The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (1995)
Detroit, MI, USA
May 9, 1995 to May 12, 1995
ISBN: 0-7803-2431-5
TABLE OF CONTENTS

4 kbps improved pitch prediction CELP speech coding with 20 ms frame (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
pp. 1-4

A low-complexity toll-quality variable bit rate coder for CDMA cellular systems (Abstract)

M. Recchione , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
P. Kroon , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 5-8

Toll-quality 16 kb/s CELP speech coding with very low complexity (Abstract)

Juin-Hwey Chen , Speech Coding Res. Dept., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 9-12

CELP coding using trellis-coded vector quantization of the excitation (Abstract)

N. Moreau , Telecom Paris, France
A. Popescu , Telecom Paris, France
pp. 13-16

Interpolating the history improved excitation coding for high quality CELP coding (Abstract)

P. Hedelin , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
T. Eriksson , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
pp. 17-20

Fast stochastic codebook search through the use of odd-symmetric crosscorrelation basis vectors (Abstract)

Cheung-Fat Chan , Dept. of Electron. Eng., City Univ. of Hong Kong, Kowloon, Hong Kong
pp. 21-24

Improvements of background sound coding in linear predictive speech coders (Abstract)

F. Jansson , Ericsson Radio Syst. AB, Stockholm, Sweden
H. Nilson , Ericsson Radio Syst. AB, Stockholm, Sweden
T. Wigren , Ericsson Radio Syst. AB, Stockholm, Sweden
S. Harrysson , Ericsson Radio Syst. AB, Stockholm, Sweden
A. Bergstrom , Ericsson Radio Syst. AB, Stockholm, Sweden
pp. 25-28

Improved CS-CELP speech coding in a noisy environment using a trained sparse conjugate codebook (Abstract)

A. Kataoka , NTT Human Interface Labs., Tokyo, Japan
T. Moriya , Ericsson Radio Syst. AB, Stockholm, Sweden
S. Hosaka , NTT Human Interface Labs., Tokyo, Japan
S. Hayashi , Ericsson Radio Syst. AB, Stockholm, Sweden
J. Ikedo , Ericsson Radio Syst. AB, Stockholm, Sweden
pp. 29-32

CELP coding based on mel-cepstral analysis (Abstract)

T. Kobayashi , Ericsson Radio Syst. AB, Stockholm, Sweden
K. Tokuda , NTT Human Interface Labs., Tokyo, Japan
S. Imai , Ericsson Radio Syst. AB, Stockholm, Sweden
K. Koishida , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
pp. 33-36

An embedded scheme for regular pulse excited (RPE) linear predictive coding (Abstract)

Shude Zhang , Dept. of Electron. & Electr. Eng., Leeds Univ., UK
G. Lockhart , Dept. of Electron. & Electr. Eng., Leeds Univ., UK
pp. 37-40

Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task (Abstract)

S. Roukos , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Padmanabhan , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
S. Balakrishnan-Aiyer , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Franz , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
J.R. Bellgarda , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
L.R. Bahl , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P.S. Gopalakrishnan , 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
M. Novak , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 41-44

New developments in the Lincoln stack-decoder based large-vocabulary CSR system (Abstract)

D.B. Paul , Lincoln Lab., MIT, Lexington, MA, USA
pp. 45-48

Large vocabulary continuous speech recognition using word graphs (Abstract)

X. Aubert , Philips Res. Lab., Aachen, Germany
H. Ney , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 49-52

Reducing word error rate on conversational speech from the Switchboard corpus (Abstract)

M. Siu , BBN Syst. & Technol. Corp., Cambridge, MA, USA
J. McDonough , BBN Syst. & Technol. Corp., Cambridge, MA, USA
E. Eide , BBN Syst. & Technol. Corp., Cambridge, MA, USA
H. Gish , BBN Syst. & Technol. Corp., Cambridge, MA, USA
P. Jeanrenaud , BBN Syst. & Technol. Corp., Cambridge, MA, USA
U. Chaudhari , BBN Syst. & Technol. Corp., Cambridge, MA, USA
K. Ng , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 53-56

Golden Mandarin (III)-a user-adaptive prosodic-segment-based Mandarin dictation machine for Chinese language with very large vocabulary (Abstract)

Keh-Jiann Chen , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Lee-Feng Chien , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Hung-Yun Hsieh , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Shi-Wei Lin , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Ren-Yuan Lyu , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Bo-Ren Bai , BBN Syst. & Technol. Corp., Cambridge, MA, USA
Yen-Ju Yang , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Rung-Chiuan Yang , BBN Syst. & Technol. Corp., Cambridge, MA, USA
Shiao-Hong Hwang , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Jia-Chi Weng , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 57-60

Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary but limited training data (Abstract)

Jia-Lin Shen , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Yen-Ju Yang , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Lin-Shan Lee , BBN Syst. & Technol. Corp., Cambridge, MA, USA
Hsin-Min Wang , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Chiu-Yu Tseng , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
pp. 61-64

Developments in continuous speech dictation using the ARPA WSJ task (Abstract)

L. Lamel , 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
J.L. Gauvain , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 65-68

Recent improvements to the ABBOT large vocabulary CSR system (Abstract)

A.J. Robinson , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
M.M. Hochberg , Dept. of Eng., Cambridge Univ., UK
S.J. Renals , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
G.D. Cook , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
pp. 69-72

The 1994 HTK large vocabulary speech recognition system (Abstract)

C.J. Leggetter , Dept. of Eng., Cambridge Univ., UK
V. Valtchev , Dept. of Eng., Cambridge Univ., UK
S.J. Young , Dept. of Eng., Cambridge Univ., UK
P.C. Woodland , Dept. of Eng., Cambridge Univ., UK
J.J. Odell , Dept. of Eng., Cambridge Univ., UK
pp. 73-76

Tangerine: a large vocabulary Mandarin dictation system (Abstract)

Yuqing Gao , Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
Zhiwei Lin , Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
S. Yogananthan , Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
G. Loudon , Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
Hsiao-Wuen Hon , Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
Baosheng Yuan , Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore
pp. 77-80

WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition (Abstract)

T. Robinson , Dept. of Eng., Cambridge Univ., UK
D. Pye , Dept. of Eng., Cambridge Univ., UK
J. Fransen , Dept. of Eng., Cambridge Univ., UK
S. Renals , Dept. of Eng., Cambridge Univ., UK
J. Foote , Dept. of Eng., Cambridge Univ., UK
pp. 81-84

Voice across Hispanic America: a telephone speech corpus of American Spanish (Abstract)

J. Godfrey , Dept. of Eng., Cambridge Univ., UK
E. Holliman , Syst. & Inf. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
B. Wheatley , Syst. & Inf. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
Y. Muthusamy , Syst. & Inf. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
J. Picone , Dept. of Eng., Cambridge Univ., UK
pp. 85-88

Implementation of the POW (phonetically optimized words) algorithm for speech database (Abstract)

Youngjik Lee , Autom. Interpretation Section, Electron. & Telecommun. Res. Inst., Seoul, South Korea
Yeonja Lim , Autom. Interpretation Section, Electron. & Telecommun. Res. Inst., Seoul, South Korea
pp. 89-92

Microsoft Windows highly intelligent speech recognizer: Whisper (Abstract)

Xuedong Huang , Microsoft Corp., Redmond, WA, USA
M. Mahajan , Microsoft Corp., Redmond, WA, USA
Mei-Yuh Hwang , Microsoft Corp., Redmond, WA, USA
F. Alleva , Microsoft Corp., Redmond, WA, USA
A. Acero , Microsoft Corp., Redmond, WA, USA
Li Jiang , Microsoft Corp., Redmond, WA, USA
pp. 93-96

Concept-based speech translation (Abstract)

L. Mayfield , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Gavalda , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
A. Waibel , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
W. Ward , Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 97-100

PhoneBook: a phonetically-rich isolated-word telephone-speech database (Abstract)

H.C. Leung , NYNEX Corp., White Plains, NY, USA
S.H. Wong , NYNEX Corp., White Plains, NY, USA
J.R. Spitz , NYNEX Corp., White Plains, NY, USA
J.F. Pitrelli , NYNEX Corp., White Plains, NY, USA
C. Fong , NYNEX Corp., White Plains, NY, USA
pp. 101-104

CTIMIT: a speech corpus for the cellular environment with applications to automatic speech recognition (Abstract)

K.L. Brown , Signal Process. Center of Technol., Lockheed Sanders Avionics, Nashua, NH, USA
E.B. George , Signal Process. Center of Technol., Lockheed Sanders Avionics, Nashua, NH, USA
pp. 105-108

Toward movement-invariant automatic lip-reading and speech recognition (Abstract)

P. Duchnowski , Interactive Syst. Lab., Karlsruhe Univ., Germany
M. Hunke , Interactive Syst. Lab., Karlsruhe Univ., Germany
A. Waibel , Interactive Syst. Lab., Karlsruhe Univ., Germany
D. Busching , Interactive Syst. Lab., Karlsruhe Univ., Germany
U. Meier , Interactive Syst. Lab., Karlsruhe Univ., Germany
pp. 109-112

Some results with a trainable speech translation and understanding system (Abstract)

E. Vidal , Dept. de Sistemas Inf. y Comput., Univ. Politecnica de Valencia, Spain
V.M. Jimenez , Dept. de Sistemas Inf. y Comput., Univ. Politecnica de Valencia, Spain
A. Castellanos , Dept. de Sistemas Inf. y Comput., Univ. Politecnica de Valencia, Spain
pp. 113-116

A continuous speech recognition system using finite state network and Viterbi beam search for the automatic interpretation (Abstract)

Young-Mok Ahn , Electron. & Telecommun. Res. Inst., Seoul, South Korea
Kyu-Woong Hwang , Electron. & Telecommun. Res. Inst., Seoul, South Korea
Joon-Hyung Ryoo , Electron. & Telecommun. Res. Inst., Seoul, South Korea
Nam-Yong Han , Electron. & Telecommun. Res. Inst., Seoul, South Korea
Hoi-Rin Kim , Electron. & Telecommun. Res. Inst., Seoul, South Korea
pp. 117-120

Robust speech recognition based on stochastic matching (Abstract)

Chin-Hui Lee , AT&T Bell Labs., Murray Hill, NJ, USA
A. Sankar , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 121-124

A maximum likelihood procedure for a universal adaptation method based on HMM composition (Abstract)

Y. Minami , NTT Human Interface Labs., Tokyo, Japan
S. Furui , NTT Human Interface Labs., Tokyo, Japan
pp. 129-132

A fast and flexible implementation of parallel model combination (Abstract)

M.J.F. Gales , Dept. of Eng., Cambridge Univ., UK
S.J. Young , Dept. of Eng., Cambridge Univ., UK
pp. 133-136

Multivariate-Gaussian-based cepstral normalization for robust speech recognition (Abstract)

E. Gouvea , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
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
B. Raj , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 137-140

Robust speech recognition in noise using adaptation and mapping techniques (Abstract)

M. Weintraub , Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA
L. Neumeyer , Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA
pp. 141-144

Noisy speech recognition using robust inversion of hidden Markov models (Abstract)

Seokyong Moon , Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
Jenq-Neng Hwang , Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
pp. 145-148

Rapid environment adaptation for robust speech recognition (Abstract)

K. Takagi , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
T. Watanabe , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
H. Hattori , C&C Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
pp. 149-152

Noise estimation techniques for robust speech recognition (Abstract)

C. Ehrlicher , Inst. of Commun. Syst. & Data Process., Tech. Hochschule Aachen, Germany
H.G. Hirsch , Inst. of Commun. Syst. & Data Process., Tech. Hochschule Aachen, Germany
pp. 153-156

Pole-filtered cepstral mean subtraction (Abstract)

D. Naik , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
pp. 157-160

Language model adaptation via minimum discrimination information (Abstract)

S. Roukos , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M.D. Monkowski , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P.S. Rao , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 161-164

Clustering word category based on binomial posteriori co-occurrence distribution (Abstract)

T. Kawabata , NTT Basic Res. Labs., Kanagawa, Japan
M. Tamoto , NTT Basic Res. Labs., Kanagawa, Japan
pp. 165-168

An integrated grammar/bigram language model using path scores (Abstract)

J.H. Wright , Ensigma Ltd., Chepstow, UK
G.J.F. Jones , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
H. Lloyd-Thomas , Ensigma Ltd., Chepstow, UK
pp. 173-176

Discourse structure for multi-speaker spontaneous spoken dialogs: incorporating heuristics into stochastic RTNs (Abstract)

S.R. Young , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 177-180

Improved backing-off for M-gram language modeling (Abstract)

H. Ney , Ensigma Ltd., Chepstow, UK
R. Kneser , Philips GmbH Forschungslab., Aachen, Germany
pp. 181-184

QWI: a method for improved smoothing in language modelling (Abstract)

E. Vidal , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
I. Torres , Dept. de Electr. y Electron., Pais Vasco Univ., Bilbao, Spain
G. Bordel , Dept. de Electr. y Electron., Pais Vasco Univ., Bilbao, Spain
pp. 185-188

Using a stochastic context-free grammar as a language model for speech recognition (Abstract)

D. Jurafsky , Int. Comput. Sci. Inst., Berkeley, CA, USA
G. Tajchaman , Int. Comput. Sci. Inst., Berkeley, CA, USA
J. Segal , Int. Comput. Sci. Inst., Berkeley, CA, USA
C. Wooters , Int. Comput. Sci. Inst., Berkeley, CA, USA
A. Stolcke , Int. Comput. Sci. Inst., Berkeley, CA, USA
E. Fosler , Int. Comput. Sci. Inst., Berkeley, CA, USA
N. Morgan , Int. Comput. Sci. Inst., Berkeley, CA, USA
pp. 189-192

Improved language modelling by unsupervised acquisition of structure (Abstract)

K. Ries , Karlsruhe Univ., Germany
K. Ries , Karlsruhe Univ., Germany
Ye-Yi Wang , Int. Comput. Sci. Inst., Berkeley, CA, USA
pp. 193-196

Understanding referring expressions in a person-machine spoken dialogue (Abstract)

R. De Mori , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
G. Dudek , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
C. Pateras , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
pp. 197-200

Analysis of acoustic-phonetic variations in fluent speech using TIMIT (Abstract)

Li Deng , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
D.X. Sun , Dept. of Appl. Math. & Stat., State Univ. of New York, Stony Brook, NY, USA
pp. 201-204

Analysing weaknesses of language models for speech recognition (Abstract)

J.P. Ueberla , Forum Technol. DRA Malvern, UK
pp. 205-208

A hidden Markov model with optimized inter-frame dependence (Abstract)

J. Ming , Sch. of Electr. Eng. & Comput. Sci., Queen's Univ., Belfast, UK
A.D. Irvine , Sch. of Electr. Eng. & Comput. Sci., Queen's Univ., Belfast, UK
P. O'Boyle , Sch. of Electr. Eng. & Comput. Sci., Queen's Univ., Belfast, UK
F.J. Smith , Sch. of Electr. Eng. & Comput. Sci., Queen's Univ., Belfast, UK
pp. 209-212

On the use of scalar quantization for fast HMM computation (Abstract)

S. Sayayama , NTT Human Interface Labs., Kanagawa, Japan
S. Takahashi , NTT Human Interface Labs., Kanagawa, Japan
pp. 213-216

Large-vocabulary speech recognition in specialized domains (Abstract)

T. Bruce , Dragon Systems Inc., Newton, MA, USA
C. Moore , Dragon Systems Inc., Newton, MA, USA
A. Weader , Dragon Systems Inc., Newton, MA, USA
P. Bamberg , Dragon Systems Inc., Newton, MA, USA
J. Yamron , Dragon Systems Inc., Newton, MA, USA
S. Bridle , Dragon Systems Inc., Newton, MA, USA
B. Baker , Dragon Systems Inc., Newton, MA, USA
H. Chevalier , Dragon Systems Inc., Newton, MA, USA
C. Kunz , Dragon Systems Inc., Newton, MA, USA
C. Roven , Dragon Systems Inc., Newton, MA, USA
C. Ingold , Dragon Systems Inc., Newton, MA, USA
pp. 217-220

Understanding and improving speech recognition performance through the use of diagnostic tools (Abstract)

P. Jeanrenaud , BBN Syst. & Technol. Corp., Cambridge, MA, USA
A. Mielke , BBN Syst. & Technol. Corp., Cambridge, MA, USA
E. Eide , BBN Syst. & Technol. Corp., Cambridge, MA, USA
H. Gish , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 221-224

Phrase bigrams for continuous speech recognition (Abstract)

E.P. Giachin , CSELT, Torino, Italy
pp. 225-228

Using explicit segmentation to improve HMM phone recognition (Abstract)

M.P. Harper , Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
L.H. Jamieson , Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
C.D. Mitchell , Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
pp. 229-232

Non-deterministic stochastic language models for speech recognition (Abstract)

E. Bocchieri , Dept. of Speech Res., AT&T Bell Labs., Murray Hill, NJ, USA
G. Riccardi , Dept. of Speech Res., AT&T Bell Labs., Murray Hill, NJ, USA
R. Pieraccini , Dept. of Speech Res., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 237-240

Improving 16 kb/s G.728 LD-CELP speech coder for frame erasure channels (Abstract)

C.R. Watkins , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
Juin-Hwey Chen , Dept. of Speech Coding Res., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 241-244

Reconstruction of missing packets for CELP-based speech coders (Abstract)

A. Husain , Sch. of Eng. Sci., Simon Fraser Univ., Burnaby, BC, Canada
V. Cuperman , Sch. of Eng. Sci., Simon Fraser Univ., Burnaby, BC, Canada
pp. 245-248

A robust variable-rate speech coder (Abstract)

A. Alwan , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
I. Shen , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
B. Tang , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
G. Pottie , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
pp. 249-252

Wideband speech coding using multiple codebooks and glottal pulses (Abstract)

B.P. Murray , Dept. of Electron. & Electr. Eng., Univ. Coll. Dublin, Ireland
A.D. Fagan , Dept. of Electron. & Electr. Eng., Univ. Coll. Dublin, Ireland
D. McElroy , Dept. of Electron. & Electr. Eng., Univ. Coll. Dublin, Ireland
pp. 253-256

Speech coding using ISI coded quantization (Abstract)

R. Laroia , Dept. of Electron. & Electr. Eng., Univ. Coll. Dublin, Ireland
Nam Phamdo , State Univ. of New York, Stony Brook, NY, USA
Cheng-Chieh Lee , Dept. of Electron. & Electr. Eng., Univ. Coll. Dublin, Ireland
pp. 257-260

New techniques for multi-prototype waveform coding at 2.84 kb/s (Abstract)

I.S. Burnett , Dept. of Electr. & Comput. Eng., Wollongong Univ., NSW, Australia
G.J. Bradley , Dept. of Electr. & Comput. Eng., Wollongong Univ., NSW, Australia
pp. 261-264

Quantization of non-linear predictors in speech coding (Abstract)

S.D. Hansen , Dept. of Electron. & Electr. Eng., Univ. Coll. Dublin, Ireland
H. Nielsen , Tele Danmark Res., Horsholm, Denmark
J. Thyssen , Tele Danmark Res., Horsholm, Denmark
pp. 265-268

A fast robust stochastic algorithm for vector quantizer design for nonstationary channels (Abstract)

S. Saoudi , Dept. SC, ENSTBr, Brest, France
Z. Reguly , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
J.M. Boucher , Dept. SC, ENSTBr, Brest, France
B. Kovesi , Dept. SC, ENSTBr, Brest, France
pp. 269-272

Voice quality of interconnected PCS, Japanese cellular, and public switched telephone networks (Abstract)

M. Baraniecki , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
C. Ravishankar , COMSAT Lab., Clarksburg, MD, USA
S. Dimolitsas , COMSAT Lab., Clarksburg, MD, USA
F.L. Corcoran , COMSAT Lab., Clarksburg, MD, USA
pp. 273-276

Objective speech measure for Chinese in wireless environment (Abstract)

C.C. Chan , Hong Kong Univ. of Sci. & Technol., Hong Kong
S.F. Lau , Hong Kong Univ. of Sci. & Technol., Hong Kong
E.H. Lam , Hong Kong Univ. of Sci. & Technol., Hong Kong
K.F. Hui , Hong Kong Univ. of Sci. & Technol., Hong Kong
O.C. Au , Hong Kong Univ. of Sci. & Technol., Hong Kong
pp. 277-280

A training procedure for verifying string hypotheses in continuous speech recognition (Abstract)

C.H. Lee , AT&T Bell Labs., Murray Hill, NJ, USA
B.H. Juang , AT&T Bell Labs., Murray Hill, NJ, USA
R.C. Rose , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 281-284

Robust utterance verification for connected digits recognition (Abstract)

Biing-Hwang Juang , AT&T Bell Labs., Murray Hill, NJ, USA
Chin-Hui Lee , AT&T Bell Labs., Murray Hill, NJ, USA
M.G. Rahim , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 285-288

A hybrid wordspotting method for spontaneous speech understanding using word-based pattern matching and phoneme-based HMM (Abstract)

H. Kanazawa , Kansai Res. Lab., Toshiba Corp., Kobe, Japan
M. Tachimori , AT&T Bell Labs., Murray Hill, NJ, USA
Y. Takebayashi , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 289-292

Acoustic and language modeling of human and nonhuman noises for human-to-human spontaneous speech recognition (Abstract)

T. Schultz , Interactive Syst. Lab., Karlsruhe Univ., Germany
I. Rogina , Interactive Syst. Lab., Karlsruhe Univ., Germany
pp. 293-296

LVCSR log-likelihood ratio scoring for keyword spotting (Abstract)

M. Weintraub , Speech Technol. & Res. Program, SRI Int., Menlo Park, CA, USA
pp. 297-300

Keyword spotting using supervised/unsupervised competitive learning (Abstract)

C. Tadj , Signal Dept., Telecom Paris, France
F. Poirier , Signal Dept., Telecom Paris, France
pp. 301-304

A continuous density neural tree network word spotting system (Abstract)

R.J. Mammone , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
S.V. Kosonocky , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
pp. 305-308

Video mail retrieval: the effect of word spotting accuracy on precision (Abstract)

G.J.F. Jones , Dept. of Eng., Cambridge Univ., UK
K. Sparck Jones , AT&T Bell Labs., Murray Hill, NJ, USA
J.T. Foote , Dept. of Eng., Cambridge Univ., UK
S.J. Young , Hong Kong Univ. of Sci. & Technol., Hong Kong
pp. 309-312

Improved topic spotting through statistical modelling of keyword dependencies (Abstract)

J.H. Wright , Ensigma Ltd., Chepstow, UK
E. Parris , Ensigma Ltd., Chepstow, UK
M.J. Carey , Ensigma Ltd., Chepstow, UK
pp. 313-316

The influence of noise on the speaker recognition performance using the higher frequency band (Abstract)

F. Itakura , Sch. of Eng., Nagoya Univ., Japan
S. Hayakawa , Sch. of Eng., Nagoya Univ., Japan
pp. 321-324

Measuring fine structure in speech: application to speaker identification (Abstract)

F. Itakura , Lincoln Lab., MIT, Lexington, MA, USA
T.F. Quatieri , Lincoln Lab., MIT, Lexington, MA, USA
D.A. Reynolds , Lincoln Lab., MIT, Lexington, MA, USA
pp. 325-328

The effects of telephone transmission degradations on speaker recognition performance (Abstract)

D.A. Reynolds , Lincoln Lab., MIT, Lexington, MA, USA
T.F. Quatieri , Lincoln Lab., MIT, Lexington, MA, USA
G.C. O'Leary , Lincoln Lab., MIT, Lexington, MA, USA
M.A. Zissman , Lincoln Lab., MIT, Lexington, MA, USA
B.A. Carlson , Lincoln Lab., MIT, Lexington, MA, USA
pp. 329-332

Covariance estimation methods for channel robust 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. 333-336

Channel and noise compensation for text dependent speaker verification over telephone (Abstract)

W.Y. Hueng , ITT Aerosp. Commun., San Diego, CA, USA
B.D. Rao , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 337-340

Testing with the YOHO CD-ROM voice verification corpus (Abstract)

B.D. Rao , US Dept. of Defence, Fort Meade, MD, USA
pp. 341-344

An orthogonal polynomial representation of speech signals and its probabilistic model for text independent speaker verification (Abstract)

Hsiao-Chuan Wang , BBN Syst. & Technol. Corp., Cambridge, MA, USA
F.K. Soong , BBN Syst. & Technol. Corp., Cambridge, MA, USA
Chao-Shih Huang , Lincoln Lab., MIT, Lexington, MA, USA
Chi-Shi Liu , Telecommun. Lab., Minist. of Transportation & Commun., Taiwan
pp. 345-348

Text-dependent speaker verification using data fusion (Abstract)

K.R. Farrell , Dictaphone Corp., Stratford, CT, USA
pp. 349-352

Neural net approaches to speaker verification: comparison with second order statistic measures (Abstract)

M.M. Homayounpour , URA, CNRS, Paris, France
G. Chollet , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 353-356

A subword neural tree network approach to text-dependent speaker verification (Abstract)

R.J. Mammone , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
Han-Sheng Liou , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
pp. 357-360

Statistical modeling of speech feature vector trajectories based on a piecewise continuous mean path (Abstract)

M.M. Thomson , Dept. of Electr. & Electron. Eng., Auckland Univ., New Zealand
pp. 361-364

Trace-segmentation of isolated utterances for speech recognition (Abstract)

G.D. Tattersall , CAIP Center, Rutgers Univ., Piscataway, NJ, USA
M.M. Thomson , Lab. of Commun. & Signals, Sao Paulo Univ., Brazil
pp. 365-368

Optimal linear feature transformations for semi-continuous hidden Markov models (Abstract)

E.G. Schukat-Talamazzini , Friedrich-Alexander Univ., Erlangen, Germany
H. Niemann , Friedrich-Alexander Univ., Erlangen, Germany
J. Hornegger , Friedrich-Alexander Univ., Erlangen, Germany
pp. 369-372

Use of generalized dynamic feature parameters for speech recognition: maximum likelihood and minimum classification error approaches (Abstract)

L. Deng , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
C. Rathinavelu , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
pp. 373-376

A statistical pattern recognition approach to robust recursive identification of non-stationary AR model of speech production system (Abstract)

B.D. Kovacevic , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
M.I. Markovic , Inst. of Appl. Math. & Electron., Belgrade, Serbia
M.M. Milosaljevic , Friedrich-Alexander Univ., Erlangen, Germany
pp. 377-380

The NP speech activity detection algorithm (Abstract)

J. Pencak , Department of Defense, Ft. Meade, MD, USA
D. Nelson , Department of Defense, Ft. Meade, MD, USA
pp. 381-384

Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units (Abstract)

L. Deng , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
J. Nu , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
H. Sameti , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
pp. 385-388

Speech analysis based on Malvar wavelet transform (Abstract)

H. Leich , TCTS Labs., Fac. Polytech. de Mons, Belgium
V. Fontaine , TCTS Labs., Fac. Polytech. de Mons, Belgium
C. Ris , TCTS Labs., Fac. Polytech. de Mons, Belgium
pp. 389-392

Magnitude spectral estimation via Poisson moments with application to speech recognition (Abstract)

J.C. Principe , Lab. of Comput. Neuroeng., Florida Univ., Gainesville, FL, USA
S. Celebi , Lab. of Comput. Neuroeng., Florida Univ., Gainesville, FL, USA
pp. 393-396

Stochastic perceptual models of speech (Abstract)

Su-Lin Wu , Int. Comput. Sci. Inst., Berkeley, CA, USA
S. Greenberg , Int. Comput. Sci. Inst., Berkeley, CA, USA
N. Morgan , Int. Comput. Sci. Inst., Berkeley, CA, USA
H. Hermansky , Int. Comput. Sci. Inst., Berkeley, CA, USA
H. Bourland , Int. Comput. Sci. Inst., Berkeley, CA, USA
pp. 397-400

Auditory scene analysis and hidden Markov model recognition of speech in noise (Abstract)

M.P. Cooke , Dept. of Comput. Sci., Sheffield Univ., UK
P.D. Green , Dept. of Comput. Sci., Sheffield Univ., UK
M.D. Crawford , Dept. of Comput. Sci., Sheffield Univ., UK
pp. 401-404

Speech enhancement based on temporal processing (Abstract)

C. Avendano , Dept. of Electr. Eng. & Appl. Phys., Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
H. Hermansky , Dept. of Electr. Eng. & Appl. Phys., Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
E.A. Wan , Dept. of Electr. Eng. & Appl. Phys., Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
pp. 405-408

A comparative study of mel cepstra and EIH for phone classification under adverse conditions (Abstract)

S. Sandhu , AT&T Bell Labs., Murray Hill, NJ, USA
O. Ghitza , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 409-412

Supplementary orthogonal cepstral features (Abstract)

K.T. Assaleh , Motorola Inc., Scottsdale, AZ, USA
pp. 413-416

Subband analysis for robust speech recognition in the presence of car noise (Abstract)

E. Erzin , Bilkent Univ., Ankara, Turkey
A.E. Cetin , AT&T Bell Labs., Murray Hill, NJ, USA
Y. Yardimci , Dept. of Electr. Eng. & Appl. Phys., Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
pp. 417-420

Robust speech feature extraction using SBCOR analysis (Abstract)

S. Kajita , Sch. of Eng., Nagoya Univ., Japan
F. Itakura , Sch. of Eng., Nagoya Univ., Japan
pp. 421-424

New HOS-based parameter estimation methods for speech recognition in noisy environments (Abstract)

S. Tortola , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
J. Vidal , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
A. Moreno , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
J.A.R. Fonollosa , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
pp. 429-432

Noise compensation for speech recognition in car noise environments (Abstract)

R. Yang , Nokia Res. Center, Tampere, Finland
P. Haavisto , Nokia Res. Center, Tampere, Finland
pp. 433-436

Speech recognition in impulsive noise (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. 437-440

Speaker-independent phone modeling based on speaker-dependent HMMs' composition and clustering (Abstract)

T. Kosaka , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
S. Matsunaga , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
M. Kuraoka , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
pp. 441-444

Using morphology towards better large-vocabulary speech recognition systems (Abstract)

P. Geutner , Dept. of Comput. Sci., Karlsruhe Univ., Germany
pp. 445-448

Optimal splitting of HMM Gaussian mixture components with MMIE training (Abstract)

Y. Normandin , CRIM, McGill Univ., Montreal, Que., Canada
pp. 449-452

Dictionary learning: performance through consistency (Abstract)

T. Sloboda , Interactive Syst. Lab., Karlsruhe Univ., Germany
pp. 453-456

Incremental MAP estimation of HMMs for efficient training and improved performance (Abstract)

M.M. Hochberg , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
D.J. Mashao , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
H.F. Silverman , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
Y. Goto , Div. of Eng., Brown Univ., Providence, RI, USA
pp. 457-460

Discrete MMI probability models for HMM speech recognition (Abstract)

J.T. Foote , Dept. of Eng., Cambridge Univ., UK
pp. 461-464

Global discrimination for neural predictive systems based on N-best algorithm (Abstract)

A. Mellouk , LRI, CNRS, Orsay, France
P. Gallinari , ATR Interpreting Telephony Res. Labs., Kyoto, Japan
pp. 465-468

Enhancement of discriminative capabilities of HMM based recognizer through modification of Viterbi algorithm (Abstract)

J. Song , Dept. of Electr. & Comput. Eng., Wollongong Univ., NSW, Australia
pp. 469-472

A generalization of the Baum algorithm to functions on non-linear manifolds (Abstract)

D. Kanevsky , T.J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 473-476

Data-driven codebook adaptation in phonetically tied SCHMMs (Abstract)

T. Kemp , Karlsruhe Univ., Germany
pp. 477-479

NATO STANAG 4479: a standard for an 800 bps vocoder and channel coding in HF-ECCM system (Abstract)

B. Mouy , Thomson-CSF, Gennevilliers, France
P. De La Noue , Thomson-CSF, Gennevilliers, France
G. Goudezeune , Thomson-CSF, Gennevilliers, France
pp. 480-483

Harmonic and noise coding of LPC residuals with classified vector quantization (Abstract)

M. Nishiguchi , InfoCom Products Co., Sony Corp., Tokyo, Japan
J. Matsumoto , InfoCom Products Co., Sony Corp., Tokyo, Japan
pp. 484-487

Progress towards a new government standard 2400 bps voice coder (Abstract)

T.E. Tremain , US Dept. of Defence, Meade, MD, USA
M.A. Kohler , US Dept. of Defence, Meade, MD, USA
L.M. Supplee , US Dept. of Defence, Meade, MD, USA
pp. 488-491

Variable dimension spectral coding of speech at 2400 bps and below with phonetic classification (Abstract)

A. Das , 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. 492-495

Spectral excitation coding of speech at 2.4 kb/s (Abstract)

B. Bhattacharya , Sch. of Eng. Sci., Simon Fraser Univ., Burnaby, BC, Canada
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. 496-499

A robust 2400 bps subband LPC vocoder (Abstract)

P.A. Laurent , Speech Group, Thomson-CSF, Gennevilliers, France
P. De La Noue , Speech Group, Thomson-CSF, Gennevilliers, France
pp. 500-503

Band-widened harmonic vocoder at 2 to 4 kbps (Abstract)

H. Leich , Sch. of Eng. Sci., Simon Fraser Univ., Burnaby, BC, Canada
Gao Yang , Lernout & Hauspie Speech Products n.v., Mons, Belgium
G. Zanellato , Lernout & Hauspie Speech Products n.v., Mons, Belgium
pp. 504-507

A speech coder based on decomposition of characteristic waveforms (Abstract)

W.B. Kleijn , Lab. of Inf. Principles Res., AT&T Bell Labs., Murray Hill, NJ, USA
J. Haagen , Lab. of Inf. Principles Res., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 508-511

Speech compression using pitch synchronous interpolation (Abstract)

R.J. Sluijter , Signal Process. Group, Philips Res. Lab., Eindhoven, Netherlands
E. Kathmann , Signal Process. Group, Philips Res. Lab., Eindhoven, Netherlands
R. Taori , Signal Process. Group, Philips Res. Lab., Eindhoven, Netherlands
pp. 512-515

Pitch synchronous multi-band (PSMB) speech coding (Abstract)

H. Yang , Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore
P. Sivaprakasapillai , Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore
S.-N. Koh , Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore
pp. 516-519

Four-level tied-structure for efficient representation of acoustic modeling (Abstract)

S. Sagayama , NTT Human Interface Labs., Kanagawa, Japan
S. Takahashi , NTT Human Interface Labs., Kanagawa, Japan
pp. 520-523

Application of clustering techniques to mixture density modelling for continuous-speech recognition (Abstract)

C. Dugast , Philips Res. Lab., Aachen, Germany
R. Haeb-Umbach , Philips Res. Lab., Aachen, Germany
P. Beyerlein , Philips Res. Lab., Aachen, Germany
pp. 524-527

Context dependent phonetic duration models for decoding conversational speech (Abstract)

M.A. Picheny , Human Language Technol. Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M.D. Monkowski , Human Language Technol. Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P. Srinivasa Rao , Human Language Technol. Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 528-531

A unified way in incorporating segmental feature and segmental model into HMM (Abstract)

Jun He , Fac. Polytech. de Mons, Belgium
H. Leich , Fac. Polytech. de Mons, Belgium
pp. 532-535

Experimental evaluation of segmental HMMs (Abstract)

W.J. Holmes , Speech Res. Unit, DRA Malvern, UK
M.J. Russell , Speech Res. Unit, DRA Malvern, UK
pp. 536-539

Improved acoustic modeling for speech recognition using 2D Markov random fields (Abstract)

H. Lucke , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
pp. 540-543

Structured Markov models for speech recognition (Abstract)

G. Ruske , Inst. for Human-Machine-Commun., Munich Univ. of Technol., Germany
F. Wolfertstetter , Inst. for Human-Machine-Commun., Munich Univ. of Technol., Germany
pp. 544-547

Robust parametric modeling of durations in hidden Markov models (Abstract)

D. Burshtein , Dept. of Electr. Eng.-Syst., Tel Aviv Univ., Israel
pp. 548-551

Improved decision trees for phonetic modeling (Abstract)

Y. Normandin , Centre de Recherche Inf. de Montreal, Que., Canada
R. Kuhn , Centre de Recherche Inf. de Montreal, Que., Canada
A. Lazarides , Centre de Recherche Inf. de Montreal, Que., Canada
J. Brousseau , Centre de Recherche Inf. de Montreal, Que., Canada
pp. 552-555

High speed speech recognition using tree-structured probability density function (Abstract)

K. Takagi , Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
K. Shinoda , Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
K.-I. Iso , Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
T. Watanabe , Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
pp. 556-559

A fast segmental Viterbi algorithm for large vocabulary recognition (Abstract)

P. Laface , Dipartimento di Autom. e Inf., Politecnico di Torino, Italy
L. Fissore , Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
C. Vair , Dipartimento di Autom. e Inf., Politecnico di Torino, Italy
pp. 560-563

Searching with a transcription graph (Abstract)

Z. Li , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
P. Kenny , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
D. O'Shaughnessy , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 564-567

On the use of stochastic inference networks for representing multiple word pronunciations (Abstract)

R. De Mori , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
C. Snow , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
M. Galler , Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
pp. 568-571

A tree search strategy for large-vocabulary continuous speech recognition (Abstract)

R.L. Mercer , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
L.R. Bahl , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P.S. Gopalakrishnan , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 572-575

Lattice-based search strategies for large vocabulary speech recognition (Abstract)

F. Richardson , Dept. of Electr. Comput. & Syst. Eng., Boston Univ., MA, USA
J.R. Rohlicek , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Ostendorf , Dept. of Electr. Comput. & Syst. Eng., Boston Univ., MA, USA
pp. 576-579

On using a priori segmentation of the speech signal in an N-best solutions post-processing (Abstract)

T. Moudenc , CNET, Lannion, France
J. Monne , CNET, Lannion, France
D. Jouvet , CNET, Lannion, France
pp. 580-583

Time-synchronous continuous speech recognizer driven by a context-free grammar (Abstract)

H. Singer , CNET, Lannion, France
T. Shimizu , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
S. Matsunaga , Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
S. Monzen , CNET, Lannion, France
pp. 584-587

Language model representations for beam-search decoding (Abstract)

M. Federico , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
F. Brugnara , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
M. Cettolo , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
G. Antoniol , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
pp. 588-591

A lower-complexity Viterbi algorithm (Abstract)

S. Patel , Bellcore, Morristown, NJ, USA
pp. 592-595

Efficient search using posterior phone probability estimates (Abstract)

M. Hochberg , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
S. Renals , Dept. of Comput. Sci., Sheffield Univ., UK
pp. 596-599

Timing patterns in fluent and disfluent spontaneous speech (Abstract)

D. O'Shaughnessy , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 600-603

Stochastic modeling of pause insertion using context-free grammar (Abstract)

S. Fujio , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
N. Higuchi , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
Y. Sagisaka , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
pp. 604-607

Automatic classification of pitch movements via MLP-based estimation of class probabilities (Abstract)

L.F.M. ten Bosch , Inst. for Perception Res., Eindhoven, Netherlands
pp. 608-611

On the effects of speech rate in large vocabulary speech recognition systems (Abstract)

R.M. Stern , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
M.A. Siegler , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 612-615

A prosodic model of Mandarin speech and its application to pitch level generation for text-to-speech (Abstract)

Shaw-Hwa Hwang , Dept. of Commun. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Sin-Horng Chen , Dept. of Commun. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
pp. 616-619

Prosodic cues to word usage (Abstract)

D.G. Novick , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
K. Ward , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
pp. 620-623

Automatic prosodic segmentation by F/sub 0/ clustering using superpositional modeling (Abstract)

Y. Sagisaka , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
H. Shimodaira , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
H. Singer , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
M. Nakai , Tohoku Univ., Sendai, Japan
pp. 624-627

Duration modeling in large vocabulary speech recognition (Abstract)

R. Schwartz , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Portland, OR, USA
Han Shu , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
A. Anastasakos , Northeastern Univ., Boston, MA, USA
pp. 628-631

Speaker-independent automatic classification of Thai tones in connected speech by analysis-synthesis method (Abstract)

J.T. Gandour , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
S. Potisuk , Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
M.P. Harper , Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
pp. 632-635

Speech synthesis system based on a variable decimation/interpolation factor (Abstract)

M.H. Savoji , Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
F.M. Gimenez de los Galanes , ETSI Telecomunicacion, Univ. Politecnica de Madrid, Spain
J.M. Pardo , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
pp. 636-639

Automatic speech synthesiser parameter estimation using HMMs (Abstract)

R.E. Donovan , Dept. of Eng., Cambridge Univ., UK
P.C. Woodland , Dept. of Eng., Cambridge Univ., UK
pp. 640-643

Speaker modification with LPC pole analysis (Abstract)

T.R. Anderson , Dept. of Eng., Cambridge Univ., UK
J. Slifka , Syst. Res. Labs. Inc., Dayton, OH, USA
pp. 644-647

Synthesizing styled speech using the Klatt synthesizer (Abstract)

J.C. Rutledge , Dept. of Electr. Eng. & Comput. Sci., Northwestern Univ., Evanston, IL, USA
K.E. Cummings , Dept. of Eng., Cambridge Univ., UK
D.A. Lambert , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
M.A. Clements , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
pp. 648-651

Acoustic measurements of the vocal-tract area function: sensitivity analysis and experiments (Abstract)

F. Itakura , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
M. Honda , Dept. of Eng., Cambridge Univ., UK
H. Yehia , Sch. of Eng., Nagoya Univ., Japan
pp. 652-655

Shape-invariant pitch-synchronous text-to-speech conversion (Abstract)

C. Garcia-Mateo , ETSI Telecomunicacion, Vigo Univ., Spain
E.R. Banga , ETSI Telecomunicacion, Vigo Univ., Spain
pp. 656-659

Speech parameter generation from HMM using dynamic features (Abstract)

S. Imai , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
K. Tokuda , Dept. of Electr. & Electron. Eng., Tokyo Inst. of Technol., Japan
T. Kobayashi , ETSI Telecomunicacion, Vigo Univ., Spain
pp. 660-663

A source generator based modeling framework for synthesis of speech 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. 664-667

MBE synthesis of speech coded in LPC format (Abstract)

C.F. Chan , Dept. of Electron. Eng., City Polytech. of Hong Kong, Hong Kong
K.F. Lam , Dept. of Electron. Eng., City Polytech. of Hong Kong, Hong Kong
pp. 668-671

Modelling speech production using Yee's finite difference method (Abstract)

J.G. Maloney , Dept. of Electron. Eng., City Polytech. of Hong Kong, Hong Kong
M.A. Clements , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
K.E. Cummings , Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 672-675

Batch, incremental and instantaneous adaptation techniques for speech recognition (Abstract)

J. Makhoul , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
R. Schwartz , Dept. of Electron. Eng., City Polytech. of Hong Kong, Hong Kong
G. Zavaliagkos , Northeastern Univ., Boston, MA, USA
pp. 676-679

Speaker adaptation using combined transformation and Bayesian methods (Abstract)

V. Digalakis , Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA
L. Neumeyer , Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA
pp. 680-683

Rapid speaker adaptation using model prediction (Abstract)

S.M. Ahadi , Dept. of Eng., Cambridge Univ., UK
P.C. Woodland , Dept. of Eng., Cambridge Univ., UK
pp. 684-687

Speaker adaptation based on transfer vector field smoothing using maximum a posteriori probability estimation (Abstract)

T. Kosaka , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
S. Matsunaga , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
M. Tonomura , ATR Interpreting Telecommun. Res. Labs., Kyoto, Japan
pp. 688-691

Experiments using data augmentation for speaker adaptation (Abstract)

M.A. Picheny , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
J.R. Bellegarda , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
D. Nahamoo , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Padmanabhan , 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. 692-695

Vector-field-smoothed Bayesian learning for incremental speaker adaptation (Abstract)

S. Sagayama , NTT Human Interface Labs., Kanagawa, Japan
J. Takahashi , NTT Human Interface Labs., Kanagawa, Japan
pp. 696-699

A speaker adaptation technique using linear regression (Abstract)

S.J. Cox , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
pp. 700-703

On-line Bayes adaptation of SCHMM parameters for speech recognition (Abstract)

Chorkin Chan , Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
Qiang Huo , Dept. of Comput. Sci., Hong Kong Univ., Hong Kong
pp. 708-711

Iterative self-learning speaker and channel adaptation under various initial conditions (Abstract)

Yunxin Zhao , Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
pp. 712-715

Fast and low-complexity LSF quantization using algebraic vector quantizer (Abstract)

J.-P. Adoul , Dept. of Electr. & Comput. Eng., Sherbrooke Univ., Que., Canada
Minjie Xie , Dept. of Electr. & Comput. Eng., Sherbrooke Univ., Que., Canada
pp. 716-719

Low cost vector quantization methods for spectral coding in low rate speech coders (Abstract)

H.R.S. Mohammadi , Sch. of Electr. Eng., New South Wales Univ., Kensington, NSW, Australia
W.H. Holmes , Sch. of Electr. Eng., New South Wales Univ., Kensington, NSW, Australia
pp. 720-723

Matrix product quantization for very-low-rate speech coding (Abstract)

S. Bruhn , Inst. for Telecommun., Tech. Univ. Berlin, Germany
pp. 724-727

An intrinsically reliable and fast algorithm to compute the line spectrum pairs (LSP) in low bit rate CELP coding (Abstract)

A. Goalic , Dept. of Signals & Commun., ENST de Bretagne, Brest, France
S. Saoudi , Dept. of Signals & Commun., ENST de Bretagne, Brest, France
pp. 728-731

Spectral dynamics is more important than spectral distortion (Abstract)

H. Petter Knagenhjelm , Speech Coding Res. Dept., AT&T Bell Labs., Murray Hill, NJ, USA
W. Bastiaan Kleijn , Speech Coding Res. Dept., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 732-735

Efficient quantization of LSF parameters using classified SVQ combined with conditional splitting (Abstract)

Young-Kwon Cho , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
Dong-Il Chang , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
Souguil Ann , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
pp. 736-739

Efficient coding of LSP parameters using split matrix quantisation (Abstract)

C. Papanastasiou , Sch. of Eng., Manchester Univ., UK
C.S. Xydeas , Sch. of Eng., Manchester Univ., UK
pp. 740-743

How good is your /spl beta/?-observations on VQ training ratios (Abstract)

J.S. Collura , US Dept. of Defense, USA
T.E. Tremain , US Dept. of Defense, USA
pp. 744-747

Variable rate spectral quantization for phonetically classified CELP coding (Abstract)

R. Hagen , Dept. of Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
E. Paksoy , US Dept. of Defense, USA
A. Gersho , Dept. of Electron. Eng., Seoul Nat. Univ., South Korea
pp. 748-751

Optimal distortion measures for the high rate vector quantization of LPC parameters (Abstract)

W.R. Gardner , Dept. of Electr. & Comput. Eng., California Univ., San Diego, La Jolla, CA, USA
B.D. Rao , US Dept. of Defense, USA
pp. 752-755

Harmonics tracking and pitch extraction based on instantaneous frequency (Abstract)

T. Abe , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
S. Imai , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
T. Kobayashi , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
pp. 756-759

Decomposition of speech signals into deterministic and stochastic components (Abstract)

V. Darsinos , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
B. Yegnanarayana , Precision & Intelligence Lab., Tokyo Inst. of Technol., Yokohama, Japan
C. D'Alessandro , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 760-763

Modeling and processing speech with sums of AM-FM formant models (Abstract)

Shan Lu , Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
P.C. Doerschuk , Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
pp. 764-767

On the statistical properties of line spectrum pairs (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. 768-771

Individual variations in glottal characteristics of female speakers (Abstract)

H.M. Hanson , Div. of Appl. Sci., Harvard Univ., Cambridge, MA, USA
pp. 772-775

A robust method for determining instants of major excitations in voiced speech (Abstract)

R.L.H.M. Smits , Dept. of Appl. Phys., Delft Univ. of Technol., Netherlands
B. Yegnanarayana , Indian Inst. of Technol., Madras, India
pp. 776-779

Interpolation of LPC spectra via pole shifting (Abstract)

V. Goncharoff , Dept. of Electr. Eng. & Comput. Sci., Illinois Univ., Chicago, IL, USA
M. Kaine-Krolak , Dept. of Electr. Eng. & Comput. Sci., Illinois Univ., Chicago, IL, USA
pp. 780-783

Speech formant frequency and bandwidth tracking using multiband energy demodulation (Abstract)

P. Maragos , Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
A. Potamianos , Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 784-787

Nonlinear prediction for speech coding using radial basis functions (Abstract)

F. Diaz-de-Maria , Dept. de Electron., Cantabria Univ., Santander, Spain
A.R. Figueiras-Vidal , Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 788-791

Recognition of unvoiced stops from their time-frequency representation (Abstract)

A. Delopoulos , Dept. of Electr. Eng., Nat. Tech. Univ. of Athens, Greece
M. Rangoussi , Dept. of Electr. Eng., Nat. Tech. Univ. of Athens, Greece
pp. 792-795

Speech enhancement based on masking properties of the auditory system (Abstract)

N. Virag , Signal Process. Lab., Swiss Federal Inst. of Technol., Lausanne, Switzerland
pp. 796-799

Optimizing speech enhancement by exploiting masking properties of the human ear (Abstract)

A. Akbari Azirani , Lab. Traitement du Signal et de l'Image, Rennes I Univ., France
G. Faucon , Lab. Traitement du Signal et de l'Image, Rennes I Univ., France
R. Le Bouquin Jeannes , Lab. Traitement du Signal et de l'Image, Rennes I Univ., France
pp. 800-803

A spectrally-based signal subspace approach for speech enhancement (Abstract)

Y. Ephraim , Dept. of Electr. & Comput. Eng., George Mason Univ., Fairfax, VA, USA
H.L. van Trees , Dept. of Electr. & Comput. Eng., George Mason Univ., Fairfax, VA, USA
pp. 804-807

Real-time implementation of HMM-based MMSE algorithm for speech enhancement in hearing aid applications (Abstract)

R.L. Brennan , Dept. of Electr. & Comput. Eng., George Mason Univ., Fairfax, VA, USA
H. Sheikhzadeh , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
H. Sameti , Lab. Traitement du Signal et de l'Image, Rennes I Univ., France
pp. 808-811

New methods for adaptive noise suppression (Abstract)

L. Arslan , Syst. & Inf. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
V. Viswanathan , Syst. & Inf. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
A. McCree , Syst. & Inf. Sci. Lab., Texas Instrum. Inc., Dallas, TX, USA
pp. 812-815

Single-sensor speech enhancement using a soft-decision/variable attenuation algorithm (Abstract)

E.B. George , Signal Process. Center of Technol., Lockheed Sanders Inc., Nashua, NH, USA
pp. 816-819

Speech enhancement using a ternary-decision based filter (Abstract)

J. Rothweiler , Martin Marietta Labs., Baltimore, MD, USA
S. Mpasi , Martin Marietta Labs., Baltimore, MD, USA
N. Russell , Martin Marietta Labs., Baltimore, MD, USA
P. Green , Martin Marietta Labs., Baltimore, MD, USA
T.S. Sun , Martin Marietta Labs., Baltimore, MD, USA
S. Nandkumar , Martin Marietta Labs., Baltimore, MD, USA
A. Goldschen , Martin Marietta Labs., Baltimore, MD, USA
J. Carmody , Martin Marietta Labs., Baltimore, MD, USA
pp. 820-823

Signal modeling enhancements for automatic speech recognition (Abstract)

P.L. Silsbee , Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
S.A. Zahorian , Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
Z.B. Nossair , Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
pp. 824-827

Co-channel speaker separation (Abstract)

E.B. George , Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
L.T. Lee , Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
D.P. Morgan , Signal Process. Center of Technol., Lockheed Sanders Inc., Nashua, NH, USA
S.M. Kay , Martin Marietta Labs., Baltimore, MD, USA
pp. 828-831

Speech enhancement based on the generalized dual excitation model with adaptive analysis window (Abstract)

J.S. Lim , Res. Lab. of Electron., MIT, Cambridge, MA, USA
C.D. Yoo , Res. Lab. of Electron., MIT, Cambridge, MA, USA
pp. 832-835

Foreign accent classification using source generator based prosodic features (Abstract)

J.H.L. Hansen , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
L.M. Arslan , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
pp. 836-839

Automatic transcription of unknown words in a speech recognition system (Abstract)

R. Haeb-Umbach , Philips GmbH Forschungslab., Aachen, Germany
P. Beyerlein , Philips GmbH Forschungslab., Aachen, Germany
E. Thelen , Philips GmbH Forschungslab., Aachen, Germany
pp. 840-843

An evaluation of an adaptive multichannel system for speech enhancement with automatic phase alignment (Abstract)

B.G. Aguiar Neto , Philips GmbH Forschungslab., Aachen, Germany
S.L. do N. Cunha Costa , Dept. de Engenharia Eletrica, Univ. Federal de Pernambuco, Campina Grande, Brazil
pp. 844-847

Knowing who to listen to in speech recognition: visually guided beamforming (Abstract)

A. Waibel , Carnegie Mellon Univ., Pittsburgh, PA, USA
M. Hunke , Carnegie Mellon Univ., Pittsburgh, PA, USA
U. Bub , Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 848-851

An N-best strategy, dynamic grammars and selectively trained neural networks for real-time recognition of continuously spelled names over the telephone (Abstract)

D. Fohr , Carnegie Mellon Univ., Pittsburgh, PA, USA
J.-C. Junqua , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
S. Valente , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
J.-F. Mari , Martin Marietta Labs., Baltimore, MD, USA
pp. 852-855

Language models for a spelled letter recognizer (Abstract)

M. Betz , Karlsruhe Univ., Germany
H. Hild , Karlsruhe Univ., Germany
pp. 856-859

Hands free continuous speech recognition in noisy environment using a four microphone array (Abstract)

P. Svaizer , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
M. Omologo , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
D. Giuliani , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
M. Matassoni , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
pp. 860-863

A new method for automatic generation of speaker-dependent phonological rules (Abstract)

T. Imai , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
E. Miyasaka , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
A. Ando , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
pp. 864-867

Enhancing automatic speech recognition with an ultrasonic lip motion detector (Abstract)

D.L. Jennings , Dept. of Electr. & Comput. Eng., Air Force Inst. of Technol., Wright-Patterson AFB, OH, USA
D.W. Ruck , Dept. of Electr. & Comput. Eng., Air Force Inst. of Technol., Wright-Patterson AFB, OH, USA
pp. 868-871

Classification and clustering of stop consonants via nonparametric transformations and wavelets (Abstract)

B. Gidas , Div. of Appl. Math., Brown Univ., Providence, RI, USA
A. Murua , Dept. of Electr. & Comput. Eng., Air Force Inst. of Technol., Wright-Patterson AFB, OH, USA
pp. 872-875
90 ms
(Ver )