Orloff , Dragon Syst. Inc., Newton, MA, USA
D. McAllaster , Dragon Syst. Inc., Newton, MA, USA
pp. 339-341

Speaker and gender normalization for continuous-density hidden Markov models (Abstract)

Xuedong Huang , Microsoft Corp., Redmond, WA, USA
A. Acero , Microsoft Corp., Redmond, WA, USA
pp. 342-345

A parametric approach to vocal tract length normalization (Abstract)

E. Eide , BBN Syst. & Technol. Corp., Cambridge, MA, USA
H. Gish , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 346-348

A study of speech recognition for children and the elderly (Abstract)

C.N. Jacobsen , AT&T Bell Labs., Murray Hill, NJ, USA
J.G. Wilpon , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 349-352

Speaker normalization using efficient frequency warping procedures (Abstract)

Li Lee , AT&T Bell Labs., Murray Hill, NJ, USA
R.C. Rose , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 353-356

A fast stochastic parser for determining phrase boundaries for text-to-speech synthesis (Abstract)

R.A. Sharman , IBM UK Labs. Ltd., Winchester, UK
J.H. Wright , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 357-360

Speech concatenation and synthesis using an overlap-add sinusoidal model (Abstract)

M.A. Clements , Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
M.W. Macon , Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 361-364

Voice conversion using partitions of spectral feature space (Abstract)

J. Mertens , Fac. of Appl. Sci., Vrije Univ., Brussels, Belgium
W. Verhelst , Fac. of Appl. Sci., Vrije Univ., Brussels, Belgium
pp. 365-368

Determination of vocal-tract shapes from formant frequencies based on perturbation theory and interpolation method (Abstract)

Zhenli Yu , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, Hong Kong
P.C. Ching , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, Hong Kong
pp. 369-372

Unit selection in a concatenative speech synthesis system using a large speech database (Abstract)

A.W. Black , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, Hong Kong
A.J. Hunt , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
pp. 373-376

Parametric hybrid source models for voiced and voiceless fricative consonants (Abstract)

S. Narayanan , AT&T Bell Labs., Murray Hill, NJ, USA
A. Alwan , Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, Hong Kong
pp. 377-380

High-quality speech synthesis using context-dependent syllabic units (Abstract)

T. Saito , Res. Lab., IBM Japan Ltd., Tokyo, Japan
Y. Hashimoto , Res. Lab., IBM Japan Ltd., Tokyo, Japan
M. Sakamoto , Res. Lab., IBM Japan Ltd., Tokyo, Japan
pp. 381-384

Articulatory copy synthesis using a nine-parameter vocal tract model (Abstract)

Dongbing Wei , Dept. of Electr. Eng. & Electron., Liverpool Univ., UK
C.C. Goodyear , Dept. of Electr. Eng. & Electron., Liverpool Univ., UK
pp. 385-388

Speech synthesis using HMMs with dynamic features (Abstract)

T. Kobayashi , Res. Lab., IBM Japan Ltd., Tokyo, Japan
S. Imai , Dragon Syst. Inc., Newton, MA, USA
T. Masuko , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
K. Tokuda , Dept. of Electr. Eng. & Electron., Liverpool Univ., UK
pp. 389-392

Interpolating V/UV mixture functions of a harmonic model for concatenative speech synthesis (Abstract)

Cheung-Fat Chan , Dept. of Electron. Eng., City Univ. of Hong Kong, Hong Kong
King-Fai Lam , Dept. of Electron. Eng., City Univ. of Hong Kong, Hong Kong
pp. 393-396

An efficient top-down parsing algorithm for understanding speech by using stochastic syntactic and semantic models (Abstract)

H. Stahl , Inst. of Human-Machine-Commun., Munich Univ. of Technol., Germany
J. Muller , Inst. of Human-Machine-Commun., Munich Univ. of Technol., Germany
M. Lang , Inst. of Human-Machine-Commun., Munich Univ. of Technol., Germany
pp. 397-400

Data-driven discourse modeling for semantic interpretation (Abstract)

J. Alvarez-Cercadillo , Inst. of Human-Machine-Commun., Munich Univ. of Technol., Germany
J. Caminero-Gil , Speech Technol. Group, Telefonica Investigacion y Desarrollo, Madrid, Spain
D. Tapias-Merino , Dragon Syst. Inc., Newton, MA, USA
C. Crespo-Casas , Inst. of Human-Machine-Commun., Munich Univ. of Technol., Germany
pp. 401-404

Statistical language modeling for speech disfluencies (Abstract)

E. Shriberg , Inst. of Human-Machine-Commun., Munich Univ. of Technol., Germany
A. Stolcke , Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA
pp. 405-408

JANUS-II-translation of spontaneous conversational speech (Abstract)

M. Maier , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Lavie , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
P. Zhan , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. McNair , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Waibel , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Sloboda , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
K. Shima , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
D. Gates , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Woszczyna , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Zeppenfeld , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Gavalda , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
L. Levin , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
L. Mayfield , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Finke , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
I. Rogina , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Kemp , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 409-412

Language model acquisition from a text corpus for speech understanding (Abstract)

T. Matsuoka , NTT Human Interface Labs., Tokyo, Japan
S. Furui , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Hasson , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Barlow , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 413-15A

A class based language model for speech recognition (Abstract)

S. Issar , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
W. Ward , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 416-418

An integrated model of acoustics and language using semantic classification trees (Abstract)

E. Noth , Lehrstuhl fur Mustererkennung, Erlangen-Nurnberg Univ., Germany
R. De Mori , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Gebhard , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
J. Fischer , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
H. Niemann , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Kompe , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Harbeck , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Kuhn , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Mast , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 419-422

Combining stochastic and linguistic language models for recognition of spontaneous speech (Abstract)

W. Eckert , Lehrstuhl fur Mustererkennung, Erlangen-Nurnberg Univ., Germany
F. Gallwitz , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
H. Niemann , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 423-426

Error correction via a post-processor for continuous speech recognition (Abstract)

E.K. Ringger , Dept. of Comput. Sci., Rochester Univ., NY, USA
J.F. Allen , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 427-430

Integration of concept-driven semantic interpretation with speech recognition (Abstract)

A. Nagai , Media Technol. Dept., Mitsubishi Electr. Corp., Kanagawa, Japan
I. Ishikawa , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
K. Nakajima , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 431-434

A second-order HMM for high performance word and phoneme-based continuous speech recognition (Abstract)

D. Fohr , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
J.-C. Junqua , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
J.-F. Mari , INRIA Lorraine, Vandoeuvre-les-Nancy, France
pp. 435-438

Evaluation of segmental unit input HMM (Abstract)

K. Yamamoto , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Nakagawa , Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan
pp. 439-442

Design of a speech recognition system based on acoustically derived segmental units (Abstract)

M. Ostendorf , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Y. Sagisaka , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
K. Paliwal , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Bacchiani , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
pp. 443-446

Modeling speech variability with segmental HMMs (Abstract)

M.J. Russell , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
W.J. Holmes , Speech Res. Unit, DRA Malvern, UK
pp. 447-450

Context-dependent units for vocabulary-independent Spanish speech recognition (Abstract)

J.M. Elvira , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
L.H. Gomez , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
J.C. Torrecilla , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
L. Villarrubia , Speech Technol. Group, Telefonica Investigacion y Desarrollo, Madrid, Spain
pp. 451-454

Context-dependent acoustic models for Chinese speech recognition (Abstract)

Taiyi Huang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Fei Qu , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
Bin Ma , Inst. of Autom., Acad. Sinica, Beijing, China
Bo Xu , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
Xijun Zhang , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 455-458

Automatic recognition of Danish natural numbers for telephone applications (Abstract)

C.N. Jacobsen , AT&T Bell Labs., Murray Hill, NJ, USA
J.G. Wilpon , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 459-462

Explicit modeling of coarticulation in a statistical speech recognizer (Abstract)

L.H. Jamieson , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Ruxin Chen , Sch. of Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA
pp. 463-466

Tied-structure HMM based on parameter correlation for efficient model training (Abstract)

S. Takahashi , NTT Human Interface Labs., Kanagawa, Japan
S. Sagayama , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 467-470

A semi-continuous stochastic trajectory model for phoneme-based continuous speech recognition (Abstract)

O. Siohan , CRIN, Vandoeuvre les Nancy, France
Yifan Gong , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 471-474

Automatic evaluation of speaker recognizability of coded speech (Abstract)

K.T. Assaleh , Speech & Signal Process. Lab., Motorola, Scottsdale, AZ, USA
pp. 475-478

A perceptually-based objective measure for speech coders using abductive network (Abstract)

M.M. Meky , City Coll., City Univ. of New York, NY, USA
T.N. Saadawi , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 479-482

Objectively measured descriptors applied to speaker characterization (Abstract)

M.A. Clements , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
B.F. Necioglu , Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
M.A. Clements , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 483-486

Objective speech quality measure for cellular phone (Abstract)

K.H. Lam , Dept. of Electr. & Electron. Eng., Hong Kong Univ. of Sci. & Technol., Kowloon, Hong Kong
K.F. Hui , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
O.C. Au , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
C.C. Chan , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
S.F. Lau , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 487-490

Vector quantization techniques for output-based objective speech quality (Abstract)

Chiyi Jin , Dept. of Electr. Eng., Wyoming Univ., Laramie, WY, USA
R. Kubichek , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 491-494

Objective measures for speech quality assessment in wireless communications (Abstract)

A. Bayya , US West Adv. Technol., Boulder, CO, USA
M. Vis , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 495-498

Performance assessment of 4.8 kbit/s AMBE coding under aeronautical environmental conditions (Abstract)

S.F. Campos Neto , COMSAT Lab., Clarksburg, MD, USA
J. Phipps , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Dimolitsas , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
F.L. Corcoran , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 499-502

Robust recognition of cellular telephone speech by adaptive vector quantization (Abstract)

R. Rajasekaran , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
J.S. Baras , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M.K. Sonmez , Speech Res. Lab., Texas Instrum. Inc., Dallas, TX, USA
pp. 503-506

Efficient decoding and training procedures for utterance verification in continuous speech recognition (Abstract)

R.C. Rose , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
E. Lleida , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 507-510

Confidence measures for the SWITCHBOARD database (Abstract)

S. Cox , Speech Res. Dept., AT&T Bell Labs., NJ, USA
R. Rose , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 511-514

A phone-dependent confidence measure for utterance rejection (Abstract)

Z. Rivlin , Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA
V. Abrash , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Chung , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Cohen , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 515-517

Utterance verification of keyword strings using word-based minimum verification error (WB-MVE) training (Abstract)

A.R. Setlur , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Chin-Hui Lee , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M.G. Rahim , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
R.A. Sukkar , AT&T Bell Labs., Naperville, IL, USA
pp. 518-521

Fast implementation methods for Viterbi-based word-spotting (Abstract)

S.J. Young , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
K.M. Knill , Dept. of Eng., Cambridge Univ., UK
pp. 522-525

Improving wordspotting performance with artificially generated data (Abstract)

R.P. Lippmann , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
E.I. Chang , Nuance Commun., Menlo Park, CA, USA
pp. 526-529

Modelling unknown words in spontaneous speech (Abstract)

A. Jusek , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Kemp , Dept. of Comput. Sci., Karlsruhe Univ., Germany
pp. 530-533

Improved modeling of OOV words in spontaneous speech (Abstract)

P. Fetter , Daimler-Benz AG, Ulm, Germany
T. Kuhn , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Kaltenmeier , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
P. Regel-Brietzmann , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 534-537

Two-pass strategy for continuous speech recognition with detection and transcription of unknown words (Abstract)

H. Sakamoto , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Matsunaga , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
pp. 538-541

A modified generalised Lloyd algorithm for VQ codebook design (Abstract)

Koh Soo-Ngee , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Chen Chang-Qian , Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
P. Sivaprakasapillai , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 542-545

Robust classification of speech based on the dyadic wavelet transform with application to CELP coding (Abstract)

J. Stegmann , Deutsche Telekom AG, Darmstadt, Germany
G. Schroder , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
K.A. Fischer , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 546-549

Optimal wavelet packets for low-delay audio coding (Abstract)

F. Moreau de Saint-Martin , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
P. Philippe , CCETT, Cesson Sevigne, France
J. Soumagne , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Lever , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 550-553

A fast VSELP speech coder based on mutually orthonormal regular pulse vectors (Abstract)

J. Soumagne , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
J. Soumagne , Dept. of Electron. Eng., Yonsei Univ., Seoul, South Korea
J. Soumagne , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 554-557

Dual-Pulse CS-CELP: a toll-quality low-complexity speech coder at 7.8 kbit/s (Abstract)

J. Ikedo , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
K. Mano , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Kataoka , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Hayashi , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
H. Ohmuro , NTT Human Interface Labs., Tokyo, Japan
T. Moriya , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 558-561

Low-delay CELP with multi-pulse VQ and fast search for GSM EFR (Abstract)

S. Taumi , Inf. Technol. Res. Labs., NEC Corp., Kanagawa, Japan
M. Serizawa , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
K. Ozawa , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Nomura , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 562-565

Speech compression with cosine and wavelet packet near-best bases (Abstract)

C. Taswell , Dept. of Comput. Sci., Stanford Univ., CA, USA
pp. 566-568

An enhanced full rate speech coder for digital cellular applications (Abstract)

C. Liu , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
W. LeBlanc , Personal Syst. Lab., Texas Instrum. Inc., Dallas, TX, USA
V. Viswanathan , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 569-572

Optimum harmonics tracking filter for auditory scene analysis (Abstract)

K. Nishi , Dept. of Commun. & Syst. Eng., Univ. of Electro-Commun., Tokyo, Japan
S. Aida , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Ando , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 573-576

Selective error protection of ITU-T G.729 codec for digital cellular channels (Abstract)

K. Swaminathan , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Austin , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
K. Swaminathan , Hughes Network Syst. Inc., Germantown, MD, USA
pp. 577-580

A Dictionary Based Method For Determining Topics In Text And Transcribed Speech (Abstract)

D. Nelson , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
P. Schone , Hughes Network Syst. Inc., Germantown, MD, USA
pp. 295-580
97 ms
(Ver )