The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (1993)
Minneapolis, MN, USA
Apr. 27, 1993 to Apr. 30, 1993
ISBN: 0-7803-0946-4
TABLE OF CONTENTS

A long history quantization approach to scalar and vector quantization of LSP coefficients (Abstract)

K. So , Dept. of Electr. Eng., Univ. of Manchester, UK
C. Xydeas , Dept. of Electr. Eng., Univ. of Manchester, UK
pp. 1-4

Efficient coding of LPC parameters using adaptive prefiltering and MSVQ with partially adaptive codebook (Abstract)

T. Taniguchi , Fujitsu Lab. Ltd., Kawasaki, Japan
Y. Tanaka , Fujitsu Lab. Ltd., Kawasaki, Japan
pp. 5-8

Immittance spectral pairs (ISP) for speech encoding (Abstract)

S. Peller , Dept. of Electr. Eng., Tel Aviv Univ., Israel
Y. Bistritz , Dept. of Electr. Eng., Tel Aviv Univ., Israel
pp. 9-12

Robust vector quantization in spectral coding (Abstract)

R. Hagen , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
P. Hedelin , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
pp. 13-16

Vector quantization of speech LSP parameters using trellis codes and l/sub 1/-norm constraints (Abstract)

J. Pan , Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA
T.R. Fischer , Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA
pp. 17-20

A combined quantization-interpolation scheme for very low bit rate coding of speech LSP parameters (Abstract)

J.M. Lopez-Soler , Dept. Electron. y Tecnologia de Computadores, Granada Univ., Spain
N. Farvardin , Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA
pp. 21-24

Interframe differential vector coding of line spectrum frequencies (Abstract)

A.E. Cetin , Dept. of Electr. & Electron. Eng., Bilkent Univ., Ankara, Turkey
E. Erzin , Dept. of Electr. & Electron. Eng., Bilkent Univ., Ankara, Turkey
pp. 25-28

Vector quantizer design for the coding of LSF parameters (Abstract)

J.S. Collura , US Dept. of Defense, Washington, DC, USA
T.E. Tremain , US Dept. of Defense, Washington, DC, USA
pp. 29-32

The estimation of powerful language models from small and large corpora (Abstract)

P. Placeway , Bolt Beranek & Newman Inc., Cambridge, MA, USA
L. Nguyen , Bolt Beranek & Newman Inc., Cambridge, MA, USA
P. Fung , Bolt Beranek & Newman Inc., Cambridge, MA, USA
R. Schwartz , Bolt Beranek & Newman Inc., Cambridge, MA, USA
pp. 33-36

Statistical language modeling combining N-gram and context-free grammars (Abstract)

M. Meteer , Rensselaer Polytech. Inst., Troy, NY, USA
J.R. Rohlicek , Bolt Beranek & Newman Inc., Cambridge, MA, USA
pp. 37-40

Automatic word classification using simulated annealing (Abstract)

G. Adda , LIMSI-CNRS, Orsay, France
M. Jardino , LIMSI-CNRS, Orsay, France
pp. 41-44

Trigger-based language models: a maximum entropy approach (Abstract)

S. Roukos , Bolt Beranek & Newman Inc., Cambridge, MA, USA
R. Rosenfeld , LIMSI-CNRS, Orsay, France
R. Lau , MIT, Cambridge, MA, USA
pp. 45-48

Flexible use of semantic constraints in speech recognition (Abstract)

S. Young , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
W. Ward , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 49-50

Probabilistic parse scoring with prosodic information (Abstract)

N.M. Veilleux , Electr. Comput. & Syst. Eng., Boston Univ., MA, USA
M. Ostendorf , Electr. Comput. & Syst. Eng., Boston Univ., MA, USA
pp. 51-54

Learning speech semantics with keyword classification trees (Abstract)

R. Kuhn , CRIM, Montreal, Que., Canada
R. De Mori , Electr. Comput. & Syst. Eng., Boston Univ., MA, USA
pp. 55-58

Better alignment procedures for speech recognition evaluation (Abstract)

W.M. Fisher , Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
J.G. Fiscus , Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
pp. 59-62

Semantics and constraint parsing of word graphs (Abstract)

L.H. Jamieson , Sch. of Electr. Eng., Purdue Univ., W. Lafayette, IN, USA
C.B. Zoltowski , Sch. of Electr. Eng., Purdue Univ., W. Lafayette, IN, USA
M.P. Harper , Sch. of Electr. Eng., Purdue Univ., W. Lafayette, IN, USA
R.A. Helzerman , Sch. of Electr. Eng., Purdue Univ., W. Lafayette, IN, USA
pp. 63-66

An heuristic-based context-free parsing algorithm (Abstract)

A.L.N. Fred , Centro de Analise e Processamento de Sinais, Inst. Superior Tecnico, Lisboa, Portugal
J.M.N. Leitao , Centro de Analise e Processamento de Sinais, Inst. Superior Tecnico, Lisboa, Portugal
pp. 67-70

Influence of background noise and microphone on the performance of the IBM Tangora speech recognition system (Abstract)

R. Bakis , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
A. Nadas , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
S. Das , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
M. Picheny , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
D. Nahamoo , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 71-74

Noise-robust HMMs based on minimum error classification (Abstract)

K. Ohkura , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
M. Sugiyama , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
D. Rainton , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 75-78

Subband or cepstral domain filtering for recognition of Lombard and channel-distorted speech (Abstract)

B.A. Hanson , Panasonic Technologies, Inc., Santa Barbara, CA, USA
T.H. Applebaum , Panasonic Technologies, Inc., Santa Barbara, CA, USA
pp. 79-82

Recognition of speech in additive and convolutional noise based on RASTA spectral processing (Abstract)

H.-G. Hirsch , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
H. Hermansky , US WEST Advanced Technologies, Boulder, CO, USA
N. Morgan , Panasonic Technologies, Inc., Santa Barbara, CA, USA
pp. 83-86

Noise masking in a transform domain (Abstract)

B.A. Mellor , Defence Research Agency, Malvern, UK
A.P. Varga , Defence Research Agency, Malvern, UK
pp. 87-90

Multi-microphone correlation-based processing for robust speech recognition (Abstract)

R.M. Stern , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
T.M. Sullivan , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 91-94

Root homomorphic deconvolution schemes for speech processing in car noise environments (Abstract)

J. Boudy , Matra Communication, Bois D'Arcy, France
P. Lockwood , Matra Communication, Bois D'Arcy, France
P. Alexandre , Matra Communication, Bois D'Arcy, France
pp. 99-102

Noisy speech recognition based on HMMs, Wiener filters and re-evaluation of most likely candidates (Abstract)

B.P. Milner , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
S.V. Vaseghi , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
pp. 103-106

Direct modulation on LPC coefficients with application to speech enhancement and improving the performance of speech recognition in noise (Abstract)

B. Wu , Dept. of Radio Eng., Southeast Univ., Nanjing, China
C. Guan , Dept. of Radio Eng., Southeast Univ., Nanjing, China
Y. Chen , Dept. of Radio Eng., Southeast Univ., Nanjing, China
pp. 107-110

The BBN/HARC spoken language understanding system (Abstract)

R. Schwartz , BBN Systems & Technologies, Cambridge, MA, USA
L. Nguyen , BBN Systems & Technologies, Cambridge, MA, USA
D. Stallard , BBN Systems & Technologies, Cambridge, MA, USA
F. Kubala , BBN Systems & Technologies, Cambridge, MA, USA
P. Fung , BBN Systems & Technologies, Cambridge, MA, USA
R. Bobrow , BBN Systems & Technologies, Cambridge, MA, USA
J. Makhoul , BBN Systems & Technologies, Cambridge, MA, USA
R. Ingria , BBN Systems & Technologies, Cambridge, MA, USA
M. Bates , BBN Systems & Technologies, Cambridge, MA, USA
pp. 111-114

Noisy spontaneous speech understanding using noise immunity keyword spotting with adaptive speech response cancellation (Abstract)

Y. Takebayashi , Toshiba Corp., Saiwai-ku, Kawasaki, Japan
H. Kanazawa , Toshiba Corp., Saiwai-ku, Kawasaki, Japan
Y. Nagata , Toshiba Corp., Saiwai-ku, Kawasaki, Japan
pp. 115-118

Word graphs: an efficient interface between continuous-speech recognition and language understanding (Abstract)

H. Ney , Philips GmbH Forschungslab., Aachen, Germany
M. Oerder , Philips GmbH Forschungslab., Aachen, Germany
pp. 119-122

Partial parsing as a robust parsing strategy (Abstract)

C. Rullent , Centro Studi e Lab. Telecomunicazioni, Torino, Italy
P. Baggia , Centro Studi e Lab. Telecomunicazioni, Torino, Italy
pp. 123-126

New techniques for speech understanding (Abstract)

M.N. Granieri , IBM SEMEA, Rome, Italy
P. Ferragina , IBM SEMEA, Rome, Italy
P. Bianchini , IBM SEMEA, Rome, Italy
L. Tarricone , IBM SEMEA, Rome, Italy
pp. 127-130

Gisting conversational speech in real time (Abstract)

M. Meteer , BBN Systems & Technologies, Cambridge, MA, USA
H. Gish , BBN Systems & Technologies, Cambridge, MA, USA
T. Miller , BBN Systems & Technologies, Cambridge, MA, USA
J.R. Rohlicek , BBN Systems & Technologies, Cambridge, MA, USA
M. Siu , BBN Systems & Technologies, Cambridge, MA, USA
L. Denenberg , BBN Systems & Technologies, Cambridge, MA, USA
W. Sadkin , BBN Systems & Technologies, Cambridge, MA, USA
pp. 131-134

Test and evaluation of a spoken dialogue system (Abstract)

E. Gerbino , Centro Studi e Lab. Telecomunicazioni, Torino, Italy
C. Rullent , Centro Studi e Lab. Telecomunicazioni, Torino, Italy
A. Ciaramella , Centro Studi e Lab. Telecomunicazioni, Torino, Italy
P. Baggia , Centro Studi e Lab. Telecomunicazioni, Torino, Italy
pp. 135-138

ATREUS: a comparative study of continuous speech recognition systems at ATR (Abstract)

K. Yamaguchi , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
A. Kurematsu , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
S. Sagayama , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
A. Nagai , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 139-142

A 2.4 kbit/s CELP speech codec with class-dependent structure (Abstract)

H. Hassanein , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
P. Lupini , Sch. of Eng. Sci., Simon Fraser Univ., BC, Canada
V. Cuperman , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 143-146

Speech classification embedded in adaptive codebook search for CELP coding (Abstract)

H.-C. Wang , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
C.-C. Kuo , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
F.-R. Jean , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 147-150

Vector quantized MBE with simplified V/UV division at 3.0 kbit/s (Abstract)

M. Nishiguchi , Sony Corp., Tokyo, Japan
R. Wakatsuki , Sony Corp., Tokyo, Japan
J. Matsumoto , Sony Corp., Tokyo, Japan
S. Ono , Sony Corp., Tokyo, Japan
pp. 151-154

Variable rate speech coding with phonetic segmentation (Abstract)

E. Paksoy , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
A. Gersho , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
K. Srinivasan , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
pp. 155-158

Implementation and evaluation of a 2400 bit/s mixed excitation LPC vocoder (Abstract)

A.V. McCree , Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
A.V. McCree , Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 159-162

Evaluation of low rate speech coders for HF (Abstract)

T.E. Tremain , US Dept. of Defense, Washington, DC, USA
J.S. Collura , US Dept. of Defense, Washington, DC, USA
M.A. Kohler , US Dept. of Defense, Washington, DC, USA
D.P. Kemp , US Dept. of Defense, Washington, DC, USA
pp. 163-166

Dynamic bit allocation in CELP excitation coding (Abstract)

J. Sjoberg , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
T. Eriksson , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
pp. 171-174

A mixed prototype waveform/CELP coder for sub 3 kbit/s (Abstract)

I.S. Burnett , Sch. of Electron. & Electr. Eng., Bath Univ., UK
R.J. Holbeche , Sch. of Electron. & Electr. Eng., Bath Univ., UK
pp. 175-178

Voiced speech coding at very low bit rates based on forward-backward waveform prediction (FBWP) (Abstract)

H. Leich , Sch. of Electron. & Electr. Eng., Bath Univ., UK
R. Boite , US Dept. of Defense, Washington, DC, USA
G. Yang , Lernout & Hauspie Speechproducts nv, Wemmel, Belgium
pp. 179-182

A text-to-speech system for Spanish with a frequency domain based prosodic modification algorithm (Abstract)

E. Lopez-Gonzalo , Sch. of Electron. & Electr. Eng., Bath Univ., UK
C. Garcia-Mateo , US Dept. of Defense, Washington, DC, USA
E.R. Banga , DTC-ETSI Telecomunicacion, Vigo Univ., Spain
pp. 183-186

Multilingual PSOLA text-to-speech system (Abstract)

I. Metayer , France Telecom-CNET, Lannion, France
D. Larreur , France Telecom-CNET, Lannion, France
D. Bigorgne , France Telecom-CNET, Lannion, France
S. White , France Telecom-CNET, Lannion, France
J.L. Le Saint-Milon , France Telecom-CNET, Lannion, France
B. Cherbonnel , France Telecom-CNET, Lannion, France
F. Emerard , France Telecom-CNET, Lannion, France
O. Boeffard , France Telecom-CNET, Lannion, France
C. Sorin , France Telecom-CNET, Lannion, France
pp. 187-190

Tree-based unit selection for English speech synthesis (Abstract)

Y. Sagisaka , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
W.J. Wang , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
N. Iwahashi , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
W.N. Campbell , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
pp. 191-194

Waveform-based speech synthesis approach with a formant frequency modification (Abstract)

T. Hirokawa , NTT Human Interface Lab., Tokyo, Japan
M. Abe , NTT Human Interface Lab., Tokyo, Japan
H. Mizuno , NTT Human Interface Lab., Tokyo, Japan
pp. 195-198

An efficient way to learn English grapheme-to-phoneme rules automatically (Abstract)

K. Torkkola , Inst. Dalle Molle D'Intelligence Artificielle Perceptive, Martigny, Switzerland
pp. 199-202

Inference of letter-phoneme correspondences with pre-defined consonant and vowel patterns (Abstract)

R.I. Damper , Dept. of Electron. & Comput. Sci., Southampton Univ., UK
R.W.P. Luk , Dept. of Electron. & Comput. Sci., Southampton Univ., UK
pp. 203-206

Application of the analysis of glottal excitation of stressed speech to speaking style modification (Abstract)

K.E. Cummings , Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
M.A. Clements , Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 207-210

Analysis and modeling of word accent and sentence intonation in Swedish (Abstract)

M. Ljungqvist , Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
H. Murata , NTT Human Interface Lab., Tokyo, Japan
H. Fujisaki , Dept. of Appl. Electron., Sci. Univ. of Tokyo, Noda, Japan
pp. 211-214

Use of temporal correlation between successive frames in a hidden Markov model based speech recognizer (Abstract)

K.K. Paliwal , Comput. Syst. & Commun. Group, Tata Inst. of Fundamental Res., Bombay, India
pp. 215-218

Phoneme HMMs constrained by frame correlations (Abstract)

T. Matsuoka , NTT Human Interface Lab., Tokyo, Japan
S. Takahashi , NTT Human Interface Lab., Tokyo, Japan
Y. Minami , NTT Human Interface Lab., Tokyo, Japan
K. Shikano , NTT Human Interface Lab., Tokyo, Japan
pp. 219-222

Automatically generated word pronunciations from phoneme classifier output (Abstract)

P. Schmid , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
R. Cole , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
M. Fanty , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
pp. 223-226

A new framework for recognition of Mandarin syllables with tones using sub-syllabic units (Abstract)

L.-S. Lee , Nat. Taiwan Univ., Taiwan
P.-Y. Ting , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
C.-H. Lin , Nat. Taiwan Univ., Taiwan
pp. 227-230

A comparison of auditory models for speaker independent phoneme recognition (Abstract)

T.R. Anderson , Armstrong Lab., Wright-Patterson AFB, OH, USA
pp. 231-234

Speaker-independent spelling recognition over the telephone (Abstract)

D. Jouvet , France Telecom, CNET, Lannion, France
A. Laine , France Telecom, CNET, Lannion, France
C. Gagnoulet , France Telecom, CNET, Lannion, France
J. Monne , France Telecom, CNET, Lannion, France
pp. 235-238

Improvements in connected digit recognition using linear discriminant analysis and mixture densities (Abstract)

R. Haeb-Umbach , Philips GmbH Res. Lab., Aachen, Germany
H. Ney , Philips GmbH Res. Lab., Aachen, Germany
D. Geller , Philips GmbH Res. Lab., Aachen, Germany
pp. 239-242

Inter-word coarticulation modeling and MMIE training for improved connected digit recognition (Abstract)

R. Cardin , Centre de Recherche Inf. de Montreal, McGill Coll., Montreal, Que., Canada
Y. Normandin , Centre de Recherche Inf. de Montreal, McGill Coll., Montreal, Que., Canada
E. Millien , Centre de Recherche Inf. de Montreal, McGill Coll., Montreal, Que., Canada
pp. 243-246

Limited parameter hidden Markov models for connected digit speaker verification over telephone channels (Abstract)

G. Gallopyn , L&H Speech Products, Leper, Belgium
H. Bourlard , L&H Speech Products, Leper, Belgium
J. de Veth , L&H Speech Products, Leper, Belgium
pp. 247-250

An algorithm for the dynamic inference of hidden Markov models (DIHMM) (Abstract)

P. Lockwood , Matra Communication, Bois D'Arcy, France
M. Blanchet , Matra Communication, Bois D'Arcy, France
pp. 251-254

Multi-speaker/speaker-independent architectures for the multi-state time delay neural network (Abstract)

A. Waibel , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
H. Hild , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 255-258

Performance through consistency: connectionist large vocabulary continuous speech recognition (Abstract)

J. Tebelskis , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 259-262

A multilayer perceptron postprocessor to hidden Markov modeling for speech recognition (Abstract)

J. Guo , Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
H.C. Lui , Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
pp. 263-266

Exploiting prediction error in a predictive-based connectionist speech recognition system (Abstract)

B. Petek , Univ. of Ljubljana, Slovenia
A. Ferligoj , Univ. of Ljubljana, Slovenia
pp. 267-270

An optimal learning method for minimizing spotting errors (Abstract)

T. Komori , ATR Auditory & Visual Perception Res. Lab., Soraku-gun, Kyoto, Japan
S. Katagiri , ATR Auditory & Visual Perception Res. Lab., Soraku-gun, Kyoto, Japan
pp. 271-274

Feature extraction based on minimum classification error/generalized probabilistic descent method (Abstract)

A. Biem , ATR Auditory & Visual Perception Res. Lab., Soraku-gun, Kyoto, Japan
S. Katagiri , ATR Auditory & Visual Perception Res. Lab., Soraku-gun, Kyoto, Japan
pp. 275-278

Speech discrimination in adverse conditions using acoustic knowledge and selectively trained neural networks (Abstract)

Y. Anglade , CRIN-CNRS, Vandoeuvre-les-Nancy, France
D. Fohr , CRIN-CNRS, Vandoeuvre-les-Nancy, France
J.-C. Junqua , L&H Speech Products, Leper, Belgium
pp. 279-282

Speech recognition using dynamical model of speech production (Abstract)

K.j. Iso , NEC Corp., Miyamae-ku, Kawasaki, Japan
pp. 283-286

Recurrent input transformations for hidden Markov models (Abstract)

V. Valtchev , Eng. Dept., Cambridge Univ., UK
S.J. Young , Eng. Dept., Cambridge Univ., UK
S. Kapadia , Eng. Dept., Cambridge Univ., UK
pp. 287-290

Prototype-based MCE/GPD training for word spotting and connected word recognition (Abstract)

E. McDermott , ATR Auditory & Visual Perception Res. Lab., Soraku-gun, Kyoto, Japan
S. Katagiri , ATR Auditory & Visual Perception Res. Lab., Soraku-gun, Kyoto, Japan
pp. 291-294

Matrix parser and its application to HMM-based speech recognition (Abstract)

H. Singer , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
S. Sagayama , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 295-298

Using search to improve hidden Markov models (Abstract)

M. Galler , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
R. De Mori , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
pp. 303-306

An improved search algorithm using incremental knowledge for continuous speech recognition (Abstract)

X. Huang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
M.-Y. Hwang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
F. Alleva , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 307-310

Predicting unseen triphones with senones (Abstract)

X. Huang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
F. Alleva , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
M.-Y. Hwang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 311-314

Analysis and improvement of the partial distance search algorithm (Abstract)

F. Ravera , France Telecom, CNET, Lannion, France
P. Massafra , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
L. Fissore , Centro Studi e Lab. Telecomunicazioni, Torino, Italy
P. Laface , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 315-318

Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniques (Abstract)

V. Digalakis , SRI Int., Menlo Park, CA, USA
M. Weintraub , SRI Int., Menlo Park, CA, USA
H. Murveit , SRI Int., Menlo Park, CA, USA
J. Butzberger , SRI Int., Menlo Park, CA, USA
pp. 319-322

Exploiting variable-width features in large vocabulary speech recognition (Abstract)

M. Jones , Eng. Dept., Cambridge Univ., UK
P.C. Woodland , Eng. Dept., Cambridge Univ., UK
pp. 323-326

A comparison of trajectory and mixture modeling in segment-based word recognition (Abstract)

A. Kannan , Electr., Comput. & Syst. Eng., Boston Univ., MA, USA
M. Ostendorf , Electr., Comput. & Syst. Eng., Boston Univ., MA, USA
pp. 327-330

Modeling duration in a hidden Markov model with the exponential family (Abstract)

L.H. Jamieson , Sch. of Elecr. Eng., Purdue Univ., W. Lafayette, IN, USA
C.D. Mitchell , Sch. of Elecr. Eng., Purdue Univ., W. Lafayette, IN, USA
pp. 331-334

Noise robustness in the auditory representation of speech signals (Abstract)

K. Wang , Dept. of Electr. Eng., Maryland Univ., College Park, MD, USA
S.A. Shamma , Dept. of Electr. Eng., Maryland Univ., College Park, MD, USA
W.J. Byrne , Dept. of Electr. Eng., Maryland Univ., College Park, MD, USA
pp. 335-338

Dynamic time warping comb filter for the enhancement of speech degraded by white Gaussian noise (Abstract)

N. Hubing , Dept. of Electr. Eng., Missouri Univ., Rolla, MO, USA
J.T. Graf , Dept. of Electr. Eng., Missouri Univ., Rolla, MO, USA
pp. 339-342

Acoustic signal separation of statistically independent sources using multiple microphones (Abstract)

A.M. Engebretson , Comput. Sci. Dept., Washington Univ., St. Louis, MO, USA
pp. 343-346

Microphone array speech enhancement in overdetermined signal scenarios (Abstract)

R.L. Moses , Dept. of Electr. Eng., Ohio State Univ., Columbus, OH, USA
R.E. Slyh , Dept. of Electr. Eng., Ohio State Univ., Columbus, OH, USA
pp. 347-350

A new two-sensor active noise cancellation algorithm (Abstract)

K.C. Zangi , MIT, Cambridge, MA, USA
pp. 351-354

A signal subspace approach for speech enhancement (Abstract)

Y. Ephraim , AT&T Bell Lab., Murray Hill, NJ, USA
H.L. Van Trees , Dept. of Electr. Eng., Ohio State Univ., Columbus, OH, USA
pp. 355-358

Speech enhancement using psychoacoustic criteria (Abstract)

M. Paraskevas , Wire Commun. Lab., Patras Univ., Greece
J. Mourjopoulos , Wire Commun. Lab., Patras Univ., Greece
D. Tsoukalas , Wire Commun. Lab., Patras Univ., Greece
pp. 359-362

Frequency domain noise suppression approaches in mobile telephone systems (Abstract)

J. Yang , NovAtel Communications Ltd., Calgary, Alta., Canada
pp. 363-366

Speech enhancement using the dual excitation speech model (Abstract)

J. Hardwick , Res. Lab. of Electron., MIT, Cambridge, MA, USA
J.S. Lim , Res. Lab. of Electron., MIT, Cambridge, MA, USA
C.D. Yoo , Res. Lab. of Electron., MIT, Cambridge, MA, USA
pp. 367-370

A comparison of composite features under degraded speech in speaker recognition (Abstract)

Z.P. Sun , Univ. Coll. of Swansea, UK
J.P. Openshaw , Univ. Coll. of Swansea, UK
J.S. Mason , Univ. Coll. of Swansea, UK
pp. 371-374

Voice identification using nearest-neighbor distance measure (Abstract)

A.L. Higgins , ITT Aerospace, San Diego, CA, USA
J.E. Porter , ITT Aerospace, San Diego, CA, USA
L.G. Bahler , ITT Aerospace, San Diego, CA, USA
pp. 375-378

Robustness study of free-text speaker identification and verification (Abstract)

P.K. Rajasekaran , ITT Aerospace, San Diego, CA, USA
Y.-H. Kao , Texas Instruments Inc., Dallas, TX, USA
J.S. Baras , ITT Aerospace, San Diego, CA, USA
pp. 379-382

Identification of speakers engaged in dialog (Abstract)

G. Yu , BBN Systems & Technologies, Cambridge, MA, USA
H. Gish , BBN Systems & Technologies, Cambridge, MA, USA
pp. 383-386

Speaker identification experiments using HMMs (Abstract)

J.J. Webb , AT&T Bell Lab., Columbus, OH, USA
E.L. Rissanen , AT&T Bell Lab., Columbus, OH, USA
pp. 387-390

Concatenated phoneme models for text-variable speaker recognition (Abstract)

T. Matsui , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
S. Furui , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
pp. 391-394

Speech segmentation and clustering based on speaker features (Abstract)

J. Murakami , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
H. Watanabe , ITT Aerospace, San Diego, CA, USA
M. Sugiyama , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 395-398

Text independent speaker identification using fuzzy mathematical algorithm (Abstract)

Y. Fang , Inst. of Acoust., Nanjing Univ., China
Z.-X. Yuan , Inst. of Acoust., Nanjing Univ., China
C.-Z. Yu , Inst. of Acoust., Nanjing Univ., China
pp. 403-406

Use of an auditory model to improve speech coders (Abstract)

D. Sen , Sch. of Electr. Eng., New South Wales Univ., Kennsington, NSW, Australia
W.H. Holmes , Sch. of Electr. Eng., New South Wales Univ., Kennsington, NSW, Australia
D.H. Irving , Sch. of Electr. Eng., New South Wales Univ., Kennsington, NSW, Australia
pp. 411-414

Low-delay wideband speech coding using a new frequency domain approach (Abstract)

V.E. Sanchez , Dpto. de Electron., Granada Univ., Spain
J.-P. Adoul , Sch. of Electr. Eng., New South Wales Univ., Kennsington, NSW, Australia
pp. 415-418

A probabilistic framework for optimum speech extrapolation in digital mobile radio (Abstract)

C.G. Gerlach , Inst. for Commun. Syst. & Data Process., Aachen Univ. of Technol., Germany
pp. 419-422

How good is your index assignment? (Abstract)

P. Knagenhjelm , Dept. of Inf. Theory, Chalmers Univ. of Technol., Gothenburg, Sweden
pp. 423-426

Investigating the use of asymmetric windows in CELP vocoders (Abstract)

D.A.F. Florencio , Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 427-430

Using neural networks for vector quantization in low rate speech coders (Abstract)

S.D. Hansen , Sch. of Electr. Eng., New South Wales Univ., Kennsington, NSW, Australia
J. Thyssen , Telecommun. Res. Lab., Horsholm, Denmark
pp. 431-434

The benefits of multi-speaker conferencing and the design of conference bridge control algorithm (Abstract)

P.A. La Follette , ARCON Corp., Waltham, MA, USA
J.D. Tardelli , ARCON Corp., Waltham, MA, USA
E.W. Kreamer , ARCON Corp., Waltham, MA, USA
P.D. Gatewood , ARCON Corp., Waltham, MA, USA
pp. 435-438

The application of subband coding to improve quality and robustness of the sinusoidal transform coder (Abstract)

T.F. Quatieri , MIT Lincoln Lab., Lexington, MA, USA
R.J. McAulay , MIT Lincoln Lab., Lexington, MA, USA
pp. 439-442

Analysis of the smoothed residual driven algorithm for speech coders (Abstract)

J.D. Gibson , Dept. of Electr. Eng., Texas A&M Univ., College Station, TX, USA
S.H. Nam , Dept. of Electr. Eng., Texas A&M Univ., College Station, TX, USA
pp. 443-446

A segmental speech model with applications to word spotting (Abstract)

K. Ng , BBN Systems & Technologies, Cambridge, MA, USA
H. Gish , BBN Systems & Technologies, Cambridge, MA, USA
pp. 447-450

A two pass classifier for utterance rejection in keyword spotting (Abstract)

J.G. Wilpon , AT&T Bell Lab., Naperville, IL, USA
R.A. Sukkar , AT&T Bell Lab., Naperville, IL, USA
pp. 451-454

Rejection techniques for digit recognition in telecommunication applications (Abstract)

L. Villarrubia , Telefonica I+D, Madrid, Spain
A. Acero , Telefonica I+D, Madrid, Spain
pp. 455-458

Phonetic training and language modeling for word spotting (Abstract)

M. Siu , BBN Systems & Technologies, Cambridge, MA, USA
H. Gish , BBN Systems & Technologies, Cambridge, MA, USA
B. Musicus , BBN Systems & Technologies, Cambridge, MA, USA
P. Jeanrenaud , BBN Systems & Technologies, Cambridge, MA, USA
J.R. Rohlicek , BBN Systems & Technologies, Cambridge, MA, USA
K. Ng , BBN Systems & Technologies, Cambridge, MA, USA
pp. 459-462

Task independent wordspotting using decision tree based allophone clustering (Abstract)

R.C. Rose , AT&T Bell Lab., Murray Hill, NJ, USA
E.M. Hofstetter , BBN Systems & Technologies, Cambridge, MA, USA
pp. 467-470

Application of large vocabulary continuous speech recognition to topic and speaker identification using telephone speech (Abstract)

M. Hunt , Dragon Systems, Inc., Newton, MA, USA
L. Gillick , Dragon Systems, Inc., Newton, MA, USA
J. Baker , Dragon Systems, Inc., Newton, MA, USA
J. Bridle , Dragon Systems, Inc., Newton, MA, USA
R. Roth , Dragon Systems, Inc., Newton, MA, USA
J. Baker , Dragon Systems, Inc., Newton, MA, USA
Y. Ito , Dragon Systems, Inc., Newton, MA, USA
S. Lowe , Dragon Systems, Inc., Newton, MA, USA
B. Peskin , Dragon Systems, Inc., Newton, MA, USA
J. Orloff , Dragon Systems, Inc., Newton, MA, USA
F. Scattone , Dragon Systems, Inc., Newton, MA, USA
pp. 471-474

Improving the MS-TDNN for word spotting (Abstract)

A. Waibel , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Houghton , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
T. Zeppenfeld , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 475-478

Phonetic recognition in a segment-based HMM (Abstract)

J.N. Marcus , Spoken Language Syst. Group, MIT, Cambridge, MA, USA
pp. 479-482

A linguistic feature representation of the speech waveform (Abstract)

S. Mitter , Dragon Systems, Inc., Newton, MA, USA
J.R. Rohlicek , BBN Systems & Technologies, Cambridge, MA, USA
H. Gish , BBN Systems & Technologies, Cambridge, MA, USA
E. Eide , BBN Systems & Technologies, Cambridge, MA, USA
pp. 483-486

Allophone modeling for vocabulary-independent HMM recognition (Abstract)

D.J.B. Pearce , GEC-Marconi Ltd., Wembley, UK
L.C. Wood , GEC-Marconi Ltd., Wembley, UK
W.J. Holmes , GEC-Marconi Ltd., Wembley, UK
pp. 487-490

MMI training for continuous phoneme recognition on the TIMIT database (Abstract)

S.J. Young , Eng. Dept., Cambridge Univ., UK
V. Valtchev , Eng. Dept., Cambridge Univ., UK
S. Kapadia , Eng. Dept., Cambridge Univ., UK
pp. 491-494

Situated state hidden Markov models (Abstract)

M. Bush , Xerox Palo Alto Res. Center, CA, USA
D. Kimber , Xerox Palo Alto Res. Center, CA, USA
pp. 495-498

A segmental HMM for speech pattern modelling (Abstract)

M. Russell , DRA Malvern, UK
pp. 499-502

Golden Mandarin (II)-an improved single-chip real-time Mandarin dictation machine for Chinese language with very large vocabulary (Abstract)

I.-J. Hung , Dragon Systems, Inc., Newton, MA, USA
T.-S. Lin , Dragon Systems, Inc., Newton, MA, USA
K.-J. Chen , Eng. Dept., Cambridge Univ., UK
M.-Y. Lee , Dragon Systems, Inc., Newton, MA, USA
Y. Lee , Dragon Systems, Inc., Newton, MA, USA
L.-s. Lee , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
H.-m. Wang , Dragon Systems, Inc., Newton, MA, USA
R. Lyu , Dragon Systems, Inc., Newton, MA, USA
C.-y. Tseng , Xerox Palo Alto Res. Center, CA, USA
Y.-C. Wu , Dragon Systems, Inc., Newton, MA, USA
L.-F. Chien , Dragon Systems, Inc., Newton, MA, USA
pp. 503-506

Cross-lingual experiments with phone recognition (Abstract)

J.-L. Gauvain , LIMSI-CNRS, Orsay, France
L.F. Lamel , LIMSI-CNRS, Orsay, France
pp. 507-510

Beam search and partial traceback in the frame-synchronous two-level algorithm (TLBS) (Abstract)

P. Lockwood , Matra Communication, Bois D'Arcy, France
O. Bezie , Matra Communication, Bois D'Arcy, France
pp. 511-514

Spanish phone recognition using semicontinuous hidden Markov models (Abstract)

F. Casacuberta , Matra Communication, Bois D'Arcy, France
I. Torres , Dpto. Electr. y Electron., Univ. del Pais Vasco, Bilbao, Spain
pp. 515-518

Glottal pulse alignment in voiced speech for pitch determination (Abstract)

J.D. Harris , Dept. of Defense, Ft. Meade, MD, USA
D. Nelson , Dept. of Defense, Ft. Meade, MD, USA
pp. 519-522

Pseudo-three-tap pitch prediction filters (Abstract)

Q. Yasheng , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
P. Kabal , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
pp. 523-526

Determining the pitch period of speech using no multiplications (Abstract)

R.L. While , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
D.W.N. Sharp , Dept. of Comput. Sci., Imperial Coll. of Sci. Technol. & Med., London, UK
pp. 527-529

Pitch from zeros of bank-filtered signals (Abstract)

P. Chen , Eng. Res. Inst., Tokyo Univ., Japan
S. Ando , Eng. Res. Inst., Tokyo Univ., Japan
pp. 530-533

Estimation of the parameters of a long-term model for accurate representation of voiced speech (Abstract)

D. Chazan , Eng. Dept., Cambridge Univ., UK
D. Malah , Dept. of Electr. Eng., Technion, Haifa, Israel
Y. Stettiner , Dept. of Electr. Eng., Technion, Haifa, Israel
pp. 534-537

Optimal estimation of vocal tract area functions from speech signal constrained by X-ray microbeam data (Abstract)

Q. Guo , Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA
P. Milenkovic , Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA
pp. 538-541

Glottal source estimation: Methods of applying the LF-model to inverse filtering (Abstract)

E.L. Riegelsberger , Dept. of Electr. Eng., Ohio State Univ., Columbus, OH, USA
A.K. Krishnamurthy , Dept. of Electr. Eng., Ohio State Univ., Columbus, OH, USA
pp. 542-545

Acoustic model of the vocal tract with boundary layer corrections (Abstract)

M. Hesham , Eng. Math. & Phys. Dept., Cairo Univ., Giza, Egypt
T. El-Mistikawy , Eng. Math. & Phys. Dept., Cairo Univ., Giza, Egypt
A. Mohsen , Eng. Math. & Phys. Dept., Cairo Univ., Giza, Egypt
pp. 546-549

HNS: Speech modification based on a harmonic+noise model (Abstract)

Y. Stylianou , Telecom Paris, France
J. Laroche , Telecom Paris, France
E. Moulines , Telecom Paris, France
pp. 550-553

An overlap-add technique based on waveform similarity (WSOLA) for high quality time-scale modification of speech (Abstract)

W. Verhelst , Fac. of Appl. Sci., Brussels Free Univ., Belgium
M. Roelands , Fac. of Appl. Sci., Brussels Free Univ., Belgium
pp. 554-557

Speaker adaptation based on MAP estimation of HMM parameters (Abstract)

J.-L. Gauvain , AT&T Bell Lab., Murray Hill, NJ, USA
C.-H. Lee , AT&T Bell Lab., Murray Hill, NJ, USA
pp. 558-561

A new speaker adaptation technique using very short calibration speech (Abstract)

Y. Zhao , Panasonic Technologies Inc., Santa Barbara, CA, USA
pp. 562-565

Speaker adaptation using improved speaker Markov models (Abstract)

G. Rigoll , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
pp. 566-569

Rapid speaker adaptation using speaker-mixture allophone models applied to speaker-independent speech recognition (Abstract)

T. Kosaka , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
J. Takami , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
S. Sagayama , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 570-573

An all-phoneme ergodic HMM for unsupervised speaker adaptation (Abstract)

Y. Miyazawa , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 574-577

Utterance normalization using vowel features in a spoken word recognition system for multiple speakers (Abstract)

S. Ohno , Dept. of Electron. Eng., Tokyo Univ., Japan
K. Hirose , Dept. of Electron. Eng., Tokyo Univ., Japan
H. Fujasaki , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 578-581

A neural network controlled adaptive search strategy for HMM-based speech recognition (Abstract)

K. Yamaguchi , ATR Interpreting Telephony Res. Lab., Soraku-gun, Kyoto, Japan
pp. 582-585

On the dynamic adaptation of stochastic language models (Abstract)

V. Steinbiss , Philips GmbH Forschungslab, Aachen, Germany
R. Kneser , Philips GmbH Forschungslab, Aachen, Germany
pp. 586-589

Learning new words from spontaneous speech (Abstract)

S.R. Young , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
W. Ward , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 590-591

An 8-bit/s speech coder based on conjugate structure CELP (Abstract)

A. Kataoka , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
S. Hayashi , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
T. Moriya , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
pp. 592-595

A 5.85 kbits CELP algorithm for cellular applications (Abstract)

P. Kroon , AT&T Bell Lab., Murray Hill, NJ, USA
D. Sereno , Dragon Systems, Inc., Newton, MA, USA
W.B. Kleijn , AT&T Bell Lab., Murray Hill, NJ, USA
L. Cellario , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
pp. 596-599

Tree coding combined with harmonic scaling of speech at 6.4 kbps (Abstract)

I. Lee , Dept. of Electr. Eng., Texas A&M Univ., College Station, TX, USA
J.D. Gibson , Dept. of Electr. Eng., Texas A&M Univ., College Station, TX, USA
pp. 600-603

Techniques for low bit rate speech coding using long analysis frames (Abstract)

T.B. Minde , Erisoft AB, Lulea, Sweden
H. Hermansson , Dragon Systems, Inc., Newton, MA, USA
T. Wigren , Dept. of Electr. Eng., Texas A&M Univ., College Station, TX, USA
J. Ahlberg , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
pp. 604-607

Use of low-delay code-excited linear prediction technology in circuit multiplexed networks (Abstract)

F.L. Corcoran , COMSAT Lab., Clarksburg, MD, USA
S. Dimolitsas , COMSAT Lab., Clarksburg, MD, USA
M. Baraniecki , Dragon Systems, Inc., Newton, MA, USA
M. Baraniecki , NTT Human Interface Lab., Musashino-Shi, Tokyo, Japan
pp. 608-611

8 kbit/s coding of speech with 6 ms frame-length (Abstract)

J.P. Adoul , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
C. Laflamme , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
R. Salami , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
R. Lefebvre , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
pp. 612-615

An 8 kbit/s LD-CELP with improved excitation and perceptual modelling (Abstract)

R. Soheili , Centre for Satellite Eng. Res., Surrey Univ., Guildford, UK
B.G. Evans , Centre for Satellite Eng. Res., Surrey Univ., Guildford, UK
A.M. Kondoz , Centre for Satellite Eng. Res., Surrey Univ., Guildford, UK
pp. 616-619

Wideband speech coding in 7.2 kbit/s (Abstract)

C. McElroy , Dept. of Electr. & Electron. Eng., Univ. Coll., Dublin, Ireland
A.D. Fagan , Dept. of Electr. & Electron. Eng., Univ. Coll., Dublin, Ireland
B. Murray , Dept. of Electr. & Electron. Eng., Univ. Coll., Dublin, Ireland
pp. 620-623

Transform coding at 4.8 kbit/sec using interleaving of transform frames and dual gain-shape vector quantisation (Abstract)

P.M. McCourt , Dept. of Electr. & Electron. Eng., Queen's Univ. of Belfast, UK
H.A. Kaouri , Dept. of Electr. & Electron. Eng., Queen's Univ. of Belfast, UK
pp. 624-627

Phonetically-driven CELP coding using self-organizing maps (Abstract)

E. Lopez-Gonzalo , Dpto. SSR, Ciudad Univ., Madrid, Spain
L.A. Hernandez-Gomez , Dpto. SSR, Ciudad Univ., Madrid, Spain
pp. 628-631

Context dependent vector quantization for continuous speech recognition (Abstract)

P.V. de Souza , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
L.R. Bahl , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
P.S. Gopalakrishnan , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
M.A. Picheny , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 632-635

Unified stochastic engine (USE) for speech recognition (Abstract)

M. Belin , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
F. Alleva , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
X. Huang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Hwang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 636-639

Large vocabulary continuous speech recognition of Wall Street Journal data (Abstract)

J. Baker , Dragon Systems Inc., Newton, MA, USA
S. Lowe , Dragon Systems Inc., Newton, MA, USA
J. Orloff , Dragon Systems Inc., Newton, MA, USA
F. Scattone , Dragon Systems Inc., Newton, MA, USA
R. Roth , Dragon Systems Inc., Newton, MA, USA
B. Peskin , Dragon Systems Inc., Newton, MA, USA
M. Hunt , Dragon Systems Inc., Newton, MA, USA
Y. Ito , Dragon Systems Inc., Newton, MA, USA
J. Baker , Dragon Systems Inc., Newton, MA, USA
L. Gillick , Dragon Systems Inc., Newton, MA, USA
pp. 640-643

A supervised approach to the construction of context-sensitive acoustic prototypes (Abstract)

M.A. Picheny , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
D. Nahamoo , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
L.R. Bahl , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
J.R. Bellegarda , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
P.V. de Souza , IBM T.J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 644-647

Continuous mixture densities and linear discriminant analysis for improved context-dependent acoustic models (Abstract)

R. Haeb-Umbach , Philips GmbH Res. Lab., Aachen, Germany
X. Aubert , Philips GmbH Res. Lab., Aachen, Germany
H. Ney , Philips GmbH Res. Lab., Aachen, Germany
pp. 648-651

Minimum error rate training based on N-best string models (Abstract)

C.H. Lee , AT&T Bell Lab., Murray Hill, NJ, USA
B.H. Juang , AT&T Bell Lab., Murray Hill, NJ, USA
W. Chou , AT&T Bell Lab., Murray Hill, NJ, USA
pp. 652-655

A new fast match for very large vocabulary continuous speech recognition (Abstract)

Z. Li , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
P. Labute , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
R. Hollan , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
D. O'Shaughnessy , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
P. Kenny , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
M. Lennig , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 656-659

The Lincoln large-vocabulary stack-decoder HMM CSR (Abstract)

B.F. Necioglu , MIT Lincoln Lab., Lexington, MA, USA
D.B. Paul , MIT Lincoln Lab., Lexington, MA, USA
pp. 660-663

Speech recognition using the modulation model (Abstract)

M.G. Rahim , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
J.L. Flanagan , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
R.J. Mammone , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
K.T. Assaleh , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
pp. 664-667

A dynamic cepstrum incorporating time-frequency masking and its application to continuous speech recognition (Abstract)

H. Kawahara , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
H. Singer , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
Y. Tohkura , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
K. Aikawa , ATR Auditory & Visual Perception Lab., Soraku-gun, Kyoto, Japan
pp. 668-671

Two-dimensional cepstral distance measure for speech recognition (Abstract)

H.-F. Pai , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
H.-C. Wang , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 672-675

A new speech recognition method based on VQ-distortion measure and HMM (Abstract)

H. Suzuki , Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan
S. Nakagawa , Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan
pp. 676-679

A comparative study of signal representations and classification techniques for speech recognition (Abstract)

B. Chigier , NYNEX Science & Technology Inc., White Plains, NY, USA
H.C. Leung , NYNEX Science & Technology Inc., White Plains, NY, USA
J.R. Glass , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
pp. 680-683

In search for the relevant parameters for speaker independent speech recognition (Abstract)

D. Van Compernolle , K. Univ., Leuven, Heverlee, Belgium
J. Smolders , K. Univ., Leuven, Heverlee, Belgium
pp. 684-687

A non-metrical space search algorithm for fast Gaussian vector quantization (Abstract)

E.G. Schukat-Talamazzini , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
S. Rieck , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
M. Bielecki , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
T. Kuhn , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
H. Niemann , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
pp. 688-691

Speaker-independent speech recognition using nonlinear predictor codebooks (Abstract)

T. Kawabata , NTT Basic Res. Lab., Musashino-shi, Tokyo, Japan
pp. 696-699

Auditory model representation for speaker recognition (Abstract)

J.M. Colombi , AFIT/EN, Wright-Patterson AFB, OH, USA
S.K. Rogers , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
G.T. Warhola , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
D.W. Ruck , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
T.R. Anderson , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
pp. 700-703

Central auditory model for spectral processing (Abstract)

J.-P. Haton , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
Y. Gao , CRIN/INRIA Lorraine, Vandoeuvre-les-Nancy, France
T. Huang , Lehrstuhl fuer Inf., Univ. Erlangen-Nurnberg, Erlangen, Germany
pp. 704-707

A wave digital filter model of the entire auditory periphery (Abstract)

C. Giguere , Eng. Dept., Cambridge Univ., UK
P.C. Woodland , Eng. Dept., Cambridge Univ., UK
pp. 708-711

A perceptual metric for masking (Abstract)

A. Alwan , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
pp. 712-715

Finding speech formants and modulations via energy separation: with application to a vocoder (Abstract)

H.M. Hanson , Div. of Appl. Sci., Harvard Univ., Cambridge, MA, USA
A. Potamianos , Div. of Appl. Sci., Harvard Univ., Cambridge, MA, USA
P. Maragos , Div. of Appl. Sci., Harvard Univ., Cambridge, MA, USA
pp. 716-719

Stop classification using DESA-1 high resolution formant tracking (Abstract)

D.J. Mashao , Div. of Eng., Brown Univ., Providence, RI, USA
H.F. Silverman , Div. of Eng., Brown Univ., Providence, RI, USA
J.T. Foote , Div. of Eng., Brown Univ., Providence, RI, USA
pp. 720-723

Analysis and automatic recognition of false starts in spontaneous speech (Abstract)

D. O'Shaughnessy , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 724-727

Optimal multi-pitch estimation using the EM algorithm for co-channel speech separation (Abstract)

D. Malah , Div. of Eng., Brown Univ., Providence, RI, USA
Y. Stettiner , Div. of Eng., Brown Univ., Providence, RI, USA
D. Chazan , IBM Sci. & Technol. Centre, Technion City, Haifa, Israel
pp. 728-731

Endpoint detection of isolated utterances based on a modified Teager energy measurement (Abstract)

G.S. Ying , Sch. of Electr. Eng., Purdue Univ., W. Lafayette, IN, USA
C.D. Mitchell , Sch. of Electr. Eng., Purdue Univ., W. Lafayette, IN, USA
L.H. Jamieson , Sch. of Electr. Eng., Purdue Univ., W. Lafayette, IN, USA
pp. 732-735
93 ms
(Ver )