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

Phonological parsing for reversible letter-to-sound/sound-to-letter generation (Abstract)

H.M. Meng , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
V.W. Zue , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
S. Seneff , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
pp. 1-4

A computationally efficient wavelet transform CELP coder (Abstract)

J. Ooi , MIT, Cambridge, MA, USA
V. Viswanathan , Lab. for Comput. Sci., MIT, Cambridge, MA, USA
pp. 101-104

Perceptual enhancement of CELP speech coders (Abstract)

D. Sen , 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. 105-108

CELP speech coding with almost no codebook search (Abstract)

C.G. Gerlach , Inst. for Commun. Syst. & Data Process., Aachen Univ. of Technol., Germany
pp. 109-112

A pitch synchronous innovation CELP (PSI-CELP) coder for 2-4 kbit/s (Abstract)

K. Mano , NTT Human Interface Labs., Tokyo, Japan
H. Ohmuro , NTT Human Interface Labs., Tokyo, Japan
Y. Moriya , NTT Human Interface Labs., Tokyo, Japan
S. Miki , NTT Human Interface Labs., Tokyo, Japan
K. Oguchi , NTT Human Interface Labs., Tokyo, Japan
pp. 113-116

Multi-band residual coding of CELP codecs at 8 kb/s (Abstract)

M. Saikaly , INRS Telecommun., Montreal, Que., Canada
P. Zheng , INRS Telecommun., Montreal, Que., Canada
P. Mermelstein , INRS Telecommun., Montreal, Que., Canada
pp. 117-120

A real-time wideband CELP coder for a videophone application (Abstract)

F.T. Johansen , NTT Human Interface Labs., Tokyo, Japan
J.E. Knudsen , INRS Telecommun., Montreal, Que., Canada
E. Harborg , SINTEF, Trondheim, Norway
A. Fuldseth , INRS Telecommun., Montreal, Que., Canada
pp. 121-124

Large vocabulary continuous speech recognition using HTK (Abstract)

V. Valtchev , Dept. of Eng., Cambridge Univ., UK
J.J. Odell , Dept. of Eng., Cambridge Univ., UK
P.C. Woodland , Dept. of Eng., Cambridge Univ., UK
S.J. Young , Dept. of Eng., Cambridge Univ., UK
pp. 125-128

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

C. Dugast , Philips GmbH Res. Lab. Aachen, Germany
V. Steinbiss , Dept. of Eng., Cambridge Univ., UK
H. Ney , Dept. of Eng., Cambridge Univ., UK
X. Aubert , Philips GmbH Res. Lab. Aachen, Germany
pp. 129-132

Efficient chart parsing of speech recognition candidates (Abstract)

T. Tashiro , ATR Interpreting Telecommun. Res. Lab., Japan
T. Morimoto , ATR Interpreting Telecommun. Res. Lab., Japan
M. Nagata , Dept. of Eng., Cambridge Univ., UK
T. Takezawa , ATR Interpreting Telecommun. Res. Lab., Japan
pp. 13-16

An initial study on a segmental probability model approach to large-vocabulary continuous Mandarin speech recognition (Abstract)

Jia-Lin Shen , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Lin-Shan Lee , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Bo-Ren Bai , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Hsin-Min Wang , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
pp. 133-136

Large vocabulary word recognition based on tree-trellis search (Abstract)

Lin-Shan Lee , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Jung-Kuei Chen , Telecommun. Lab., Minist. of Commun., Chung-Li, Taiwan
F.K. Soong , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
pp. 137-140

Search algorithm that merges candidates in meaning level for very large vocabulary spontaneous speech recognition (Abstract)

T. Yamada , NTT Human Interface Labs., Tokyo, Japan
K. Shikano , NTT Human Interface Labs., Tokyo, Japan
S. Takahashi , NTT Human Interface Labs., Tokyo, Japan
Y. Minami , NTT Human Interface Labs., Tokyo, Japan
pp. 141-144

Context-free large-vocabulary connected speech recognition with evolutional grammars (Abstract)

S.C. Glinski , AT&T Bell Labs., Murray Hill, NJ, USA
M.K. Brown , AT&T Bell Labs., Murray Hill, NJ, USA
pp. 145-148

Non-uniform unit parsing for SSS-LR continuous speech recognition (Abstract)

S. Matsunaga , ATR Interpreting Telecommun.Res. Labs., Kyoto, Japan
J. Takami , ATR Interpreting Telecommun.Res. Labs., Kyoto, Japan
H. Singer , ATR Interpreting Telecommun.Res. Labs., Kyoto, Japan
pp. 149-152

An algorithm of high resolution and efficient multiple string hypothesization for continuous speech recognition using inter-word models (Abstract)

T. Matsuoka , ATR Interpreting Telecommun.Res. Labs., Kyoto, Japan
B.-H. Juang , ATR Interpreting Telecommun.Res. Labs., Kyoto, Japan
C.-H. Lee , NTT Human Interface Labs., Tokyo, Japan
W. Chou , Dept. of Res. Technol., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 153-156

Fast match acoustic models in large vocabulary continuous speech recognition (Abstract)

H. Garudadri , INRS Telecommun., Vardun, Que., Canada
P. Kenny , INRS Telecommun., Vardun, Que., Canada
P. Labute , INRS Telecommun., Vardun, Que., Canada
G. Boulianne , INRS Telecommun., Vardun, Que., Canada
pp. 157-160

A channel-bank-based phone detection strategy (Abstract)

D. Nahamoo , Continuous Speech Recognition Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M.A. Picheny , Continuous Speech Recognition Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
P.S. Gopalakrishnan , Continuous Speech Recognition Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
M. Padmanabhan , Continuous Speech Recognition Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 161-164

Hybrid system combining expert-TDNNs and HMMs for continuous speech recognition (Abstract)

L. Devillers , Lab. d'Informatique pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
C. Dugast , Continuous Speech Recognition Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 165-168

A generalised model for utilising prosodic information in continuous speech recognition (Abstract)

A. Hunt , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
pp. 169-172

Integrating semantic constraints into the Sphinx-II recognition search (Abstract)

W. Ward , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
S. Issar , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 17-19

Automatic classification of prosodically marked phrase boundaries in German (Abstract)

A. Kiessling , Continuous Speech Recognition Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
A. Batliner , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
H. Niemann , NTT Human Interface Labs., Tokyo, Japan
R. Kompe , Lehrstuhl fur Mustererkennung, Erlangen-Nurnberg Univ., Germany
U. Kilian , Continuous Speech Recognition Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 173-176

Suprasegmental features and continuous speech recognition (Abstract)

P. Dumouchel , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 177-180

An automatic intonation tone contour labelling and classification algorithm (Abstract)

A. Grigoriu , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
J.P. Vonwiller , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
R.W. King , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
pp. 181-184

Prosodic phrase segmentation by pitch pattern clustering (Abstract)

M. Nakai , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
H. Shimodaira , JAIST, Nomi, Japan
pp. 185-188

Fine pitch contour extraction by voice fundamental wave filtering method (Abstract)

H. Ohmura , Electrotech. Lab., Ibaraki, Japan
pp. 189-192

Subband-Autocorrelation analysis and its application for speech recognition (Abstract)

S. Kajita , Sch. of Eng., Nagoya Univ., Japan
F. Itakura , Sch. of Eng., Nagoya Univ., Japan
pp. 193-196

Optimization of time-frequency masking filters using the minimum classification error criterion (Abstract)

M. Bacchiani , ATR Human Inf. Process. Res. Labs, Kyoto, Japan
K. Aikawa , ATR Human Inf. Process. Res. Labs, Kyoto, Japan
pp. 197-200

A new paradigm for reliable automatic formant tracking (Abstract)

M.-O. Berger , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
Y. Laprie , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
pp. 201-204

Recursive tracking of formants in speech signals (Abstract)

I.J. Cox , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
S. Hingorani , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
M. Niranjan , Dept. of Eng., Cambridge Univ., UK
pp. 205-208

Low rate audio coder with hierarchical filterbanks and lattice vector quantization (Abstract)

Shiufun Cheung , Res. Lab. of Electron., MIT, Cambridge, MA, USA
P. Monta , Res. Lab. of Electron., MIT, Cambridge, MA, USA
pp. 209-212

Detecting misrecognitions and out-of-vocabulary words (Abstract)

S.R. Young , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 21-24

A two-channel approach to the removal of impulsive noise from archived recordings (Abstract)

C.M. Hicks , Dept. of Eng., Cambridge Univ., UK
S.J. Godsill , Dept. of Eng., Cambridge Univ., UK
pp. 213-216

Improved musical pitch tracking using principal decomposition analysis (Abstract)

E. Dorken , Boston Univ., MA, USA
S. Hamid Nawab , Boston Univ., MA, USA
pp. 217-220

Real-time, loose-harmonic matching fundamental frequency estimation for musical signals (Abstract)

P.F.-C. Enriquez , ETSI Telecomunicacion, Univ. Politecnica de Madrid, Spain
F.J. Casajus Quiros , ETSI Telecomunicacion, Univ. Politecnica de Madrid, Spain
pp. 221-224

Real time speech rate converting system for elderly people (Abstract)

T. Takagi , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
R. Ikezawa , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
N. Seiyama , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
E. Miyasaka , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
A. Nakamura , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
pp. 225-228

Automatic model parameter generation for the speech training of deaf children (Abstract)

H. Javkin , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
K. Youdelman , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
N. Antonanzas-Barroso , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
Y. Yamada , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
E. Keate , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
pp. 229-232

Recursive restoration of pitch variation defects in musical recordings (Abstract)

S.J. Godsill , Dept. of Eng., Cambridge Univ., UK
pp. 233-236

Detection of human speech in structured noise (Abstract)

H. Wechsler , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
J.D. Hoyt , Eng. Res. Facility, Federal Bur. of Investigation, Quantico, VA, USA
pp. 237-240

Active control using IIR filters-a second look (Abstract)

S.D. Snyder , Dept. of Mech. Eng., Adelaide Univ., SA, Australia
pp. 241-244

DSP implementation and performance evaluation of a compact stereo echo canceller (Abstract)

N. Kawayachi , NHK Sci. & Tech. Res. Labs., Tokyo, Japan
A. Hirano , Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
Y. Arasawa , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
A. Sugiyama , Inf. Technol. Res. Labs., NEC Corp., Kawasaki, Japan
pp. 245-248

A time varying step size normalized LMS echo canceler algorithm (Abstract)

L.N. de Rivera O , Dept. of Electr. Eng., Univ. Autonoma Metropolitana, Mexico City, Mexico
J.C.S. Garcia , Dept. of Electr. Eng., Univ. Autonoma Metropolitana, Mexico City, Mexico
H.P. Meana , Dept. of Electr. Eng., Univ. Autonoma Metropolitana, Mexico City, Mexico
F.C. Sanchez , Dept. of Electr. Eng., Univ. Autonoma Metropolitana, Mexico City, Mexico
M.N. Miyatake , Dept. of Electr. Eng., Univ. Autonoma Metropolitana, Mexico City, Mexico
pp. 249-252

Heuristic search integrating syntactic, semantic and dialog-level constraints (Abstract)

T. Kawahara , Dept. of Inf. Sci., Kyoto Univ., Japan
S. Doshita , Dept. of Inf. Sci., Kyoto Univ., Japan
M. Araki , Dept. of Inf. Sci., Kyoto Univ., Japan
pp. 25-28

Fully adaptive generalized recursive control system for active acoustic attenuation (Abstract)

L.J. Eriksson , DIGISONIX Inc., Middleton, WI, USA
S.R. Popovich , DIGISONIX Inc., Middleton, WI, USA
T.A. Laak , DIGISONIX Inc., Middleton, WI, USA
M.C. Allie , DIGISONIX Inc., Middleton, WI, USA
D.E. Melton , DIGISONIX Inc., Middleton, WI, USA
pp. 253-256

Characterization of talker radiation pattern using a microphone array (Abstract)

H.F. Silverman , Div. of Eng., Brown Univ., Providence, RI, USA
P.C. Meuse , Div. of Eng., Brown Univ., Providence, RI, USA
pp. 257-260

Effects of room reverberation on time-delay estimation performance (Abstract)

S. Bedard , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
B. Champagne , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
A. Stephenne , INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
pp. 261-264

New adaptive-filtering techniques applied to speech echo cancellation (Abstract)

A. Alwan , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
M.G. Siqueira , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
pp. 265-268

Colouration in assisted reverberation systems (Abstract)

M.A. Poletti , Ind. Res. Ltd., Lower Hutt, New Zealand
pp. 269-272

Acoustic event localization using a crosspower-spectrum phase based technique (Abstract)

P. Svaizer , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
M. Omologo , Istituto per la Ricerca Sci. e Tecnologica, Trento, Italy
pp. 273-276

Parametric separation applied to underwater acoustic multipath propagation (Abstract)

A. Essebbar , ENSIEG, CNRS, St. Martin d'Heres, France
pp. 277-280

Far field array processing with neural networks (Abstract)

B. Colnet , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
J.-P. Haton , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
pp. 281-284

Adaptive waveform selection for active sonar (Abstract)

R.J. Evans , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
D.J. Kershaw , Mater. Res. Lab., Defence Sci. & Technol. Organ., Ascot Vale, Vic., Australia
pp. 285-288

A comparison between spectral and bispectral analysis for ship detection from acoustical time series (Abstract)

C.S. Regazzoni , Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
G. Tacconi , Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
A. Tesei , Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
pp. 289-292

On jointly learning the parameters in a character-synchronous integrated speech and language model (Abstract)

Keh-Yih Su , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Tung-Hui Chiang , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Yi-Chung Lin , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 29-32

The use of non-supervised neural networks to detect lines in lofargram (Abstract)

B. Colnet , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
J.C. Di Martino , CRIN-INRIA Lorraine, Vandoeuvre-les-Nancy, France
M. Di Martino , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
pp. 293-296

Adaptive detection of moving signal using shallow sea hydroacoustic data (Abstract)

V.A. Zverev , Inst. of Appl. Phys., Acad. of Sci., Nizhny Novgorod, Russia
A.B. Gershman , Inst. of Appl. Phys., Acad. of Sci., Nizhny Novgorod, Russia
pp. 297-300

GASTOM 90 tomography experiment data inversion (Abstract)

Y. Stephan , Centre Mil. d'Oceanogr., EPSHOM, Brest, France
F.R. Martin-Lauzer , Centre Mil. d'Oceanogr., EPSHOM, Brest, France
pp. 301-304

Probabilistic ray identification: a new tool for ocean acoustic tomography (Abstract)

D. Mauuary , Centre Mil. d'Oceanogr., EPSHOM, Brest, France
Y. Stephan , Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
F.R. Martin-Lauzer , CMO, Brest, France
pp. 305-308

Quantisation error modelling of narrowband adaptive arrays using projected perturbation sequences (Abstract)

S. Ivandich , Adaptive Signal Process. Lab., Curtin Univ. of Technol., Bentley, WA, Australia
pp. 309-312

An integrated approach to passive target classification (Abstract)

K.A. Kumar , Dept. of Electr. & Comput. Eng., Regional Eng. Coll., Tiruchirappalli, India
P. Ramakrishna Rao , Dept. of Electr. & Comput. Eng., Regional Eng. Coll., Tiruchirappalli, India
R. Rajagopal , Dept. of Electr. & Comput. Eng., Regional Eng. Coll., Tiruchirappalli, India
pp. 313-316

Maneuvering target motion analysis using hidden Markov model (Abstract)

O. Tremois , IRISA, Rennes, France
J.P. Le Cadre , IRISA, Rennes, France
pp. 317-320

Optimum Costas-like decompositions of Costas arrays for channel characterization and communications (Abstract)

S.K. Mehta , Naval Underwater Warfare Center, New London, CT, USA
E.L. Titlebaum , IRISA, Rennes, France
pp. 321-324

Transient sonar signal classification using hidden Markov model and neural net (Abstract)

G.C. Chen , RDT&E Div., Naval Command, Control & Ocean Surveillance Center, San Diego, CA, USA
C.E. Persons , RDT&E Div., Naval Command, Control & Ocean Surveillance Center, San Diego, CA, USA
A. Kundu , RDT&E Div., Naval Command, Control & Ocean Surveillance Center, San Diego, CA, USA
pp. 325-328

Statistics of the phase delays between array receivers estimated from the eigendecomposition of the signal correlation matrix (Abstract)

Y.H. Leung , Dept. of Electr. & Electron. Eng., Western Australia Univ., Crawley, WA, Australia
A. Cantoni , RDT&E Div., Naval Command, Control & Ocean Surveillance Center, San Diego, CA, USA
J.J. Smith , Dept. of Electr. & Electron. Eng., Western Australia Univ., Crawley, WA, Australia
pp. 329-332

A multimodal, keyword-based spoken dialogue system-MultiksDial (Abstract)

H. Kamio , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
T. Nitta , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
Y. Masai , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
S. Tanaka , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
J. Iwasaki , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
H. Matsu'ura , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
pp. 33-36

Extraction of pertinent parameters in oceanographic data (Abstract)

L. Kerleguer , Centre Mil. d'Oceanogr., Brest, France
P. Mennecier , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
M. Cresp , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
M. Bouvet , Centre Mil. d'Oceanogr., Brest, France
pp. 333-336

Matched field processing in shallow ocean: signal arrival identification using EM algorithm (Abstract)

C.F. Mecklenbrauker , Dept. of Electr. Eng., Ruhr-Univ., Bochum, Germany
J.F. Bohme , Dept. of Electr. Eng., Ruhr-Univ., Bochum, Germany
pp. 337-340

Bayesian time delay estimation for ocean acoustic tomography (Abstract)

G. Jourdain , Centre d'Etudes des PHenomenes Aleatoires et Geophys., Saint Martin d'Heres, France
D. Mauuary , Centre d'Etudes des PHenomenes Aleatoires et Geophys., Saint Martin d'Heres, France
pp. 341-344

Resolving ambiguities in estimating spatial frequencies in sparse linear array (Abstract)

Hongya Ge , Dept. of Electr. Eng., Rhode Island Univ., Kingston, RI, USA
D.W. Tufts , Dept. of Electr. Eng., Rhode Island Univ., Kingston, RI, USA
R. Kumaresan , Dept. of Electr. Eng., Rhode Island Univ., Kingston, RI, USA
pp. 345-348

A deconvolution approach to moving sources localization (Abstract)

J.-J. Fuchs , IRISA, Rennes, France
H. Chuberre , IRISA, Rennes, France
pp. 349-352

High-resolution bathymetric simulations based on Kirchhoff scattering theory and anisotropic seafloor modeling (Abstract)

D. Alexandrou , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
V. Premus , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
D. Pantzartzis , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
pp. 353-356

Geolocalization by combined range difference and range rate difference measurements (Abstract)

G.H. Niezgoda , Dept. of Electr. & Comput. Eng., R. Mil. Coll. of Canada, Kingston, Ont., Canada
K.C. Ho , Dept. of Electr. & Comput. Eng., R. Mil. Coll. of Canada, Kingston, Ont., Canada
pp. 357-360

Extraction of multiple periodic waveforms from noisy data (Abstract)

P.P. Kanjilal , Dept. of Electron. & Electr. Commun. Eng., Indian Inst. of Technol., Kharagpur, India
S. Palit , Dept. of Electron. & Electr. Commun. Eng., Indian Inst. of Technol., Kharagpur, India
pp. 361-364

Deconvolution of sensor array signals using time-scaling (Abstract)

A. El-Jaroudi , Dept. of Electron. & Electr. Commun. Eng., Indian Inst. of Technol., Kharagpur, India
M. Simaan , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
T. Akgul , Lab. for Comput. Neurosci., Pittsburgh Univ., PA, USA
pp. 365-368

Correction of I/Q errors in homodyne step frequency radar refocuses range profiles (Abstract)

G.F. Stickley , Dept. of Electr. & Comput. Eng., Queensland Univ., Qld., Australia
D.A. Noon , Dept. of Electr. & Comput. Eng., Queensland Univ., Qld., Australia
D. Longstaff , Dept. of Electr. & Comput. Eng., Queensland Univ., Qld., Australia
pp. 369-372

Learning consistent semantics from training data (Abstract)

E. Millien , CRIM, Montreal, Que., Canada
R. Kuhn , CRIM, Montreal, Que., Canada
R. de mori , CRIM, Montreal, Que., Canada
pp. 37-40

Radar target recognition using range profiles (Abstract)

A. Zyweck , Microwave Radar Div., Defence Sci. & Technol. Organ., Adelaide, SA, Australia
R.E. Bogner , CRIM, Montreal, Que., Canada
pp. 373-376

Weak radar signal detection based on wavelet transform (Abstract)

S. Mori , Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
I. Sasase , Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
N. Ehara , Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
pp. 377-380

Detection, identification and tracking of active scatterers (Abstract)

Z. Mohcine , S2HF-IRESTE La Chantrerie, Nantes, France
S. Joseph , S2HF-IRESTE La Chantrerie, Nantes, France
pp. 381-384

Estimation of the causal impulse response of underwater target (Abstract)

A. Dziedzic , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
Zhigang Sun , Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
G. Gimenez , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
P. Delachartre , Univ. Claude Bernard, Villeurbanne, France
D. Tray , S2HF-IRESTE La Chantrerie, Nantes, France
pp. 385-388

An adaptive linear multiuser receiver for deep water acoustic local area networks (Abstract)

J. Catipovic , Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
D. Brady , S2HF-IRESTE La Chantrerie, Nantes, France
Z. Zvonar , Woods Hole Oceanogr. Instn., MA, USA
pp. 389-392

An efficient closed-form localization solution from time difference of arrival measurements (Abstract)

K.C. Ho , Dept. of Electr. & Comput. Eng., R. Mil. Coll. of Canada, Kingston, Ont., Canada
Y.T. Chan , Dept. of Electr. & Comput. Eng., R. Mil. Coll. of Canada, Kingston, Ont., Canada
pp. 393-396

Time delay estimation using integrated polyspectrum (Abstract)

J.K. Tugnait , Dept. of Electr. Eng., Auburn Univ., AL, USA
Yisong Ye , Dept. of Electr. Eng., Auburn Univ., AL, USA
pp. 397-400

A VLSI architecture for real-time hierarchical encoding/decoding of video using the wavelet transform (Abstract)

M. Vishwanath , Comput. Sci. Lab., Xerox Palo Alto Res. Center, CA, USA
C. Chakrabarti , Dept. of Electr. Eng., Auburn Univ., AL, USA
pp. 401-404

Digit pipelined discrete wavelet transform (Abstract)

R.M. Owens , Dept. of Comput. Sci. & Eng., Pennsylvania State Univ., University Park, PA, USA
C. Nagendra , Dept. of Comput. Sci. & Eng., Pennsylvania State Univ., University Park, PA, USA
M.J. Irwin , Dept. of Comput. Sci. & Eng., Pennsylvania State Univ., University Park, PA, USA
pp. 405-408

A low power subband video decoder architecture (Abstract)

B.M. Gordon , Comput. Syst. Lab., Stanford Univ., CA, USA
T.H.Y. Meng , Comput. Syst. Lab., Stanford Univ., CA, USA
pp. 409-412

Parsing word graphs using a linguistic grammar and a statistical language model (Abstract)

L.A. Schmid , Corp. Res., Siemens AG, Munich, Germany
pp. 41-44

A hierarchical multiprocessor architecture based on heterogeneous processors for video coding applications (Abstract)

R. Hoffer , Lab. fur Informationstechnol., Hannover Univ., Germany
P. Pirsch , Lab. fur Informationstechnol., Hannover Univ., Germany
W. Gehrke , Lab. fur Informationstechnol., Hannover Univ., Germany
pp. 413-416

Video DSP architecture for MPEG2 codec (Abstract)

M. Toyokura , Semicond. Res. Center, Matsushita Electr. Ind. Co. Ltd., Japan
B. Wilson , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
H. Takeno , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
K. Aono , Multimedia Eng. Lab., Toshiba Corp., Kawasaki, Japan
T. Akiyama , Lab. fur Informationstechnol., Hannover Univ., Germany
T. Araki , Semicond. Res. Center, Matsushita Electr. Ind. Co. Ltd., Japan
pp. 417-420

Arithmetic codec from behavioral description based LSI-CAD for fully programmable image coding system (Abstract)

J. Suzuki , NTT Transmission Syst. Labs., Yokosuka, Japan
S. Ono , Lab. fur Informationstechnol., Hannover Univ., Germany
F. Colin , Semicond. Res. Center, Matsushita Electr. Ind. Co. Ltd., Japan
pp. 421-424

Secure speech and data communication over the public switching telephone network (Abstract)

L. Diez-Del-Rio , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
R. Sarmiento , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
R. Garcia-Gomez , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
J. Parera , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
S. Moreno-Perez , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
M. Veiga-Perez , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
pp. 425-428

A DSP core for speech coding applications (Abstract)

T. Karema , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
E. Ofner , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
A. Gierlinger , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
J. Jernej , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
V. Eerola , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
J. Nurmi , Signal Process. Lab., Tampere Univ. of Technol., Finland
pp. 429-432

Concurrency characteristics in DSP programs (Abstract)

J. Rabaey , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
L. Guerra , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
M. Potkonjak , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
pp. 433-436

Application-driven design of DSP architectures and compilers (Abstract)

C.G. Lee , Dept. of Electr. & Comput. Eng., Toronto Univ., Ont., Canada
M.A.R. Saghir , Dept. of Electr. & Comput. Eng., Toronto Univ., Ont., Canada
P. Chow , Dept. of Electr. & Comput. Eng., Toronto Univ., Ont., Canada
pp. 437-440

Behavioral synthesis of low-cost partial scan designs for DSP applications (Abstract)

S. Dey , C&C Res. Lab., NEC USA, Princeton, NJ, USA
R.K. Roy , C&C Res. Lab., NEC USA, Princeton, NJ, USA
M. Potkonjak , C&C Res. Lab., NEC USA, Princeton, NJ, USA
pp. 441-444

Automatic code generation for heterogeneous multiprocessors (Abstract)

E.A. Lee , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
T.M. Parks , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
J.L. Pino , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
pp. 445-448

Dynamic data flow and control flow in high level DSP code synthesis (Abstract)

O. Mauss , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
S. Ritz , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
H. Meyr , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
M. Pankert , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
pp. 449-452

Minimum cost based phoneme class detection for improved iterative speech enhancement (Abstract)

J.N.L. Hansen , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
L.M. Arslan , Dept. of Electr. Eng., Duke Univ., Durham, NC, USA
pp. 45-48

Minimizing memory requirements for chain-structured synchronous dataflow programs (Abstract)

S.S. Bhattacharyya , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
E.A. Lee , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
P.K. Murthy , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
pp. 453-456

Word-length determination and scaling software for a signal flow block diagram (Abstract)

Wonyong Sung , Inter-Univ. Semicond. Res. Center, Seoul Nat. Univ., South Korea
Ki-Il Kum , Inter-Univ. Semicond. Res. Center, Seoul Nat. Univ., South Korea
pp. 457-460

RECALS II: a new list scheduling algorithm (Abstract)

R. Jain , Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA
Minjoong Rim , Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA
pp. 461-464

Retiming of DSP programs for optimum vectorization (Abstract)

S. Ritz , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
H. Meyr , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
V. Zivojnovic , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
pp. 465-468

Generating efficient loop code for programmable DSPs (Abstract)

J.M. Potter , Univ. of Technol., Sydney, NSW, Australia
H.J. Reekie , Univ. of Technol., Sydney, NSW, Australia
pp. 469-472

Specification and support for multidimensional DSP in the SILAGE language (Abstract)

I.M. Verbauwhede , Dept. of Electr. Eng. & Comput. Sci., California Univ., Berkeley, CA, USA
C.J. Scheers , Univ. of Technol., Sydney, NSW, Australia
J.M. Rabaey , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
pp. 473-476

On the formal derivation of a systolic array for recursive least squares estimation (Abstract)

J.G. McWhirter , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
G. Hekstra , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
M. Moonen , ESAT, Katholieke Univ., Leuven, Belgium
I.K. Proudler , Univ. of Technol., Sydney, NSW, Australia
pp. 477-480

Computation of the real Schur decomposition of nonsymmetric matrices and its hardware implementation (Abstract)

K. Huper , Inst. for Network Theory & Circuit Design, Tech. Univ. Munchen, Germany
R. Pauli , Inst. for Network Theory & Circuit Design, Tech. Univ. Munchen, Germany
S. Paul , Inst. for Network Theory & Circuit Design, Tech. Univ. Munchen, Germany
pp. 481-484

A novel efficient parallel algorithm for RNS to binary conversion for arbitrary moduli set (Abstract)

A. Das , Div. of Comput. Technol., Nanyang Technol. Univ., Singapore
pp. 485-488

Algorithm and architecture: for non-linear noise filtering via piecewise linear compression (Abstract)

B.K. Natarajan , Hewlett-Packard Co., Palo Alto, CA, USA
K. Konstantinides , Hewlett-Packard Co., Palo Alto, CA, USA
pp. 489-492

On the limitations of cepstral features in noise (Abstract)

J.S. Masan , Dept. of Electr. Eng., Univ. Coll. of Swansea, UK
J.P. Openshaw , Dept. of Electr. Eng., Univ. Coll. of Swansea, UK
pp. 49-52

A 'Jacobi' signal processing unit for time-adaptive SVD (Abstract)

G.J. Hekstra , Dept. of Electr. Eng., Delft Univ. of Technol., Netherlands
E.D. Deprettere , Dept. of Electr. Eng., Delft Univ. of Technol., Netherlands
H.W. van Dijk , Dept. of Electr. Eng., Delft Univ. of Technol., Netherlands
pp. 493-496

Design of high throughput, low latency and low cost structures for linear systems (Abstract)

M. Potkonjak , Comput. & Commun. Res. Lab., NEC USA, Princeton, NJ, USA
M.B. Srivastava , Dept. of Electr. Eng., Delft Univ. of Technol., Netherlands
pp. 497-500

A stochastic language model for speech recognition integrating local and global constraints (Abstract)

R. Isotani , ATR Interpreting Telcommun Res. Labs., Kyoto, Japan
S. Matsunaga , ATR Interpreting Telcommun Res. Labs., Kyoto, Japan
pp. 5-8

A novel VLSI array design for the discrete Hartley transform using cyclic convolution (Abstract)

Chi-Min Liu , ATR Interpreting Telcommun Res. Labs., Kyoto, Japan
Chein-Wei Jen , Dept. of Electr. Eng., Delft Univ. of Technol., Netherlands
Jiun-In Guo , Comput. & Commun. Res. Labs., Ind. Technol. Res. Inst., Hsinchu, Taiwan
pp. 501-504

Using preliminary decisions to reduce complexity in adaptive equalizers (Abstract)

P.M.S. Burt , Lab. of Commun. & Signals, Sao Paulo Univ., Brazil
pp. 505-508

Optimal VLSI architecture for distributed arithmetic-based algorithms (Abstract)

K. Nourji , Telecom Paris, Ecole Nat. Superieure des Telecommun., Paris, France
N. Demassieux , Telecom Paris, Ecole Nat. Superieure des Telecommun., Paris, France
pp. 509-512

An analysis of FPGA-based custom computers for DSP applications (Abstract)

J.C. Mudge , CSIRO/Flinders Joint Res. Centre in Inf. Technol., Flinders Univ., Adelaide, SA, Australia
N.W. Bergmann , CSIRO/Flinders Joint Res. Centre in Inf. Technol., Flinders Univ., Adelaide, SA, Australia
pp. 513-516

A multi-channel decimator for a tri-level delta-sigma modulator (Abstract)

S. Bernadas , Crystal Semicond. Corp., Austin, TX, USA
C. Thompson , Crystal Semicond. Corp., Austin, TX, USA
pp. 517-519

Square-root, reciprocal, sine/cosine, arctangent cell for signal and image processing (Abstract)

Lei Lin , Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA
V.K. Jain , Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA
pp. 521-524

A self-structuring algorithm for artificial neural networks (Abstract)

A.D.M. Garvin , Dept. of Eng., Cambridge Univ., UK
pp. 525-528

On the design of nonlinear speech predictors with recurrent nets (Abstract)

Lizhong Wu , Dept. of Comput. Sci. & Technol., Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
M. Niranjan , Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA
pp. 529-532

A family of MLP based nonlinear spectral estimators for noise reduction (Abstract)

Fei Xie , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
D. Van Compernolle , ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
pp. 53-56

Noise reduction in state space using the focused gamma neural network (Abstract)

Jyh-Ming Kuo , Comput. NeuroEng. Lab., Florida Univ., Gainesville, FL, USA
J.C. Principe , Comput. NeuroEng. Lab., Florida Univ., Gainesville, FL, USA
pp. 533-536

Design of neural estimators for multisensors: second order backpropagation, initialization and generalization (Abstract)

H. Clergeot , LESiR-ENS Cachan, France
P. Hirschauer , LESiR-ENS Cachan, France
P. Larzabal , LESiR-ENS Cachan, France
pp. 537-540

An invariance property of neural networks (Abstract)

H. Gish , BBN Syst. & Technol. Corp., Cambridge, MA, USA
Manhung Siu , BBN Syst. & Technol. Corp., Cambridge, MA, USA
pp. 541-544

A constrained neural network with complex activation function: application to time-frequency analysis (Abstract)

M. Ibn Kahla , ENSEEIHT, Toulouse, France
F. Castanie , ENSEEIHT, Toulouse, France
S. Puechmorel , ENSEEIHT, Toulouse, France
pp. 545-548

The conditional expectation via a general class of nonlinear networks (Abstract)

J.A. Cadzow , Dept. of Electr. Eng., Vanderbilt Univ., Nashville, TN, USA
Mang Zhu , Dept. of Electr. Eng., Vanderbilt Univ., Nashville, TN, USA
pp. 549-552

Bimodal recognition experiments with recurrent neural networks (Abstract)

K. Vagges , Centro di Studio per le Ricerche di Fonetica, CNR, Padova, Italy
G.A. Mian , Inst. for Integrated Syst. in Signal Process., Tech. Hochschule Aachen, Germany
P. Cosi , Centro di Studio per le Ricerche di Fonetica, CNR, Padova, Italy
E. Magno Caldognetto , Centro di Studio per le Ricerche di Fonetica, CNR, Padova, Italy
M. Contolini , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
pp. 553-556

A new competitive learning algorithm for vector quantization (Abstract)

Zhenya Ile , Dept. of Radio Eng., Southeast Univ., Nanjing, China
Ce Zhu , Dept. of Radio Eng., Southeast Univ., Nanjing, China
Lihua Li , Dept. of Radio Eng., Southeast Univ., Nanjing, China
Jun Wang , Dept. of Radio Eng., Southeast Univ., Nanjing, China
pp. 557-560

The design of neural network configuration for object recognition (Abstract)

A. Pleasants , Dept. of Electr. & Electron. Eng., Victoria Univ. of Technol., Melbourne, Vic., Australia
P. Im , Dept. of Electr. & Electron. Eng., Victoria Univ. of Technol., Melbourne, Vic., Australia
B. Qiu , Dept. of Electr. & Electron. Eng., Victoria Univ. of Technol., Melbourne, Vic., Australia
pp. 561-564

M-lattice: a novel non-linear dynamical system and its application to halftoning (Abstract)

A. Sherstinsky , Media Lab., MIT, Cambridge, MA, USA
R.W. Picard , Media Lab., MIT, Cambridge, MA, USA
pp. 565-568

A multiresolution probabilistic neural network for image segmentation (Abstract)

S. Kollias , Div. of Comput. Sci., Nat. Tech. Univ. of Athens, Greece
D. Kalogeras , Div. of Comput. Sci., Nat. Tech. Univ. of Athens, Greece
pp. 569-572

Markov model based noise modeling and its application to noisy speech recognition using dynamical features of speech (Abstract)

K. Shirai , Dept. of Electr. Eng., Waseda Univ., Tokyo, Japan
T. Kobayashi , Dept. of Electr. Eng., Waseda Univ., Tokyo, Japan
R. Mine , Dept. of Electr. Eng., Waseda Univ., Tokyo, Japan
pp. 57-60

Echocardiogram structure and tissue classification using hierarchical fuzzy neural networks (Abstract)

A. DeMaria , Dept. of Radio Eng., Southeast Univ., Nanjing, China
T. Pollard , ORINCON Corp., San Diego, CA, USA
T. Brotherton , ORINCON Corp., San Diego, CA, USA
P. Simpson , ORINCON Corp., San Diego, CA, USA
pp. 573-576

A simulation environment for very large neural networks (Abstract)

M. Cavaiuolo , Inf. Technol. Div., Defence Sci. & Technol. Organ., Salisbury, SA, Australia
A. Yakovleff , Inf. Technol. Div., Defence Sci. & Technol. Organ., Salisbury, SA, Australia
pp. 577-580

Approach of using a density equalizing function to self-organizing learning for solving travelling salesman problem (Abstract)

Wan-Chi Siu , Dept. of Electron. Eng., Hong Kong Polytech., Kowloon, Hong Kong
C.S.-T. Choy , Dept. of Electron. Eng., Hong Kong Polytech., Kowloon, Hong Kong
pp. 581-584

A new cascaded projection pursuit network for nonlinear regression (Abstract)

I-Chang Jou , ORINCON Corp., San Diego, CA, USA
Jenq-Neng Hwang , Dept. of Electron. Eng., Hong Kong Polytech., Kowloon, Hong Kong
Shih-Shien You , Telecommun. Labs., Minist. of Transp. & Commun., Chung-Li, Taiwan
Shyh-Rong Lay , Dept. of Radio Eng., Southeast Univ., Nanjing, China
pp. 585-588

Neural receiver for CPM signals (Abstract)

P. Bollini , Dipartimento di Ingegneria Elettron., Firenze Univ., Italy
G. Mangani , Dept. of Radio Eng., Southeast Univ., Nanjing, China
G. Castellini , Dept. of Electron. Eng., Hong Kong Polytech., Kowloon, Hong Kong
E. Del Re , ORINCON Corp., San Diego, CA, USA
L. Pierucci , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
pp. 589-592

Application of neural networks to detecting misfire in automotive engines (Abstract)

Jaehong Park , Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
W.B. Ribbens , Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
Daeeun Kim , Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
pp. 593-596

Optimal, matching-score network for pattern classification (Abstract)

A. Luk , Dept. of Electron. Eng., City Polytech. of Hong Kong, Kowloon, Hong Kong
Wai-Fung Leung , Dept. of Electron. Eng., City Polytech. of Hong Kong, Kowloon, Hong Kong
pp. 597-600

Multiple neural networks using the reduced input dimension (Abstract)

Jongwan Kim , Dept. of Comput. Eng., Seoul Nat. Univ., South Korea
Jesung Ahn , Dept. of Comput. Eng., Seoul Nat. Univ., South Korea
Jesung Ahn , Dept. of Comput. Eng., Seoul Nat. Univ., South Korea
Heeyeung Hwang , Dept. of Radio Eng., Southeast Univ., Nanjing, China
Seongwon Cho , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
pp. 601-604

On-line handwritten character recognition using parallel neural networks (Abstract)

E.J. Bellegarda , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
J.R. Bellegarda , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
J.H. Kim , Dept. of Comput. Eng., Seoul Nat. Univ., South Korea
pp. 605-608

Invariant property of spatio-temporal feature maps using gated neuronal architecture (Abstract)

M. Palaniswani , Sch. of Electr. Eng. & Comput. Sci., Melbourne Univ., Parkville, Vic., Australia
V. Chandrasekaran , Sch. of Electr. Eng. & Comput. Sci., Melbourne Univ., Parkville, Vic., Australia
T.M. Caelli , Sch. of Electr. Eng. & Comput. Sci., Melbourne Univ., Parkville, Vic., Australia
pp. 609-612

Environment normalization for robust speech recognition using direct cepstral comparison (Abstract)

P.J. Moreno , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
Fu-Hua Liu , 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
A. Acero , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 61-64

A new composite feature vector for Arabic handwritten signature recognition (Abstract)

G.A. Auda , Dept. of Comput. Eng., Cairo Univ., Giza, Egypt
A.M. Darwish , Dept. of Comput. Eng., Cairo Univ., Giza, Egypt
pp. 613-616

On two-pattern classification and feature selection using neural networks (Abstract)

G.A. Auda , Univ. Estadual de Campinas, Sao Paulo, Brazil
pp. 617-620

Using artificial neural networks to improve the mechanical signature analysis test (Abstract)

T. Bussert , Dept. of Comput. Eng., Cairo Univ., Giza, Egypt
V. DeBrunner , Dept. of Electr. Eng., Oklahoma Univ., Norman, OK, USA
pp. 621-624

Transformation of optimized prototypes for handwritten digit recognition (Abstract)

Hong Yan , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
pp. 625-628

Incremental learning using the time delay neural network (Abstract)

Hong Yan , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 629-632

A connectionist recognizer for on-line cursive handwriting recognition (Abstract)

U. Bodenhausen , Dept. of Comput. Sci., Karlsruhe Univ., Germany
S. Manke , Dept. of Comput. Sci., Karlsruhe Univ., Germany
pp. 633-636

On-line cursive script recognition using time delay neural networks and hidden Markov models (Abstract)

M. Schenkel , Swiss Federal Inst. of Technol., Zurich, Switzerland
D. Henderson , Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA
I. Guyon , Dept. of Comput. Sci., Karlsruhe Univ., Germany
pp. 637-640

Performance of radar target recognition schemes using neural networks-a comparative study (Abstract)

D. Nandagopal , Guided Weapons Div., Defence Sci. & Technol. Organ., Salisbury, SA, Australia
P. Lozo , Guided Weapons Div., Defence Sci. & Technol. Organ., Salisbury, SA, Australia
N.M. Martin , Guided Weapons Div., Defence Sci. & Technol. Organ., Salisbury, SA, Australia
R.P. Johnson , Guided Weapons Div., Defence Sci. & Technol. Organ., Salisbury, SA, Australia
M. Palaniswami , Dept. de Senales, Sistemas y Radiocomunicaciones, Univ. Politecnica de Madrid, Spain
pp. 641-644

Isolated word recognition using a hybrid neural network (Abstract)

B. Azimisadjadi , Electron. Res. Center, Sharif Univ. of Technol., Tehran, Iran
S.B. Zahirazami , Electron. Res. Center, Sharif Univ. of Technol., Tehran, Iran
V. Tabarabaee , Electron. Res. Center, Sharif Univ. of Technol., Tehran, Iran
C. Lucas , Guided Weapons Div., Defence Sci. & Technol. Organ., Salisbury, SA, Australia
pp. 649-652

Noisy speech recognition using cepstral-time features and spectral-time filters (Abstract)

B.P. Milner , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
J.J. Humphries , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
S.V. Vaseghi , Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
pp. 65-68

Application of a generalized probabilistic descent method to recurrent neural network based speech recognition (Abstract)

Sin-Horng Chen , Nat. Chiao Tung Univ., Hsinchu, Taiwan
Yuan-Fu Liao , Nat. Chiao Tung Univ., Hsinchu, Taiwan
Wen-Yuan Chen , Nat. Chiao Tung Univ., Hsinchu, Taiwan
pp. 653-656

Hybrid model decomposition of speech and noise in a radial basis function neural model framework (Abstract)

H.B.D. Sorensen , Dept. of Electron. & Electr. Eng., Eng. Acad. of Denmark, Lyngby, Denmark
U. Hartmann , Nat. Chiao Tung Univ., Hsinchu, Taiwan
pp. 657-660

A neural architecture for hierarchical clustering (Abstract)

R.E. Bogner , Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
M.L. Southcott , Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
J. Zhu , Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
A. Bouzerdoum , Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
pp. 661-664

Vowel classification using a neural predictive HMM: a discriminative training approach (Abstract)

K. Hassanein , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
M.I. Elmasry , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
L. Deng , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
pp. 665-668

"Eigenlips" for robust speech recognition (Abstract)

Y. Konig , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
C. Bregler , Int. Comput. Sci. Inst., Berkeley, CA, USA
pp. 669-672

Incorporating linguistic features in a hybrid HMM/MLP speech recognizer (Abstract)

M. Cohen , Speech Res. & Technol. Program, SRI Int., Menlo Park, CA, USA
I. Arima , Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
H. Franco , Speech Res. & Technol. Program, SRI Int., Menlo Park, CA, USA
V. Abrash , Speech Res. & Technol. Program, SRI Int., Menlo Park, CA, USA
pp. 673-676

A new model-discriminant training algorithm for hybrid NN-HMM systems (Abstract)

G. Ruske , Lehrstuhl fur Datenverarbeitung, Munchen Univ., Germany
P. Caspary , Lehrstuhl fur Datenverarbeitung, Munchen Univ., Germany
W. Reichl , Lehrstuhl fur Datenverarbeitung, Munchen Univ., Germany
pp. 677-680

Combining stochastic trajectory model and discriminative feature in speech recognizer (Abstract)

H. Leich , T.C.T.S., Fac. Polytech. de Mons, Belgium
Jun He , T.C.T.S., Fac. Polytech. de Mons, Belgium
pp. 681-684

Noise immunization using neural net for speech recognition (Abstract)

R. Sankar , Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA
S. Patravali , Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA
pp. 685-688

Speech recognition in noisy car environment based on OSALPC representation and robust similarity measuring techniques (Abstract)

J. Hernando , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
C. Nadeu , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
pp. 69-72

Steady-state performance limitations of full-band acoustic echo cancellers (Abstract)

R. Goubran , Dept. of Signal Theor. & Commun., Univ. Politecnica de Catalunya, Barcelona, Spain
M.E. Knappe , Bell-Northern Res., Ottawa, Ont., Canada
pp. 73-76

Auditory model inversion for sound separation (Abstract)

R.E. Lyon , Apple Comput. Inc., Cupertino, CA, USA
D. Naar , Apple Comput. Inc., Cupertino, CA, USA
M. Slaney , Apple Comput. Inc., Cupertino, CA, USA
pp. 77-80

Speech parameter extraction in noisy environment using a masking model (Abstract)

M. Iwata , Dept. of Electr. Eng. & Comput. Sci., Kumamoto Univ., Japan
T. Usagawa , Dept. of Electr. Eng. & Comput. Sci., Kumamoto Univ., Japan
M. Ebata , Dept. of Electr. Eng. & Comput. Sci., Kumamoto Univ., Japan
pp. 81-84

Non-linear regression based feature extraction for connected-word recognition in noise (Abstract)

F. Seide , Telecommun. Group, Tech. Univ. Hamburg-Harburg, Germany
A. Mertins , Telecommun. Group, Tech. Univ. Hamburg-Harburg, Germany
pp. 85-88

A hierarchical LPNN network for noise reduction and noise degraded speech recognition (Abstract)

Yuqing Gao , Apple-ISS Res. Center, Inst. of Syst. Sci., Singapore
J.-P. Haton , Apple-ISS Res. Center, Inst. of Syst. Sci., Singapore
pp. 89-92

Improving sentence recognition in stochastic context-free grammars (Abstract)

J.M.N. Leitao , Centro de Analise e Processamento de Sinais, Inst. Superior Tecnico, Lisbon, Portugal
A.L.N. Fred , Centro de Analise e Processamento de Sinais, Inst. Superior Tecnico, Lisbon, Portugal
pp. 9-II12

Implementation and performance of an 8-kbit/s conjugate structure CELP speech coder (Abstract)

S. Hayashi , NTT Human Interface Labs., Tokyo, Japan
A. Kataoka , NTT Human Interface Labs., Tokyo, Japan
T. Moriya , NTT Human Interface Labs., Tokyo, Japan
pp. 93-96

8 kbit/s ACELP coding of speech with 10 ms speech-frame: a candidate for CCITT standardization (Abstract)

J.-P. Adoul , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
C. Laflamme , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
R. Salami , Dept. of Electr. Eng., Sherbrooke Univ., Que., Canada
pp. 97-100
92 ms
(Ver )