The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (1994)
Adelaide, SA, Australia
Apr. 19, 1994 to Apr. 22, 1994
ISBN: 0-7803-1775-0
TABLE OF CONTENTS

Speech enhancement based on a new set of auditory constrained parameters (Abstract)

J.H.L. Hansen , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
S. Nandkumar , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
pp. 1-4

Low residual noise speech enhancement utilizing time-frequency filtering (Abstract)

G. Whipple , Dept. of Defense, Fort Meade, MD, USA
pp. 5-8

Cepstrum based deconvolution for speech dereverberation (Abstract)

S. Subramaniam , Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
A.P. Petropulu , Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
pp. 9-I12

A comparative analysis of Japanese and English digit recognition (Abstract)

J. Picone , Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
K. Kondo , Tsukuba Res. & Dev. Center, Ibaraki, Japan
pp. 101-104

Application of vector quantized hidden Markov modeling to telephone network based connected digit recognition (Abstract)

E.R. Buhrke , AT&T Bell Labs., Murray Hill, NJ, USA
R. Cardin , Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
pp. 105-108

Sources of degradation of speech recognition in the telephone network (Abstract)

R.M. Stern , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
P.J. Moreno , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 109-112

The development of file formats for very large speech corpora: SPHERE and SHORTEN (Abstract)

T. Robinson , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
J.S. Garofolo , Nat. Inst. of Stand. & Technol., USA
pp. 113-116

Toward vocabulary independent telephone speech recognition (Abstract)

B.J. Wheatley , Texas Instrum. Inc., Dallas, TX, USA
Y.H. Kao , Texas Instrum. Inc., Dallas, TX, USA
P.K. Rajasekaran , Texas Instrum. Inc., Dallas, TX, USA
C.T. Hemphill , Texas Instrum. Inc., Dallas, TX, USA
pp. 117-120

On the use of data-driven clustering technique for identification of poly- and mono-phonemes for four European languages (Abstract)

O. Anderson , Center for PersonKommunikation, Aalborg Univ., Denmark
W. Barry , Texas Instrum. Inc., Dallas, TX, USA
P. Dalsgaard , Center for PersonKommunikation, Aalborg Univ., Denmark
pp. 121-124

Speaker adaptation of tied-mixture-based phoneme models for text-prompted speaker recognition (Abstract)

S. Furui , NTT Human Interface Labs., Tokyo, Japan
T. Matsui , NTT Human Interface Labs., Tokyo, Japan
pp. 125-128

Robust cepstral features for speaker identification (Abstract)

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. 129-132

Comparative performance of spectral subtraction and HMM-based speech enhancement strategies with application to hearing and design (Abstract)

H. Sheikhzadeh , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
L. Deng , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
R.L. Brennan , Texas Instrum. Inc., Dallas, TX, USA
H. Sameti , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
pp. 13-16

A quantitative assessment of the relative speaker discriminating properties of phonemes (Abstract)

J.S. Mason , Univ. Coll. of Swansea, UK
J.P. Eatock , Univ. Coll. of Swansea, UK
pp. 133-136

Text-dependent speaker recognition using the information in the higher frequency band (Abstract)

S. Hayakawa , Sch. of Eng., Nagoya Univ., Japan
F. Itakura , Sch. of Eng., Nagoya Univ., Japan
pp. 137-140

A distributed decision approach to speaker verification (Abstract)

Chung-Tshuy Lee , Dept. of Electr. Eng. & Comput. Sci., Northwestern Univ., Evanston, IL, USA
Chung-Chieh Lee , Dept. of Electr. Eng. & Comput. Sci., Northwestern Univ., Evanston, IL, USA
M.A. Lund , Dept. of Electr. Eng. & Comput. Sci., Northwestern Univ., Evanston, IL, USA
R.W. Bossemeyer , Texas Instrum. Inc., Dallas, TX, USA
pp. 141-144

A robust, segmental method for text independent speaker identification (Abstract)

M. Schmidt , BBN Syst. & Technol. Corp., Cambridge, MA, USA
H. Gish , BBN Syst. & Technol. Corp., Cambridge, MA, USA
A. Mielke , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 145-148

Investigations on speaker characterization from Orphee system techniques (Abstract)

M.-J. Caraty , Univ. Pierre et Marie Curie, Paris, France
J.-L. Le Floch , Univ. Pierre et Marie Curie, Paris, France
C. Montacie , Univ. Pierre et Marie Curie, Paris, France
pp. 149-152

A hybrid HMM-MLP speaker verification algorithm for telephone speech (Abstract)

D.M. Lubensky , NYNEX Sci. & Technol. Inc., White Plains, NY, USA
J.M. Naik , NYNEX Sci. & Technol. Inc., White Plains, NY, USA
pp. 153-156

Hierarchical pattern classification for high performance text-independent speaker verification systems (Abstract)

M. Savic , NYNEX Sci. & Technol. Inc., White Plains, NY, USA
J. Sorensen , Dictaphone Corp., Stratford, CT, USA
pp. 157-160

Segmentation of speech using speaker identification (Abstract)

L. Wilcox , Xerox PARC, Palo Alto, CA, USA
V. Balasubramanian , Xerox PARC, Palo Alto, CA, USA
D. Kimber , Xerox PARC, Palo Alto, CA, USA
F. Chen , Xerox PARC, Palo Alto, CA, USA
pp. 161-164

Speaker identification using neural tree networks (Abstract)

K.R. Farrell , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
R.J. Mammone , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
pp. 165-168

Detecting an imposter in telephone speech (Abstract)

E. Barnard , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
J.R. Sachs , Xerox PARC, Palo Alto, CA, USA
J. Schalkwyk , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
pp. 169-172

Noise suppression using a wavelet model (Abstract)

A. Teolis , Inst. for Syst. Res., Maryland Univ., College Park, MD, USA
J.J. Benedetto , Inst. for Syst. Res., Maryland Univ., College Park, MD, USA
pp. 17-20

Low-bit-rate speech coding using a two-dimensional transform of residual signals and waveform interpolation (Abstract)

H. Kimura , Inst. for Syst. Res., Maryland Univ., College Park, MD, USA
Y. Tanaka , Fujitsu Labs. Ltd., Kawasaki, Japan
pp. 173-176

Transform trellis coded quantization of speech using small frame sizes (Abstract)

J.M. Lopez , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
J.L. Perez , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
V.E. Sanchez , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
A.J. Rubio , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
pp. 177-180

High-quality harmonic coding at very low bit rates (Abstract)

H. Leich , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
Gao Yang , Lemout & Hauspie Speech Products, Belgium
pp. 181-184

Non-linear short-term prediction in speech coding (Abstract)

S.D. Hansen , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
H. Nielsen , Tele Danmark Res., Horsholm, Denmark
J. Thyssen , Tele Danmark Res., Horsholm, Denmark
pp. 185-188

Variable bit rate ADPCM via arithmetic coding (Abstract)

R.R. Bitmead , Dept. of Syst. Eng., Australian Nat. Univ., Canberra, ACT, Australia
S. Crisafulli , Dept. of Syst. Eng., Australian Nat. Univ., Canberra, ACT, Australia
R.J. Orsi , Dept. of Syst. Eng., Australian Nat. Univ., Canberra, ACT, Australia
C.R. Watkins , Dept. of Syst. Eng., Australian Nat. Univ., Canberra, ACT, Australia
pp. 189-192

High quality coding of wideband audio signals using transform coded excitation (TCX) (Abstract)

R. Lefebvre , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
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
pp. 193-196

Speech coding based on adaptive mel-cepstral analysis (Abstract)

K. Tokuda , Dept. of Electr. & Electron. Eng., Tokyo Inst. of Technol., Japan
S. Imai , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
H. Matsumura , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
T. Kobayashi , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
pp. 197-200

Spectral entropy: an alternative indicator for rate allocation? (Abstract)

S.A. McClellan , 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. 201-204

Mixed-phase AR models for voiced speech and perceptual cost functions (Abstract)

B.D. Rao , Dept. of Electr. & Comput. Eng., California Univ., San Diego, La Jolla, CA, USA
W.R. Gardner , Dept. of Electr. & Comput. Eng., California Univ., San Diego, La Jolla, CA, USA
pp. 205-208

Speech compression using ARMA model and wavelet transform (Abstract)

Sun-Won Park , Dept. of Electr. Eng. & Comput. Sci., Texas A&M Univ., Kingsville, TX, USA
pp. 209-212

Adaptation techniques for ambience and microphone compensation in the IBM Tangora speech recognition system (Abstract)

D. Nahamoo , Dept. of Comput. Sci., IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
S. Das , Dept. of Comput. Sci., IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
A. Nadas , Dept. of Comput. Sci., IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Picheny , Dept. of Comput. Sci., IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 21-24

SLHMM: a continuous speech recognition system based on Alphanet-HMM (Abstract)

P. Garcia-Teodoro , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
A.J. Rubio-Ayuso , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
J.E. Diaz , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
J.C. Segura-Luna , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
pp. 213-216

Learning state-dependent stream weights for multi-codebook HMM speech recognition systems (Abstract)

A. Waibel , Karlsruhe Univ., Germany
I. Rogina , Karlsruhe Univ., Germany
pp. 217-220

Bayesian learning of the SCHMM parameters for speech recognition (Abstract)

Chin-Hui Lee , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
Chorkin Chan , Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
Qing Huo , Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
pp. 221-224

Non-linear input transformations for discriminative HMMs (Abstract)

M.H. Johnsen , Dept of Telecommun., Inst. of Technol., Trondheim, Norway
F.T. Johansen , Dept of Telecommun., Inst. of Technol., Trondheim, Norway
pp. 225-228

Using MAP estimated parameters to improve HMM speech recognition performance (Abstract)

M.M. Hochberg , Dept of Telecommun., Inst. of Technol., Trondheim, Norway
Y. Gotoh , Div. of Eng., Brown Univ., Providence, RI, USA
H.F. Silverman , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
pp. 229-232

Discriminative training for improved neural prediction systems (Abstract)

A. Mellouk , Lab. de Recherche en Inf., Univ. de Paris-Sud, Orsay, France
P. Gallinari , Dept of Telecommun., Inst. of Technol., Trondheim, Norway
pp. 233-236

An evaluation of cross-language adaptation for rapid HMM development in a new language (Abstract)

B. Wheatley , Central Res. Labs., Texas Instrum. Inc., Dallas, TX, USA
Y. Muthusamy , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
K. Kondo , Dept of Telecommun., Inst. of Technol., Trondheim, Norway
W. Anderson , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
pp. 237-240

Automatic training of phoneme dictionary based on mutual information criterion (Abstract)

S. Okawa , Sch. of Sci. & Eng., Waseda Univ., Tokyo, Japan
K. Shirai , Sch. of Sci. & Eng., Waseda Univ., Tokyo, Japan
T. Kobayashi , Sch. of Sci. & Eng., Waseda Univ., Tokyo, Japan
pp. 241-244

Tree-structured speaker clustering for fast speaker adaptation (Abstract)

S. Sagayama , Sch. of Sci. & Eng., Waseda Univ., Tokyo, Japan
T. Kosaka , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
pp. 245-248

All-phoneme ergodic hidden Markov network for unsupervised speaker adaptation (Abstract)

S. Sagayama , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
S. Matsunaga , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
Y. Miyazawa , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
J.-I. Takami , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
pp. 249-252

Co-channel speaker separation based on maximum-likelihood deconvolution (Abstract)

J.S. Sorensen , Dept. of Electr. Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
Huiqin Gao , 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
pp. 25-28

Phoneme recognition improvement by restricting training section in concatenated HMM training (Abstract)

K. Doi , Ryukoku Univ., Ohtsu, Japan
Y. Ariki , Ryukoku Univ., Ohtsu, Japan
pp. 253-256

A codec candidate for the GSM half rate speech channel (Abstract)

B. Wachter , ANT Nachrichtentech. GmbH, Backnang, Germany
J.-M. Muller , ANT Nachrichtentech. GmbH, Backnang, Germany
pp. 257-260

Complexity reduction for FS-1016 with multistage search (Abstract)

M. Jelinek , ESIEE, Noisy-le-Grand, France
M. Mauc , ESIEE, Noisy-le-Grand, France
G. Baudoin , ESIEE, Noisy-le-Grand, France
pp. 261-264

Speech and channel codec candidate for the half rate digital cellular channel (Abstract)

Yi-Sheng Wang , Hughes Network Syst. Inc., Germantown, MD, USA
K. Swaminathan , Hughes Network Syst. Inc., Germantown, MD, USA
P.K. Gupta , Hughes Network Syst. Inc., Germantown, MD, USA
K. Ganesan , Hughes Network Syst. Inc., Germantown, MD, USA
pp. 265-268

M-LCELP speech coding at 4 kbps (Abstract)

M. Serizawa , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
K. Ozawa , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
T. Nomura , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
T. Miyano , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
pp. 269-272

Comparison of ARMA modelling methods for low bit rate speech coding (Abstract)

W.H. Holmes , Sch. of Electr. Eng., New South Wales Univ., Kensington, NSW, Australia
S. Yim , Sch. of Electr. Eng., New South Wales Univ., Kensington, NSW, Australia
D. Sen , Sch. of Electr. Eng., New South Wales Univ., Kensington, NSW, Australia
pp. 273-276

A 5.6 kb/s speech codec using a pulse codebook and improved Viterbi decoding (Abstract)

M. Takashima , Central Res. Lab., Hitachi Ltd., Tokyo, Japan
N. Ishikawa , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
H. Sekine , Central Res. Lab., Hitachi Ltd., Tokyo, Japan
Y. Asakawa , Central Res. Lab., Hitachi Ltd., Tokyo, Japan
pp. 277-280

A VR-CELP codec implementation for CDMA mobile communications (Abstract)

P. Blocher , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
D. Sereno , CSELT, Torino, Italy
L. Cellario , CSELT, Torino, Italy
M. Giani , Central Res. Lab., Hitachi Ltd., Tokyo, Japan
pp. 281-284

Reed-Solomon coding for CELP EDAC in land mobile radio (Abstract)

D.E. Ray , U.S. Dept. of Defense, USA
D.J. Rahikka , U.S. Dept. of Defense, USA
pp. 285-288

Analysis of phoneme-based features for language identification (Abstract)

K.M. Berkling , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
E. Barnard , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
T. Arai , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
pp. 289-292

A new speech enhancement technique with application to speaker identification (Abstract)

R.J. Mammone , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
M.A. Ramalho , Bellcore, Red Bank, NJ, USA
pp. 29-32

Language identification using phone-based acoustic likelihoods (Abstract)

J.L. Gauvain , LIMSI-CNRS, Orsay, France
L.F. Lamel , LIMSI-CNRS, Orsay, France
pp. 293-296

Automatic language identification using syllabic spectral features (Abstract)

Kung-Pu Li , ITT Aerosp. Commun. Div., San Diego, CA, USA
pp. 297-300

Automatic language identification using sub-word models (Abstract)

M.J. Carey , Ensigma Ltd., Chepstow, UK
R.C.F. Tucker , Ensigma Ltd., Chepstow, UK
E.S. Parris , Ensigma Ltd., Chepstow, UK
pp. 301-304

Automatic language identification of telephone speech messages using phoneme recognition and N-gram modeling (Abstract)

M.A. Zissman , Lincoln Lab., MIT, Lexington, MA, USA
E. Singer , Lincoln Lab., MIT, Lexington, MA, USA
pp. 305-308

Distance measures for text-independent speaker recognition based on MAR model (Abstract)

S. Furui , NTT Human Interface Labs., Tokyo, Japan
T. Matsui , NTT Human Interface Labs., Tokyo, Japan
C. Griffin , NTT Human Interface Labs., Tokyo, Japan
pp. 309-312

Discriminating semi-continuous HMM for speaker verification (Abstract)

M.A. Jack , Centre for Speech Technol. Res., Edinburgh, UK
M.E. Forsyth , Centre for Speech Technol. Res., Edinburgh, UK
pp. 313-316

A model distance measure for talker clustering and identification (Abstract)

H.F. Silverman , Centre for Speech Technol. Res., Edinburgh, UK
J.T. Foote , Dept. of Eng., Cambridge Univ., UK
pp. 317-320

Improved voice identification using a nearest-neighbor distance measure (Abstract)

L.G. Bahler , ITT Aerosp./Commun. Div, San Diego, CA, USA
J.E. Porter , ITT Aerosp./Commun. Div, San Diego, CA, USA
A.L. Higgins , ITT Aerosp./Commun. Div, San Diego, CA, USA
pp. 321-323

Speaker recognition based on minimum error discriminative training (Abstract)

Chi-Shi Liu , AT&T Bell Labs., Murray Hill, NJ, USA
Biing-Hwang Juang , AT&T Bell Labs., Murray Hill, NJ, USA
Chin-Hui Lee , AT&T Bell Labs., Murray Hill, NJ, USA
A.E. Rosenberg , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 325-328

Speaker recognition in tactical communications (Abstract)

R. Ricart , Booz, Allen & Hamilton Inc., McLean, VA, USA
J. Cupples , AT&T Bell Labs., Murray Hill, NJ, USA
L. Fenstermacher , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 329-332

Acoustic modeling for speech recognition based on spotting of phonetic units (Abstract)

L.T. Niles , Xerox Palo Alto Res. Center, CA, USA
pp. 33-36

Perceptual benchmarks for automatic language identification (Abstract)

N. Jain , AT&T Bell Labs., Murray Hill, NJ, USA
R.A. Cole , AT&T Bell Labs., Murray Hill, NJ, USA
Y.K. Muthusamy , Comput. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
pp. 333-336

Unanswerable queries in a spontaneous speech task (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. 341-344

JANUS 93: towards spontaneous speech translation (Abstract)

F.D. Buo , AT&T Bell Labs., Murray Hill, NJ, USA
N. Coccaro , AT&T Bell Labs., Murray Hill, NJ, USA
N. Aoki-Waibel , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Woszczyna , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 345-348

Correcting complex false starts in spontaneous speech (Abstract)

D. O'Shaughnessy , INRS Telecommun., Verdun, Que., Canada
pp. 349-352

Ergodic hidden Markov models and polygrams for language modeling (Abstract)

E.G. Schukat-Talamazzini , Erlangen-Nurnberg Univ., Germany
H. Niemann , Erlangen-Nurnberg Univ., Germany
T. Kuhn , Erlangen-Nurnberg Univ., Germany
pp. 357-360

A robust language model incorporating a substring parser and extended n-grams (Abstract)

J.H. Wright , Centre for Commun. Res., Bristol Univ., UK
H. Lloyd-Thomas , Erlangen-Nurnberg Univ., Germany
G.J.F. Jones , Erlangen-Nurnberg Univ., Germany
pp. 361-364

Learning complex output representations in connectionist parsing of spoken language (Abstract)

F.D. Buo , Karlsruhe Univ., Germany
A. Waibel , Erlangen-Nurnberg Univ., Germany
T.S. Polzin , Erlangen-Nurnberg Univ., Germany
pp. 365-368

Sentence spotting applied to partial sentences and unknown words (Abstract)

J. Kiyama , Real World Comput. Partnership, Tsukaba, Japan
R. Oka , Real World Comput. Partnership, Tsukaba, Japan
Y. Itoh , Real World Comput. Partnership, Tsukaba, Japan
pp. 369-372

IPA: improved phone modelling with recurrent neural networks (Abstract)

M. Hochberg , Dept. of Eng., Cambridge Univ., UK
T. Robinson , Dept. of Eng., Cambridge Univ., UK
S. Renals , Dept. of Eng., Cambridge Univ., UK
pp. 37-40

Optimizing recognition and rejection performance in wordspotting systems (Abstract)

J.-M. Boite , L&H Speech Products, Ieper, Belgium
H. Bourlard , L&H Speech Products, Ieper, Belgium
B. D'hoore , L&H Speech Products, Ieper, Belgium
pp. 373-376

A fast lattice-based approach to vocabulary independent wordspotting (Abstract)

S.J. Young , Dept. of Eng., Cambridge Univ., UK
D.A. James , Dept. of Eng., Cambridge Univ., UK
pp. 377-380

Spotting events in continuous speech (Abstract)

P. Jeanrenaud , BNN Syst. & Technol., Cambridge, MA, USA
M. Meteer , BNN Syst. & Technol., Cambridge, MA, USA
J.R. Rohlicek , BNN Syst. & Technol., Cambridge, MA, USA
M. Siu , BNN Syst. & Technol., Cambridge, MA, USA
H. Gish , BNN Syst. & Technol., Cambridge, MA, USA
pp. 381-384

Approaches to topic identification on the switchboard corpus (Abstract)

K. Ng , BNN Syst. & Technol., Cambridge, MA, USA
H. Gish , BNN Syst. & Technol., Cambridge, MA, USA
P. Jeanrenaud , BNN Syst. & Technol., Cambridge, MA, USA
J.R. Rohlicek , BNN Syst. & Technol., Cambridge, MA, USA
J. McDonough , BNN Syst. & Technol., Cambridge, MA, USA
pp. 385-388

Wordspotter training using figure-of-merit back propagation (Abstract)

C.R. Jankowski , Lincoln Lab., MIT, Lexington, MA, USA
E.I. Chang , Lincoln Lab., MIT, Lexington, MA, USA
R.P. Lippmann , Lincoln Lab., MIT, Lexington, MA, USA
pp. 389-392

The performance prediction method on sentence recognition system using a finite state automaton (Abstract)

T. Otsuki , Fac. of Eng., Yamagata Univ., Yonezawa, Japan
A. Ito , Lincoln Lab., MIT, Lexington, MA, USA
S. Makino , Lincoln Lab., MIT, Lexington, MA, USA
T. Otomo , BNN Syst. & Technol., Cambridge, MA, USA
pp. 397-400

New ways to use LVQ-codebooks together with hidden Markov models (Abstract)

K. Torkkola , Inst. Dalle Molle d'Intelligence Artificielle Perceptive, Martigny, Switzerland
pp. 401-404

Parallel distributed binary mapping models for speech recognition (Abstract)

Jianmin Li , Dept. of Comput. Sci., Tsinghua Univ., Beijing, China
Ditang Fang , Dept. of Comput. Sci., Tsinghua Univ., Beijing, China
pp. 405-408

Continuous speech recognition in noise using spectral subtraction and HMM adaptation (Abstract)

S.J. Young , Dept. of Eng., Cambridge Univ., UK
J.A.N. Flores , Dept. of Eng., Cambridge Univ., UK
pp. 409-412

Phoneme recognition in continuous speech using large inhomogeneous hidden Markov models (Abstract)

R.N.V. Sitaram , Dept. of Electr. Commun. Eng., Indian Inst. of Sci., Bangalore, India
T.V. Sreenivas , Dept. of Electr. Commun. Eng., Indian Inst. of Sci., Bangalore, India
pp. 41-44

Duration and spectral based stress token generation for HMM speech recognition under stress (Abstract)

S.E. Bou-Ghazale , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
J.H.L. Hansen , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
pp. 413-416

Probabilistic optimum filtering for robust speech recognition (Abstract)

L. Neumeyer , Speech Res. & Technol. Program, SRI Int., Menlo Park, CA, USA
M. Weintraub , Speech Res. & Technol. Program, SRI Int., Menlo Park, CA, USA
pp. 417-420

Integrating RASTA-PLP into speech recognition (Abstract)

J. Koehler , California Univ., Berkeley, CA, USA
H.G. Hirsch , BNN Syst. & Technol., Cambridge, MA, USA
N. Morgan , California Univ., Berkeley, CA, USA
G. Tong , BNN Syst. & Technol., Cambridge, MA, USA
H. Hermansky , California Univ., Berkeley, CA, USA
pp. 421-424

Degraded word recognition based on segmental signal-to-noise ratio weighting (Abstract)

Y. Matsunoo , Fac. of Technol., Tokyo Univ. of Agric. & Technol., Japan
H. Kobatake , Fac. of Technol., Tokyo Univ. of Agric. & Technol., Japan
pp. 425-428

On the importance of the microphone position for speech recognition in the car (Abstract)

J. Smolders , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
T. Claes , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
D. Van Compernolle , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
G. Sablon , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
pp. 429-432

Adaptation to new microphones using tied-mixture normalization (Abstract)

A. Anastasakos , Northeastern Univ., Boston, MA, USA
R. Schwartz , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
J. Makhoul , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
F. Kubala , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
pp. 433-436

Noise independent speech recognition for a variety of noise types (Abstract)

W.C. Treurniet , Communication Res. Centre, Ottawa, Ont., Canada
Y. Gong , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
pp. 437-440

Root adaptive homomorphic deconvolution schemes for speech recognition in noise (Abstract)

P. Lockwood , Speech Process. Group, Matra Commun., Bois d'Arcy, France
P. Alexandre , Speech Process. Group, Matra Commun., Bois d'Arcy, France
pp. 441-444

Signal bias removal for robust telephone based speech recognition in adverse environments (Abstract)

Biing-Hwang Juang , AT&T Bell Labs., Murray Hill, NJ, USA
M.G. Rahim , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 445-448

Adaptive noise immunity learning for word spotting (Abstract)

H. Kanazawa , Res. & Dev. Center, Toshiba Corp., Kawasaki, Japan
Y. Takebayashi , Res. & Dev. Center, Toshiba Corp., Kawasaki, Japan
pp. 449-452

Phonetic classification and recognition using HMM representation of overlapping articulatory features for all classes of English sounds (Abstract)

D. Sun , Res. & Dev. Center, Toshiba Corp., Kawasaki, Japan
L. Deng , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
pp. 45-48

Time-scale modification of speech based on a nonlinear oscillator model (Abstract)

G. Kubin , Inf. Principles Res. Lab., AT&T Bell Labs., Murray Hill, NJ, USA
W.B. Kleijn , Inf. Principles Res. Lab., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 453-456

A robust sequential parameter estimation for time-varying speech signal analysis (Abstract)

Souguil Ann , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
W.B. Kleijn , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
W.B. Kleijn , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
pp. 457-460

Speech spectrum transformation by speaker interpolation (Abstract)

N. Iwahashi , Sony Corp. Res. Labs, Tokyo, Japan
Y. Sagisaka , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
pp. 461-464

A novel approach for classifying continuous speech into visible mouth-shape related classes (Abstract)

S.-H. Luo , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
R.W. King , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
pp. 465-468

Voice conversion based on piecewise linear conversion rules of formant frequency and spectrum tilt (Abstract)

M. Abe , NTT Human Interface Labs., Kanagawa, Japan
H. Mizuno , NTT Human Interface Labs., Kanagawa, Japan
pp. 469-472

Voiced-speech analysis based on the residual interfering signal canceler (RISC) algorithm (Abstract)

C.S. Ramalingam , Dept. of Electr. Eng., Rhode Island Univ., Kingston, RI, USA
R. Kumaresan , Dept. of Electr. Eng., Rhode Island Univ., Kingston, RI, USA
pp. 473-476

Determination of human vocal-tract dynamic geometry from formant trajectories using spatial and temporal Fourier analysis (Abstract)

F. Itakura , Sch. of Eng., Nagoya Univ., Japan
H. Yehia , Sch. of Eng., Nagoya Univ., Japan
pp. 477-480

Analysis of spectral interpolation with weighting dependent on frame energy (Abstract)

J.S. Erkelens , Dept. of Appl. Phys., Delft Univ. of Technol., Netherlands
P.M.T. Broersen , Dept. of Appl. Phys., Delft Univ. of Technol., Netherlands
pp. 481-484

Filter bank design based on discriminative feature extraction (Abstract)

A. Biem , ATR Human Inf. Process. Labs., Japan
S. Katagiri , ATR Human Inf. Process. Labs., Japan
pp. 485-488

Vector quantization with hyper-columnar clusters (Abstract)

M. Kohata , Fac. of Eng., Tohoku Univ., Sendai, Japan
T. Takagi , Fac. of Eng., Tohoku Univ., Sendai, Japan
pp. 489-492

Segmental phoneme recognition using piecewise linear regression (Abstract)

S. Krishnan , Comput. Syst. & Commun. Group, Tata Inst. of Fundamental Res., Bombay, India
P.V. Rao , Comput. Syst. & Commun. Group, Tata Inst. of Fundamental Res., Bombay, India
pp. 49-52

A novel split residual vector quantization scheme for low bit rate speech coding (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. 493-496

Efficient vector quantisation of LPC parameters for noisy channels (Abstract)

A. Perkis , Dept. of Telecommun., Norwegian Inst. of Technol., Trondheim, Norway
H. Skinnemoen , Dept. of Telecommun., Norwegian Inst. of Technol., Trondheim, Norway
pp. 497-500

Efficient interblock noiseless coding of speech LPC parameters (Abstract)

S. Bruhn , Inst. fur Telecommun., Tech. Univ. Berlin, Germany
pp. 501-504

Variable dimension vector quantization of linear predictive coefficients of speech (Abstract)

T. Lookabaugh , Dept. of Telecommun., Norwegian Inst. of Technol., Trondheim, Norway
P.A. Chou , Xerox Palo Alto Res. Center, CA, USA
pp. 505-508

Spectral quantization of cepstral coefficients (Abstract)

R. Hagen , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
pp. 509-512

Vector quantization-lattice vector quantization of speech LPC coefficients (Abstract)

Jianping 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. 513-516

Segmental quantization of speech spectral information (Abstract)

T. Svendsen , Dept. of Telecommun., Norwegian Inst. of Technol., Trondheim, Norway
pp. 517-520

Low-complexity encoding of speech LSF parameters using constrained-storage TSVQ (Abstract)

D. Chemla , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
Wai-Yip Chan , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
pp. 521-524

Single stage spectral quantization at 20 bits (Abstract)

P. Hedelin , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
pp. 525-528

High-order allpole modelling of the spectral envelope (Abstract)

T.F. Quatieri , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
R.J. McAuley , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
T.G. Champion , Rome Lab., Hanscom AFB, MA, USA
pp. 529-532

A new method for segmenting continuous speech (Abstract)

B.I. Pawate , Tsukuba Res. & Dev. Center, Texas Instrum., Ibaraki, Japan
E. Dowling , Dept. of Electr. Eng., McGill Univ., Montreal, Que., Canada
pp. 53-56

Robust methods for using context-dependent features and models in a continuous speech recognizer (Abstract)

P.S. Gopalakrishnan , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
L.R. Bahl , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
D. Nahamoo , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M.A. Picheny , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P.V. de Souza , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 533-536

A comparison of phoneme decision tree (PDT) and context adaptive phone (CAP) based approaches to vocabulary-independent speech recognition (Abstract)

M.J. Russell , Speech Res. Unit, DRA Malvern, UK
S.R. Browning , Speech Res. Unit, DRA Malvern, UK
S.N. Downey , Speech Res. Unit, DRA Malvern, UK
P. Nowell , Speech Res. Unit, DRA Malvern, UK
R.K. Moore , Speech Res. Unit, DRA Malvern, UK
pp. 541-544

Towards large vocabulary Mandarin Chinese speech recognition (Abstract)

S. Narayan , Adv. Technol. Group, Apple Comput. Inc., Cupertino, CA, USA
Yen-Lu Chow , Adv. Technol. Group, Apple Comput. Inc., Cupertino, CA, USA
Kai-Fu Lee , Adv. Technol. Group, Apple Comput. Inc., Cupertino, CA, USA
Baosheng Yuan , Adv. Technol. Group, Apple Comput. Inc., Cupertino, CA, USA
Hsiao-Wuen Hon , Adv. Technol. Group, Apple Comput. Inc., Cupertino, CA, USA
pp. 545-548

Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-II (Abstract)

M. Hwamg , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Rosenfeld , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
L. Chase , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Weide , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
X. Huang , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Mosur , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
E. Theyer , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
F. Alleva , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 549-552

New graph search techniques for speech recognition (Abstract)

D. O'Shaughnessy , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
P. Kenny , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
Z. Li , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
P. Labute , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 553-556

The LIMSI continuous speech dictation system: evaluation on the ARPA Wall Street Journal task (Abstract)

J.L. Gauvain , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
M. Adda-Decker , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
G. Adda , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
L.F. Lamel , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 557-560

Comparative experiments on large vocabulary speech recognition (Abstract)

L. Nguyen , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
J. Makhoul , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
E. Zavaliagkos , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
R. Schwartz , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
F. Kubala , IBM Syst. & Technol., Cambridge, MA, USA
A. Anastasakos , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 561-564

Development of a text-to-speech system for Japanese based on waveform splicing (Abstract)

N. Higuchi , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
S. Yamamoto , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
H. Kawa , KDD Kamifukuoka R&D Labs., Saitama, Japan
T. Simizu , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 569-572

Stochastic trajectory modeling for speech recognition (Abstract)

J.-P. Haton , CRIN/CNRS, Inst. Nat. de Recherche en Inf. et Autom., Vandoeuvre, France
Yifan Gong , CRIN/CNRS, Inst. Nat. de Recherche en Inf. et Autom., Vandoeuvre, France
pp. 57-60

New algorithm for spectral smoothing and envelope modification for LP-PSOLA synthesis (Abstract)

J.M. Pardo , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
M.H. Savoji , CRIN/CNRS, Inst. Nat. de Recherche en Inf. et Autom., Vandoeuvre, France
F.M. Gimenez de los Galanes , Dept. Ingenieria Electron., Univ. Politecnica de Madrid, Spain
pp. 573-576

A new waveform speech synthesis approach based on the COC speech spectrum (Abstract)

K. Itoh , NTT Human Interface Labs., Kanagawa, Japan
T. Hirokawa , NTT Human Interface Labs., Kanagawa, Japan
S. Nakajima , NTT Human Interface Labs., Kanagawa, Japan
pp. 577-580

Hybrid time- and frequency-domain speech synthesis with extended glottal source generation (Abstract)

G. Fries , Forschungs und Technol., Deutsche Bundespost Telekom, Darmstadt, Germany
pp. 581-584

Articulatory speech synthesis based on fractional delay waveguide filters (Abstract)

T. Kuisma , Acoust. Lab., Helsinki Univ. of Technol., Espoo, Finland
V. Valimaki , Acoust. Lab., Helsinki Univ. of Technol., Espoo, Finland
M. Karjalainen , Acoust. Lab., Helsinki Univ. of Technol., Espoo, Finland
pp. 585-588

Data-driven joint f/sub 0/ and duration modeling in text to speech conversion for Spanish (Abstract)

E. Lopez-Gonzalo , ETSI Telecomunicacion, Univ. Politecnica de Madrid, Spain
L.A. Hernandez-Gomez , ETSI Telecomunicacion, Univ. Politecnica de Madrid, Spain
pp. 589-592

Automatic generation of prosodic rules for speech synthesis (Abstract)

Y. Yamashita , Inst. of Sci. & Ind. Res., Osaka Univ., Japan
R. Miroguchi , Inst. of Sci. & Ind. Res., Osaka Univ., Japan
pp. 593-596

A MRF-based parallel processing algorithm for speech recognition using linear predictive HMM (Abstract)

H. Noda , Commun. Res. Lab., Japan Ministry of Posts & Telecommun., Kobe, Japan
M.N. Shirazi , Inst. of Sci. & Ind. Res., Osaka Univ., Japan
pp. 597-600

Speech modelling using cepstral-time feature matrices and hidden Markov models (Abstract)

S.V. Vaseghi , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
B.P. Milner , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
pp. 601-604

HMM with global path constraint in Viterbi decoding for isolated word recognition (Abstract)

Jeung-Yoon Choi , Dept. of Electron. Eng., Yonsei Univ., Seoul, South Korea
Weon-Goo Kim , Dept. of Electron. Eng., Yonsei Univ., Seoul, South Korea
Jeung-Yoon Choi , Dept. of Electron. Eng., Yonsei Univ., Seoul, South Korea
pp. 605-608

Pseudo-segment based speech recognition using neural recurrent whole-word recognizers (Abstract)

D. Van Compernolle , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
K. Demuynck , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
J. Duchateau , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
P. Le Cerf , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
pp. 609-612

Using multiple vector quantization and semicontinuous hidden Markov models for speech recognition (Abstract)

A.J. Rubio , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
J.C. Segura , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
A.M. Peinado , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
M.C. Benitez , Dept. de Electron. y Tecnologia de Computadores, Granada Univ., Spain
pp. 61-64

Using Gaussian mixture modeling in speech recognition (Abstract)

M. Alder , Centre for Intelligent Inf. Process. Syst., Western Australia Univ., Nedlands, WA, Australia
R. Togneri , Centre for Intelligent Inf. Process. Syst., Western Australia Univ., Nedlands, WA, Australia
Y. Zhang , Centre for Intelligent Inf. Process. Syst., Western Australia Univ., Nedlands, WA, Australia
pp. 613-616

Task independent and dependent training: performance comparison of HMM and hybrid HMM/MLP approaches (Abstract)

J.-M. Boite , L&H Speech Products, Ieper, Belgium
B. D'hoore , L&H Speech Products, Ieper, Belgium
H. Bourlard , L&H Speech Products, Ieper, Belgium
J. Vantieghem , L&H Speech Products, Ieper, Belgium
S. Accaino , L&H Speech Products, Ieper, Belgium
pp. 617-620

The influence of speech coding algorithms on automatic speech recognition (Abstract)

J. Zinke , TELENORMA, Bosch Telecom, Frankfurt, Germany
S. Euler , TELENORMA, Bosch Telecom, Frankfurt, Germany
pp. 621-624

Discriminative training of high performance speech recognizer using N best candidates (Abstract)

F.K. Soong , TELENORMA, Bosch Telecom, Frankfurt, Germany
Jung-Kuei Chen , Telecommun. Lab., Minist. of Commun., Chung-Li, Taiwan
pp. 625-628

Model topology selection for isolated word recognition (Abstract)

P. Laface , Dipartimento di Autom. e Inf., Politecnico di Torino, Italy
L. Fissore , TELENORMA, Bosch Telecom, Frankfurt, Germany
pp. 629-632

Which model for future speech recognition systems: hidden Markov models or finite-state automata? (Abstract)

K. Perot , L&H Speech Products, Ieper, Belgium
J.F. Mari , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
B. Mathieu , L&H Speech Products, Ieper, Belgium
K. Smaili , L&H Speech Products, Ieper, Belgium
J. Di Martino , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
pp. 633-635

On the fuzzy vector quantization based hidden Markov model (Abstract)

E. Tsuboka , Central Res. Labs., Matsushita Electr. Ind. Co. Ltd., Kyoto, Japan
J. Nakahashi , Central Res. Labs., Matsushita Electr. Ind. Co. Ltd., Kyoto, Japan
pp. 637-640

Word accent patterns modelling by concatenation of mora hidden Markov models (Abstract)

T. Yoshimura , Electrotech. Lab., Ibaraki, Japan
S. Hayamizu , Electrotech. Lab., Ibaraki, Japan
K. Tanalia , Electrotech. Lab., Ibaraki, Japan
pp. 69-72

Phonemic segmentation of fluent speech (Abstract)

D.B. Grayden , Melbourne Univ., Parkville, Vic., Australia
M.S. Scordilis , Melbourne Univ., Parkville, Vic., Australia
pp. 73-76

Knowledge based approach to consonant recognition (Abstract)

A. Samouelian , Dept. of Electr. & Comput. Eng., Wollongong Univ., NSW, Australia
pp. 77-80

Macrophone: an American English telephone speech corpus for the Polyphone project (Abstract)

K. Taussig , Speech Res. & Technol Program, SRI Int., Menlo Park, CA, USA
J. Godfrey , Speech Res. & Technol Program, SRI Int., Menlo Park, CA, USA
J. Bernstein , Speech Res. & Technol Program, SRI Int., Menlo Park, CA, USA
pp. 81-84

Constructing telephone acoustic models from a high-quality speech corpus (Abstract)

M. Weintraub , Speech Res. & Technol. Program, SRI Int., Menlo Park, CA, USA
L. Neumeyer , Speech Res. & Technol. Program, SRI Int., Menlo Park, CA, USA
pp. 85-88

The voice across Japan database-the Japanese language contribution to Polyphone (Abstract)

N. Arai , Comput. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
T. Staples , Comput. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
J. Picone , Comput. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
pp. 89-92

Towards automatic collection of the US census (Abstract)

D.G. Novick , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
D. Burnett , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
M. Fant , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
B. Hansen , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
R.A. Cole , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
S. Sutton , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
pp. 93-96

The Australian National Database of Spoken Language (Abstract)

J.P. Vonwiller , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
J.M. Harrington , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
P.J. Dermody , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
J.B. Millar , Comput. Sci. Lab., Australian Nat. Univ., Canberra, ACT, Australia
pp. 97-I100
95 ms
(Ver 3.1 (10032016))