The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (1992)
San Francisco, CA, USA
Mar. 23, 1992 to Mar. 26, 1992
ISBN: 0-7803-0532-9
TABLE OF CONTENTS

New uses for the N-Best sentence hypotheses within the BYBLOS speech recognition system (Abstract)

J. Makhoul , BBN Systems & Technologies, Cambridge, MA, USA
F. Kubala , BBN Systems & Technologies, Cambridge, MA, USA
S. Austin , BBN Systems & Technologies, Cambridge, MA, USA
R. Schwartz , BBN Systems & Technologies, Cambridge, MA, USA
L. Nguyen , BBN Systems & Technologies, Cambridge, MA, USA
P. Placeway , BBN Systems & Technologies, Cambridge, MA, USA
pp. 1-4

Exploiting correlations among competing models with application to large vocabulary speech recognition (Abstract)

X. Huang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Rosefeld , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Furst , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 5-8

Improvements in beam search for 10000-word continuous speech recognition (Abstract)

R. Haeb-Umbach , Philips Res. Lab. Aachen, Germany
M. Oerder , Philips Res. Lab. Aachen, Germany
H. Ney , Philips Res. Lab. Aachen, Germany
B.-H. Tran , Philips Res. Lab. Aachen, Germany
pp. 9-12

Linear discriminant analysis for improved large vocabulary continuous speech recognition (Abstract)

H. Ney , Philips Res. Lab., Aachen, Germany
R. Haeb-Umbach , Philips Res. Lab., Aachen, Germany
pp. 13-16

A fast match for continuous speech recognition using allophonic models (Abstract)

P.S. Gopalakrishnan , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M.A. Picheny , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
D. Nahamoo , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P.V. de Souza , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
L.R. Bahl , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 17-20

Continuous speech recognition by context-dependent phonetic HMM and an efficient algorithm for finding N-Best sentence hypotheses (Abstract)

T. Hozumi , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
H. Satoru , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
I. Katunobu , Tokyo Inst. of Technol., Japan
pp. 21-24

Dividing the distributions of HMM and linear interpolation in speech recognition (Abstract)

K. Asai , Electrotech. Lab., Ibaraki, Japan
S. Hayamizu , Electrotech. Lab., Ibaraki, Japan
K. Handa , Electrotech. Lab., Ibaraki, Japan
pp. 29-32

Subphonetic modeling with Markov states-Senone (Abstract)

M.Y. Hwang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburg, PA, USA
X. Huang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburg, PA, USA
pp. 33-36

Japanese dictation system using character source modeling (Abstract)

S. Matsunaga , NTT Human Interface Labs., Tokyo, Japan
T. Yamada , NTT Human Interface Labs., Tokyo, Japan
K. Shikano , NTT Human Interface Labs., Tokyo, Japan
pp. 37-40

Techniques for improving the quality of LD-CELP coders at 8 kb/s (Abstract)

B.G. Evans , Centre for Satellite Eng. Res., Surrey Univ., Guildford, UK
R. Soheili , Centre for Satellite Eng. Res., Surrey Univ., Guildford, UK
A.M. Kondoz , Centre for Satellite Eng. Res., Surrey Univ., Guildford, UK
pp. 41-44

Low-delay VXC at 8 kbit/s with interframe coding (Abstract)

J.-H. Yao , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
J.J. Shynk , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
A. Gersho , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
pp. 45-48

On reducing the bit rate of a CELP-based speech coder (Abstract)

Y.J. Liu , ITT Aerospace, Nutley, NJ, USA
pp. 49-52

Reduced complexity CELP coder (Abstract)

M. Mauc , ESIEE Dept. Signaux et Telecommun., Noisy le Grand, France
G. Baudoin , ESIEE Dept. Signaux et Telecommun., Noisy le Grand, France
pp. 53-56

A multi-stage perspective on CELP speech coding (Abstract)

P. Hedelin , Dept. of Inf. Theor., Chalmers Univ. of Technol., Gothenburg, Sweden
pp. 57-60

Successive orthogonalizations in the multistage CELP coder (Abstract)

N. Moreau , Telecom, Paris, France
P. Dymarski , ESIEE Dept. Signaux et Telecommun., Noisy le Grand, France
pp. 61-64

A new excitation model for LPC vocoder at 2.4 kb/s (Abstract)

Zhang Xiongwei , Nanjing Inst. of Commun. Eng., China
Chen Xianzhi , Nanjing Inst. of Commun. Eng., China
pp. 65-68

Improving the performance of the 16 kb/s LD-CELP speech coder (Abstract)

R.V. Cox , AT&T Bell Labs., Murray Hill, NJ, USA
N. Jayant , AT&T Bell Labs., Murray Hill, NJ, USA
J.-H. Chen , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 69-72

On the effectiveness of parameter reoptimization in multipulse based coders (Abstract)

G.A. Mian , AT&T Bell Labs., Murray Hill, NJ, USA
G. Riccardi , AT&T Bell Labs., Murray Hill, NJ, USA
M. Fratti , Teletra-Alcatel, Milan, Italy
pp. 73-76

Kalman filtering techniques in speech coding (Abstract)

R.R. Bitmead , AT&T Bell Labs., Murray Hill, NJ, USA
J.D. Mills , AT&T Bell Labs., Murray Hill, NJ, USA
S. Crisafulli , Dept. Syst. Eng., Australian Nat. Univ., Canberra, ACT, Australia
pp. 77-80

Time-scale modification of speech using an incremental time-frequency approach with waveform structure compensation (Abstract)

P. Kabal , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
B. Sylvestre , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
pp. 81-84

Signal reconstruction from modified wavelet transform-An application to auditory signal processing (Abstract)

T. Irino , NTT Basic Res. Labs., Tokyo, Japan
H. Kawahara , NTT Basic Res. Labs., Tokyo, Japan
pp. 85-88

An efficient approximation-elimination algorithm for fast-nearest-neighbour search (speech coding) (Abstract)

K.K. Paliwal , Comput. Syst. & Commun. Group, Tata Inst. of Fundamental Res., Bombay, India
V. Ramasubramanian , Comput. Syst. & Commun. Group, Tata Inst. of Fundamental Res., Bombay, India
pp. 89-92

Speech coding by the efficient transformation of the spectral envelope of subwords (Abstract)

M. Ready , Speech Res. Lab., California Univ., Davis, CA, USA
C. Caldwell , Speech Res. Lab., California Univ., Davis, CA, USA
D. Irvine , Speech Res. Lab., California Univ., Davis, CA, USA
V.R. Algazi , Speech Res. Lab., California Univ., Davis, CA, USA
K. Brown , Speech Res. Lab., California Univ., Davis, CA, USA
S. Chung , Speech Res. Lab., California Univ., Davis, CA, USA
pp. 93-96

Low bit-rate quantization of LSP parameters using two-dimensional differential coding (Abstract)

Hsiao-Chuan Wang , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Chih-Chung Kuo , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Fu-Rong Jean , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 97-100

Adaptive vector quantization for waveform coding (Abstract)

S. Ardalan , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
J. Foster , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
T.K. Wang , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
pp. 101-104

Tree searched multi-stage vector quantization of LPC parameters for 4 kb/s speech coding (Abstract)

B. Bhattacharya , Sch. of Eng. Sci., Simon Fraser Univ., Burnaby, BC, Canada
S. Mahmoud , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
W. LeBlanc , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
V. Cuperman , Speech Res. Lab., California Univ., Davis, CA, USA
pp. 105-108

A fast VQ codebook design algorithm for a large number of data (Abstract)

M. Kimura , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
H. Shimodaira , Dept. of Inf. Eng., Tohoku Univ., Sendai, Japan
M. Nakai , Dept. of Inf. Eng., Tohoku Univ., Sendai, Japan
pp. 109-112

Synthesis/coding of audio signals using optimized wavelets (Abstract)

A.H. Tewfik , Dept. of Electr. Eng., Minnesota Univ., Minneapolis, MN, USA
D. Sinha , Dept. of Electr. Eng., Minnesota Univ., Minneapolis, MN, USA
pp. 113-116

Thinned lattice filter for LPC analysis (Abstract)

Kwok-Wah Law , Dept. of Electron. Eng., City Polytech. of Hong Kong, Kowloon, Hong Kong
Cheung-Fat Chan , Dept. of Electron. Eng., City Polytech. of Hong Kong, Kowloon, Hong Kong
pp. 117-120

RASTA-PLP speech analysis technique (Abstract)

H. Hermansky , US West Advanced Technologies, Boulder, CO, USA
N. Morgan , Dept. of Electron. Eng., City Polytech. of Hong Kong, Kowloon, Hong Kong
P. Kohn , Speech Res. Lab., California Univ., Davis, CA, USA
A. Bayya , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
pp. 121-124

Exploiting recursive parameter trajectories in speech analysis (Abstract)

K. Yoo , Dept. of Electr. Eng., Missouri Univ., Rolla, MO, USA
N. Hubing , Dept. of Electr. Eng., Missouri Univ., Rolla, MO, USA
pp. 125-128

Real-time robust pitch detector (Abstract)

M.C. Dogan , Dept. of Electr. Eng.-Syst., Univ. of Southern California, Los Angeles, CA, USA
J.M. Mendel , Dept. of Electr. Eng.-Syst., Univ. of Southern California, Los Angeles, CA, USA
pp. 129-132

Pitch determination of noisy speech using higher order statistics (Abstract)

J.A.R. Fonollosa , ETSE Telecommun., Univ. Politecnica de Catalunya, Barcelona, Spain
A. Moreno , ETSE Telecommun., Univ. Politecnica de Catalunya, Barcelona, Spain
pp. 133-136

An adaptive algorithm for mel-cepstral analysis of speech (Abstract)

K. Tokuda , ETSE Telecommun., Univ. Politecnica de Catalunya, Barcelona, Spain
S. Imai , Speech Res. Lab., California Univ., Davis, CA, USA
T. Fukada , Inf. Syst. Res. Center, Canon Inc., Kawasaki, Japan
T. Kobayashi , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
pp. 137-140

Signal approximation via data-adaptive normalized Gaussian functions and its applications for speech processing (Abstract)

K. Chen , Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
S. Qian , National Instruments, Austin, TX, USA
D. Chen , National Instruments, Austin, TX, USA
pp. 141-144

Voice transformation using PSOLA technique (Abstract)

H. Valbret , Telecom Paris, France
J.P. Tubach , Telecom Paris, France
E. Moulines , Telecom Paris, France
pp. 145-148

A scheme for pitch extraction of speech using autocorrelation function with frame length proportional to the time lag (Abstract)

S. Seto , Telecom Paris, France
H. Fujisaki , Telecom Paris, France
K. Hirose , Fac. of Eng., Tokyo Univ., Japan
pp. 149-152

Cinematic techniques for speech processing: temporal decomposition and multivariate linear prediction (Abstract)

M.-J. Caraty , Univ. Pierre et Marie Curie, Paris, France
F. Bimbot , Univ. Pierre et Marie Curie, Paris, France
C. Montacie , Univ. Pierre et Marie Curie, Paris, France
P. Deleglise , Univ. Pierre et Marie Curie, Paris, France
pp. 153-156

Cooccurrence smoothing for stochastic language modeling (Abstract)

U. Essen , Philips GmbH Forschungslaboratorien, Aachen, Germany
V. Steinbiss , Philips GmbH Forschungslaboratorien, Aachen, Germany
pp. 161-164

Task adaptation in stochastic language models for continuous speech recognition (Abstract)

T. Yamada , NTT Human Interface Labs., Tokyo, Japan
S. Matsunaga , NTT Human Interface Labs., Tokyo, Japan
K. Shikano , NTT Human Interface Labs., Tokyo, Japan
pp. 165-168

Hybrid grammar-bigram speech recognition system with first-order dependence model (Abstract)

J.H. Wright , Centre for Commun. Res., Bristol Univ., UK
G.J.F. Jones , Centre for Commun. Res., Bristol Univ., UK
E.N. Wrigley , Centre for Commun. Res., Bristol Univ., UK
pp. 169-172

Hidden Markov estimation for unrestricted stochastic context-free grammars (Abstract)

J. Kupiec , Xerox Palo Alto Res. Center, CA, USA
pp. 177-180

Integrating probabilistic LR parsing into speech understanding systems (Abstract)

V. Zue , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
D. Goddeau , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
pp. 181-184

A unified framework to incorporate speech and language information in spoken language processing (Abstract)

Yi-Chung Lin , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Tung-Hui Chiang , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Keh-Yih Su , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 185-188

Robust parsing for spoken language systems (Abstract)

S. Seneff , Lab for Comput. Sci., MIT, Cambridge, MA, USA
pp. 189-192

A speech understanding system based on statistical representation of semantics (Abstract)

C.-H. Lee , AT&T Bell Labs., Murray Hill, NJ, USA
R. Pieraccini , AT&T Bell Labs., Murray Hill, NJ, USA
E. Tzoukermann , AT&T Bell Labs., Murray Hill, NJ, USA
J.-L. Gauvain , AT&T Bell Labs., Murray Hill, NJ, USA
E. Levin , AT&T Bell Labs., Murray Hill, NJ, USA
J.G. Wilpon , AT&T Bell Labs., Murray Hill, NJ, USA
Z. Gorelov , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 193-196

A real-time task-oriented speech understanding system using keyword-spotting (Abstract)

Y. Takebayashi , Toshiba Corp., Kawasaki, Japan
H. Tsuboi , Toshiba Corp., Kawasaki, Japan
pp. 197-200

A structured network architecture for adaptive language acquisition (Abstract)

A.L. Gorin , AT&T Bell Labs., Murray Hill, NJ, USA
L.G. Miller , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 201-204

PARSEC: a structured connectionist parsing system for spoken language (Abstract)

A. Waibel , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
A.N. Jain , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
D.S. Touretzky , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 205-208

Testing generality in JANUS: a multi-lingual speech translation system (Abstract)

T. Sloboda , AT&T Bell Labs., Murray Hill, NJ, USA
H. Saito , AT&T Bell Labs., Murray Hill, NJ, USA
A. McNair , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
J. Tebelskis , AT&T Bell Labs., Murray Hill, NJ, USA
C. Augustine , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
I. Rogina , AT&T Bell Labs., Murray Hill, NJ, USA
L. Osterholtz , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 209-212

Efficient grammar processing for a spoken language translation system (Abstract)

F.C.N. Pereira , AT&T Bell Labs., Murray Hill, NJ, USA
D.B. Roe , AT&T Bell Labs., Murray Hill, NJ, USA
R.W. Sproat , AT&T Bell Labs., Murray Hill, NJ, USA
A. Macarron , AT&T Bell Labs., Murray Hill, NJ, USA
P.J. Moreno , AT&T Bell Labs., Murray Hill, NJ, USA
M.D. Riley , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 213-216

Accent phrase segmentation using pitch pattern clustering (Abstract)

H. Shimodaira , Dept. of Inf. Eng., Tohoku Univ., Sendai, Japan
M. Kumura , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 217-220

Automatic recognition of intonational features (Abstract)

M. Ostendorf , Boston Univ., MA, USA
C.W. Wightman , Boston Univ., MA, USA
pp. 221-224

Use of acoustic sentence level and lexical stress in HSMM speech recognition (Abstract)

F. McInnes , Center for Speech Technol. Res., Edinburgh Univ., UK
D. McKelvie , Center for Speech Technol. Res., Edinburgh Univ., UK
J.L. Hieronymus , Center for Speech Technol. Res., Edinburgh Univ., UK
pp. 225-227

The use of emphasis to automatically summarize a spoken discourse (Abstract)

F.R. Chen , Xerox Palo Alto Res. Center, CA, USA
M. Withgott , Xerox Palo Alto Res. Center, CA, USA
pp. 229-232

An improved approach to the hidden Markov model decomposition of speech and noise (Abstract)

M.J.F. Gales , Dept. of Eng., Cambridge Univ., UK
S. Young , Dept. of Eng., Cambridge Univ., UK
pp. 233-236

Speech recognition in noise using a projection-based likelihood measure for mixture density HMM's (Abstract)

M.A. Clements , Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
B.A. Carlson , Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 237-240

Spectral contrast normalization and other techniques for speech recognition in noise (Abstract)

D.C. Bateman , Marconi Speech & Information Systems, Portsmouth, UK
D.K. Bye , Marconi Speech & Information Systems, Portsmouth, UK
M.J. Hunt , Marconi Speech & Information Systems, Portsmouth, UK
pp. 241-244

A robust connected-words recognizer (Abstract)

H.W. Ruehl , Philips Kommunikations Industrie AG, Nuernberg, Germany
S. Dobler , Philips Kommunikations Industrie AG, Nuernberg, Germany
P. Meyer , Philips Kommunikations Industrie AG, Nuernberg, Germany
pp. 245-248

HMM modeling for speaker independent voice dialing in car environment (Abstract)

P. Ruscitti , Philips Kommunikations Industrie AG, Nuernberg, Germany
L. Fissore , CSELT, Torino, Italy
P. Laface , Philips Kommunikations Industrie AG, Nuernberg, Germany
pp. 249-252

Speech recognition using hidden Markov model decomposition and a general background speech model (Abstract)

M.Q. Wang , Dept. of Eng., Cambridge Univ., UK
S.J. Young , Dept. of Eng., Cambridge Univ., UK
pp. 253-256

Efficient joint compensation of speech for the effects of additive noise and linear filtering (Abstract)

R.M. Stern , Philips Kommunikations Industrie AG, Nuernberg, Germany
F.-H. Liu , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Acero , Dept. of Eng., Cambridge Univ., UK
pp. 257-260

Telephone channel normalization for automatic speech recognition (Abstract)

B. Mazor , GTE Laboratories Inc., Waltham, MA, USA
S. Lerner , GTE Laboratories Inc., Waltham, MA, USA
pp. 261-264

Non-linear spectral subtraction (NSS) and hidden Markov models for robust speech recognition in car noise environments (Abstract)

M. Blanchet , Matra Commun., Bois d'Arcy, France
P. Lockwood , Matra Commun., Bois d'Arcy, France
J. Boudy , Matra Commun., Bois d'Arcy, France
pp. 265-268

A robust speech/non-speech detection algorithm using time and frequency-based features (Abstract)

B. Mak , Speech Technol. Lab., Panasonic Technologies Inc., Santa Barbara, CA, USA
J.-C. Junqua , Speech Technol. Lab., Panasonic Technologies Inc., Santa Barbara, CA, USA
B. Reaves , Speech Technol. Lab., Panasonic Technologies Inc., Santa Barbara, CA, USA
pp. 269-272

Pitch dependent phone modelling for HMM based speech recognition (Abstract)

H. Singer , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
S. Sagayama , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
pp. 273-276

Single sensor active noise cancellation based on the EM algorithm (Abstract)

D. Gauger , AT&T Bell Labs., Murray Hill, NJ, USA
K.C. Zangi , Speech Technol. Lab., Panasonic Technologies Inc., Santa Barbara, CA, USA
A.V. Oppenheim , MIT, Cambridge, MA, USA
E. Weinstein , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
M. Feder , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 277-280

Hands-free voice communication in an automobile with a microphone array (Abstract)

P. Papamichalis , Texas Instruments, Dallas, TX, USA
V. Viswanathan , Texas Instruments, Dallas, TX, USA
S. Oh , Texas Instruments, Dallas, TX, USA
pp. 281-284

Beamforming microphone arrays for speech enhancement (Abstract)

R.J. Mammone , 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
K. Farrell , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
pp. 285-288

Speech enhancement using state dependent dynamical system model (Abstract)

Y. Ephraim , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 289-292

A wideband blind identification approach to speech acquisition using a microphone array (Abstract)

L. Tong , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
R. Liu , AT&T Bell Labs., Murray Hill, NJ, USA
Y.F. Huang , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
V.C. Soon , Dept. of Electr. Eng., Notre Dame Univ., IN, USA
pp. 293-296

Dual-channel speech enhancement with auditory spectrum based constraints (Abstract)

S. Nandkumar , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
J.H.L. Hansen , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
pp. 297-300

Vector equalization in hidden Markov models for noisy speech recognition (Abstract)

B.H. Juang , AT&T Bell Labs., Murray Hill, NJ, USA
K.K. Paliwal , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 301-304

A microphone array for car environments (Abstract)

Y. Grenier , ENST, Paris, France
pp. 305-308

Robust estimation of AR parameters and its application for speech enhancement (Abstract)

Souguil Ann , AT&T Bell Labs., Murray Hill, NJ, USA
Byung-Gook Lee , AT&T Bell Labs., Murray Hill, NJ, USA
Y. Grenier , Dept. of Electron. Eng., Changwon Nat. Univ., Kyungnam, South Korea
Iickho Song , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
pp. 309-312

CELP coding at 4.0 kb/sec and below: improvements to FS-1016 (Abstract)

S.R. Koch , GE Corp. Res. & Dev., Schenectady, NY, USA
R.L. Zinser , GE Corp. Res. & Dev., Schenectady, NY, USA
pp. 313-316

Ultra-fast CELP coding using deterministic multi-codebook innovations (Abstract)

D. Lin , Hughes Network Systems, Germantown, MD, USA
pp. 317-320

Improved 4.8 kb/s CELP coding using two-stage vector quantization with multiple candidates (LCELP) (Abstract)

K. Ozawa , AT&T Bell Labs., Murray Hill, NJ, USA
J. Takizawa , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
M. Serizawa , NEC Corp., Kanagawa, Japan
S. Ikeda , AT&T Bell Labs., Murray Hill, NJ, USA
T. Miyano , NEC Corp., Kanagawa, Japan
pp. 321-324

Tree-structured delta codebook for an efficient implementation of CELP (Abstract)

Y. Ohta , Fujitsu Laboratories Ltd., Kawasaki, Japan
T. Taniguchi , Fujitsu Laboratories Ltd., Kawasaki, Japan
Y. Tanaka , Fujitsu Laboratories Ltd., Kawasaki, Japan
pp. 325-328

Fractional excitation and other efficient transformed codebooks for CELP coding of speech (Abstract)

M. Delprat , Matra Commun., Bois d'Arcy, France
C. Baroux , Matra Commun., Bois d'Arcy, France
F. Dervaux , Matra Commun., Bois d'Arcy, France
C. Gruet , Matra Commun., Bois d'Arcy, France
pp. 329-332

Excitation modeling based on speech residual information (Abstract)

V. Cuperman , Sch. of Eng. Sci., Simon Fraser Univ., Burnaby, BC, Canada
P. Lupini , Sch. of Eng. Sci., Simon Fraser Univ., Burnaby, BC, Canada
pp. 333-336

Generalized analysis-by-synthesis coding and its application to pitch prediction (Abstract)

R.P. Ramachandran , AT&T Bell Labs., Murray Hill, NJ, USA
W.B. Kleijn , AT&T Bell Labs., Murray Hill, NJ, USA
P. Kroon , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 337-340

A deconvolution-based efficient method for generating the excitation in linear predictive speech coding (Abstract)

D. Docampo , ETSI Telecomunicacion, Vigo Univ., Spain
F. Gonzalez , ETSI Telecomunicacion, Vigo Univ., Spain
F. Perez , ETSI Telecomunicacion, Vigo Univ., Spain
V. Abreu , ETSI Telecomunicacion, Vigo Univ., Spain
pp. 341-344

Mixture excitations and finite-state CELP speech coders (Abstract)

H. Abut , ETSI Telecomunicacion, Vigo Univ., Spain
A. Benyassine , New Jersey Inst. of Technol., Newark, NJ, USA
pp. 345-348

Improved phonetically-segmented vector excitation coding at 3.4 kb/s (Abstract)

A. Gersho , Dept of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
S. Wang , Dept of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
pp. 349-352

Predictor codebooks for speaker-independent speech recognition (Abstract)

T. Kawabata , NTT Basic Res. Labs., Tokyo, Japan
pp. 353-356

An improved VQ codebook design algorithm for HMM (Abstract)

H.S. Lee , Dept of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
J.M. Koo , DigiCom Inst. of Telematics, Seoul, South Korea
C.K. Un , ETSI Telecomunicacion, Vigo Univ., Spain
pp. 357-360

Mixture density estimators in Viterbi training (Abstract)

C.J. Wellekens , Lernout & Hauspie Speech Products, Ieper, Belgium
pp. 361-364

HMM based on pair-wise Bayes classifiers (Abstract)

T. Kawahara , Dept. of Inf. Sci., Kyoto Univ., Japan
S. Doshita , Dept. of Inf. Sci., Kyoto Univ., Japan
pp. 365-368

Temporal decomposition for the initialization of a HMM isolated word-recognizer (Abstract)

M. Taylor , Telecom Paris, France
F. Bimbot , Telecom Paris, France
pp. 369-372

Modeling improvement of the continuous hidden Markov model for speech recognition (Abstract)

Z.-P. Hu , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
S. Imai , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
pp. 373-376

A family of parallel hidden Markov models (Abstract)

R. De Mori , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
D. Giuliani , ETSI Telecomunicacion, Vigo Univ., Spain
F. Brugnara , IRST, Povo di Trento, Italy
M. Omologo , ETSI Telecomunicacion, Vigo Univ., Spain
pp. 377-380

Modeling state durations in hidden Markov models for automatic speech recognition (Abstract)

P. Ramesh , AT&T Bell Labs., Murray Hill, NJ, USA
J.G. Wilpon , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 381-384

Representing dynamic features of phonetic segment in an orthogonalized codebook of HMM based speech recognition system (Abstract)

J. Iwasaki , Toshiba Corp., Kawasaki, Japan
Y. Masai , Toshiba Corp., Kawasaki, Japan
T. Nitta , Toshiba Corp., Kawasaki, Japan
H. Matsu'ura , Toshiba Corp., Kawasaki, Japan
pp. 385-388

Context modeling with the stochastic segment model (Abstract)

M. Ostendorf , Boston Univ., MA, USA
O. Kimball , Boston Univ., MA, USA
I. Bechwati , Boston Univ., MA, USA
pp. 389-392

Context-dependent hidden control neutral network architecture for continuous speech recognition (Abstract)

B. Petek , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
J. Tebelskis , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 397-400

Fast learning for multi-layer perceptrons using statistical techniques (Abstract)

E.R. Buhrke , Dept. of Electr. & Comput. Eng., Illinois Inst. of Technol., Chicago, IL, USA
J.L. LoCicero , Dept. of Electr. & Comput. Eng., Illinois Inst. of Technol., Chicago, IL, USA
pp. 401-404

A neural fuzzy training approach for continuous speech recognition improvement (Abstract)

Y. Komori , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
pp. 405-408

Speaker-independent phoneme recognition using large-scale neural networks (Abstract)

M. Sugiyama , Boston Univ., MA, USA
S. Nakamura , Fac. of Sci. & Technol., Keio Univ., Yokohama, Japan
H. Sawai , Dept. of Electr. & Comput. Eng., Illinois Inst. of Technol., Chicago, IL, USA
pp. 409-412

A multi-task neural network approach to speech recognition (Abstract)

E.L. Richards , Dept. of Comput. Sci., Colorado Univ., Boulder, CO, USA
pp. 413-416

Prototype-based discriminative training for various speech units (Abstract)

S. Katagiri , ATR Auditory & Visual Perception Res. Lab., Kyoto, Japan
E. McDermott , ATR Auditory & Visual Perception Res. Lab., Kyoto, Japan
pp. 417-420

Incorporating acoustic-phonetic knowledge in hybrid TDNN/HMM frameworks (Abstract)

C. Dugast , Philips Res. Lab. Aachen, Germany
L. Devillers , ATR Auditory & Visual Perception Res. Lab., Kyoto, Japan
pp. 421-424

Error-correcting training for phoneme spotting (Abstract)

M.A. Bush , Xerox Palo Alto Res. Center, CA, USA
L.T. Niles , Xerox Palo Alto Res. Center, CA, USA
L.D. Wilcox , Xerox Palo Alto Res. Center, CA, USA
pp. 425-428

Parallel sequential running neural network and its application to automatic speech recognition (Abstract)

Huaiyu Zeng , Inst. of Acoust., Acad. Sinica, Beijing, China
Tiecheng Yu , Inst. of Acoust., Acad. Sinica, Beijing, China
pp. 429-432

A segment-based speaker adaptation neural network applied to continuous speech recognition (Abstract)

H. Sawai , Xerox Palo Alto Res. Center, CA, USA
Y. Komori , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
K. Fukuzawa , ATR Interpreting Telephony Res. Lab., Kyoto, Japan
M. Sugiyama , Toshiba Corp., Kawasaki, Japan
pp. 433-436

A Bayesian approach to speaker adaptation for the stochastic segment model (Abstract)

J.R. Rohlicek , Xerox Palo Alto Res. Center, CA, USA
B.F. Necioglu , Boston Univ., MA, USA
M. Ostendorf , Boston Univ., MA, USA
pp. 437-440

An LVQ based reference model for speaker-adaptive speech recognition (Abstract)

J. Tebelskis , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
O. Schmidbauer , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 441-444

Robust speaker adaptation using a piecewise linear acoustic mapping (Abstract)

P.V. de Souza , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
D. Nahamoo , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
L.R. Bahl , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
A.J. Nadas , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
J.R. Bellegarda , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M.A. Picheny , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 445-448

A piecewise linear spectral mapping for supervised speaker adaptation (Abstract)

H. Matsukoto , Dept. of Electr. & Electron. Eng., Shinshu Univ., Nagano, Japan
H. Inoue , Dept. of Electr. & Electron. Eng., Shinshu Univ., Nagano, Japan
pp. 449-452

Rapid connectionist speaker adaptation (Abstract)

M. Witbrock , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
P. Haffner , Dept. of Electr. & Electron. Eng., Shinshu Univ., Nagano, Japan
pp. 453-456

Speaker adaptive phoneme recognition based on feature mapping from spectral domain to probabilistic domain (Abstract)

T. Kobayashi , Dept. of Electr. Eng., Waseda Univ., Tokyo, Japan
J. Osada , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Y. Uchiyama , Dept. of Electr. & Electron. Eng., Shinshu Univ., Nagano, Japan
K. Shirai , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 457-460

Fast speaker adaptation combined with soft vector quantization in an HMM speech recognition system (Abstract)

A. Kaltenmeir , Daimler Benz AG, Ulm, Germany
P. Regal-Brietzmann , Daimler Benz AG, Ulm, Germany
F. Class , Daimler Benz AG, Ulm, Germany
K. Trottler , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 461-464

Speaker normalization for speech recognition (Abstract)

X. Huang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 465-468

Speaker independent speech recognition method using training speech from a small number of speakers (Abstract)

M. Miyata , Matsushita Research Institute Tokyo, Inc., Kawasaki, Japan
K. Niyada , Matsushita Research Institute Tokyo, Inc., Kawasaki, Japan
M. Hoshimi , Matsushita Research Institute Tokyo, Inc., Kawasaki, Japan
S. Hiraoka , Matsushita Research Institute Tokyo, Inc., Kawasaki, Japan
pp. 469-472

Segmental GPD training of HMM based speech recognizer (Abstract)

W. Chou , AT&T Bell Labs., Murray Hill, NJ, USA
B.H. Juang , AT&T Bell Labs., Murray Hill, NJ, USA
C.H. Lee , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 473-476

Adaptation of large vocabulary recognition system parameters (Abstract)

M.A. Picheny , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
S. Roukos , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
L. Bahl , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P.V. de Souza , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
D. Nahamoo , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 477-480

Improved acoustic modeling with Bayesian learning (Abstract)

J.-L. Gauvain , AT&T Bell Labs., Murray Hill, NJ, USA
C.-H. Lee , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 481-484

Vocabulary learning and environment normalization in vocabulary-independent speech recognition (Abstract)

H.-W. Hon , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
K.-F. Lee , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 485-488

Discriminative template training for dynamic programming speech recognition (Abstract)

Biing-Hwang Juang , Logica Cambridge Ltd., UK
Pao-Chung Chang , Telecommunication Labs., Minist. of Commun., Taiwan
pp. 493-496

Application of a generalized probabilistic descent method to dynamic time warping-based speech recognition (Abstract)

S. Katagiri , ATR Auditory & Visual Perception Res. Lab., Kyoto, Japan
T. Komori , ATR Auditory & Visual Perception Res. Lab., Kyoto, Japan
pp. 497-500

Discriminative analysis for feature reduction in automatic speech recognition (Abstract)

E.L. Bocchieri , AT&T Bell Labs., Murray Hill, NJ, USA
J.G. Wilpon , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 501-504

High performance connected digit recognition using codebook exponents (Abstract)

Y. Normandin , Centre de Recherche Inf. de Montreal, Que., Canada
R. De Mori , Centre de Recherche Inf. de Montreal, Que., Canada
R. Cardin , Centre de Recherche Inf. de Montreal, Que., Canada
pp. 505-508

On the performance of polynomial and HMM whole-word classifiers for digit recognition over telephone (Abstract)

H. Katterfeldt , Daimler-Benz Research Center, Ulm, Germany
P. Regel-Brietzmann , Daimler-Benz Research Center, Ulm, Germany
B. Vater , Daimler-Benz Research Center, Ulm, Germany
pp. 513-516

SWITCHBOARD: telephone speech corpus for research and development (Abstract)

E.C. Holliman , Texas Instruments, Inc., Dallas, TX, USA
J.J. Godfrey , Texas Instruments, Inc., Dallas, TX, USA
J. McDaniel , Texas Instruments, Inc., Dallas, TX, USA
pp. 517-520

Recognition of hesitations in spontaneous speech (Abstract)

D. O'Shaughnessy , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 521-524

An improved speech detection algorithm for isolated Korean utterances (Abstract)

C.K. Park , Electron. & Telecommun. Res. Inst., Daejon, South Korea
M. Hahn , Electron. & Telecommun. Res. Inst., Daejon, South Korea
pp. 525-528

Static representation of speech dynamics for isolated word recognition (Abstract)

Jian-Xiong Wu , Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
Chorkin Chan , Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
pp. 529-532

Robust automatic time alignment of orthographic transcriptions with unconstrained speech (Abstract)

C. Hemphill , Texas Instruments Inc., Dallas, TX, USA
D. Fisher , Texas Instruments Inc., Dallas, TX, USA
G. Doddington , Texas Instruments Inc., Dallas, TX, USA
J. Godfrey , Texas Instruments Inc., Dallas, TX, USA
J. McDaniel , Texas Instruments Inc., Dallas, TX, USA
E. Holliman , Texas Instruments Inc., Dallas, TX, USA
B. Wheatley , Texas Instruments Inc., Dallas, TX, USA
pp. 533-536

On increasing structural complexity of finite state speech models (Abstract)

P. Conner , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
S.V. Vaseghi , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
pp. 537-540

Application of the modulation model to speech recognition (Abstract)

A.B. Fineberg , 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
J.L. Flanagan , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
pp. 541-544

HMM representation of quantized articulatory features for recognition of highly confusable words (Abstract)

K. Erler , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
L. Deng , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
pp. 545-548

On the use of acoustic-phonetic features in interactive labelling of multi-lingual speech corpora (Abstract)

O. Andersen , Speech Technol. Centre, Aalborg Univ., Denmark
P. Dalsgaard , Speech Technol. Centre, Aalborg Univ., Denmark
W. Barry , Center for Comput. Aids for Ind. Productivity, Rutgers Univ., Piscataway, NJ, USA
R. Jorgensen , Texas Instruments Inc., Dallas, TX, USA
pp. 549-552

Phonemic HMM constrained by statistical VQ-code transition (Abstract)

T. Matsuoka , NTT Human Interface Labs., Tokyo, Japan
K. Shikano , NTT Human Interface Labs., Tokyo, Japan
S. Takahashi , NTT Human Interface Labs., Tokyo, Japan
pp. 553-556

Experiments on speaker-independent phone recognition using BREF (Abstract)

J.-L. Gauvain , LIMSI-CNRS, Orsay, France
L.F. Lamel , LIMSI-CNRS, Orsay, France
pp. 557-560

Experiments on stress-dependent phone modelling for continuous speech recognition (Abstract)

G. Adda , LIMSI-CNRS, Orsay, France
M. Adda-Decker , LIMSI-CNRS, Orsay, France
pp. 561-564

Use of semi-Markov models for speaker-independent phoneme recognition (Abstract)

J. Sorensen , Dept. of Electr., Comput., & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
M. Savic , Dept. of Electr., Comput., & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
N. Ratnayake , Dept. of Electr., Comput., & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
pp. 565-568

The general use of tying in phoneme-based HMM speech recognisers (Abstract)

S.J. Young , Dept. of Eng., Cambridge Univ., UK
pp. 569-572

A successive state splitting algorithm for efficient allophone modeling (Abstract)

S. Sagayama , ATR Interpreting Telephone Res. Lab., Kyoto, Japan
J. Takami , ATR Interpreting Telephone Res. Lab., Kyoto, Japan
pp. 573-576

Acoustic modelling of subword units in the Isadora speech recognizer (Abstract)

T. Kuhn , Lehrstuhl fuer Inf., Erlangen Univ., Germany
W. Eckert , Lehrstuhl fuer Inf., Erlangen Univ., Germany
H. Niemann , Lehrstuhl fuer Inf., Erlangen Univ., Germany
S. Rieck , Lehrstuhl fuer Inf., Erlangen Univ., Germany
E.G. Schukat-Talamazzini , Lehrstuhl fuer Inf., Erlangen Univ., Germany
pp. 577-580

Recognition of demisyllable based units using semicontinuous hidden Markov models (Abstract)

B. Plannerer , Lehrstuhl fuer Datenverarbeitung, Tech. Univ. Munchen, Germany
G. Ruske , Lehrstuhl fuer Datenverarbeitung, Tech. Univ. Munchen, Germany
pp. 581-584

The automatic recognition of stop consonants using hidden Markov models (Abstract)

M.W. Coetzer , Lehrstuhl fuer Inf., Erlangen Univ., Germany
T. Waardenburg , Stellenbosch Univ., South Africa
J.A. de Preez , Stellenbosch Univ., South Africa
pp. 585-588

Relationship among phoneme/word recognition rate, perplexity and sentence recognition and comparison of language models (Abstract)

I. Murase , Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan
S. Nakagawa , Dept. of Inf. & Comput. Sci., Toyohashi Univ. of Technol., Japan
pp. 589-592

Hybrid segmental-LVQ/HMM for large vocabulary speech recognition (Abstract)

P. Kenny , INRS-Telecommun., Nun's Island, Que., Canada
M. Lennig , INRS-Telecommun., Nun's Island, Que., Canada
V. Gupta , INRS-Telecommun., Nun's Island, Que., Canada
Y.M. Cheng , INRS-Telecommun., Nun's Island, Que., Canada
S. Parthasarathy , Texas Instruments Inc., Dallas, TX, USA
D. O'Shaughnessy , INRS-Telecommun., Nun's Island, Que., Canada
P. Mermelstein , INRS-Telecommun., Nun's Island, Que., Canada
pp. 593-596

Continuous speech recognition with modified learning vector quantization algorithm and two-level DP-matching (Abstract)

T. Sone , Res. Center for Appl. Inf. Sci., Tohoku Univ., Sendai, Japan
S. Makino , Res. Center for Appl. Inf. Sci., Tohoku Univ., Sendai, Japan
K. Kido , Res. Center for Appl. Inf. Sci., Tohoku Univ., Sendai, Japan
M. Endo , Res. Center for Appl. Inf. Sci., Tohoku Univ., Sendai, Japan
pp. 597-600

Connectionist probability estimation in the DECIPHER speech recognition system (Abstract)

N. Morgan , Int. Comput. Sci. Inst., Berkeley, CA, USA
H. Franco , Res. Center for Appl. Inf. Sci., Tohoku Univ., Sendai, Japan
S. Renals , Int. Comput. Sci. Inst., Berkeley, CA, USA
M. Cohen , Res. Center for Appl. Inf. Sci., Tohoku Univ., Sendai, Japan
pp. 601-604

Expanding the vocabulary of a connectionist recognizer trained on the DARPA Resource Management corpus (Abstract)

H. Lucke , Dept. of Eng., Cambridge Univ., UK
F. Fallside , Dept. of Eng., Cambridge Univ., UK
pp. 605-608

Speech recognition using stochastic segment neural networks (Abstract)

H.C. Leung , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
V.W. Zue , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
I.L. Heherington , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
pp. 613-616

A real-time recurrent error propagation network word recognition system (Abstract)

T. Robinson , Dept. of Eng., Cambridge Univ., UK
pp. 617-620

Speech recognition using segmental neural nets (Abstract)

R. Schwartz , Res. Center for Appl. Inf. Sci., Tohoku Univ., Sendai, Japan
G. Zavaliagkos , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
S. Austin , BNN Syst. & Technol., Cambridge, MA, USA
J. Makhoul , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
pp. 625-628

A speech recognizer using radial basis function neural networks in an HMM framework (Abstract)

R.P. Lippman , MIT Lincoln Lab., Lexington, MA, USA
E. Singer , MIT Lincoln Lab., Lexington, MA, USA
pp. 629-632

Adaptive language modeling using minimum discriminant estimation (Abstract)

V. Della Pietra , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
R.L. Mercer , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
S. Roukos , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
S. Della Pietra , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 633-636

Pole-zero code excited linear prediction using perceptually weighted error criterion (Abstract)

M. Dunn , Dept. of Electron. & Electr. Eng., Univ., Coll. Dublin, Ireland
A.D. Fagan , Dept. of Electron. & Electr. Eng., Univ., Coll. Dublin, Ireland
B. Murray , Dept. of Electron. & Electr. Eng., Univ., Coll. Dublin, Ireland
pp. 637-639
81 ms
(Ver 3.3 (11022016))