The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (2000)
Istanbul, Turkey
June 5, 2000 to June 9, 2000
ISBN: 0-7803-6293-4
TABLE OF CONTENTS

Author Index (Abstract)

pp. 1241-1251

Efficient ML training of CDHMM parameters based on prior evolution, posterior intervention and feedback (Abstract)

Qiang Hue , Dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., China
pp. II1001-II1004

Asynchronous-transition HMM (Abstract)

S. Matsuda , Japan Adv. Inst. of Sci. & Technol., Ishikawa, Japan
pp. II1005-II1008

Factored sparse inverse covariance matrices (Abstract)

J.A. Bilmes , Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
pp. II1009-II1012

Sub-state tying in tied mixture hidden Markov models (Abstract)

Liang Gu , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
pp. II1013-II1016

Unified frame and segment based models for automatic speech recognition (Abstract)

Hsiao-Wuen Hon , Speech Technol. Group, Microsoft Res., Redmond, WA, USA
pp. II1017-II1020

Use of higher level linguistic structure in acoustic modeling for speech recognition (Abstract)

I. Shafran , Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
pp. II1021-II1024

Improving the performance of a small microphone array at low frequencies using critical band and LPC codebooks (Abstract)

Yuchang Cao , Sch. of Electron. & Sci. Eng., Queensland Univ. of Technol., Brisbane, Qld., Australia
pp. II1033-II1036

Speech dereverberation and noise reduction with a combined microphone array approach (Abstract)

J. Gonzalez-Rodriguez , Speech & Signal Process. Group, Univ. Politecnica de Madrid, Spain
pp. II1037-II1040

Exploring permutation inconsistency in blind separation of speech signals in a reverberant environment (Abstract)

M.Z. Ikram , Center for Signal & Image Process., Georgia Inst. of Technol., Atlanta, GA, USA
pp. II1041-II1044

Intelligibility assessment of a multi-band speech enhancement scheme (Abstract)

A. Hussain , Dept. of Appl. Comput., Dundee Univ., UK
pp. II1045-II1048

Localization of multiple sound sources based on a CSP analysis with a microphone array (Abstract)

T. Nishiura , Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan
pp. II1053-II1056

Automatic enhancement of speech intelligibility (Abstract)

V. Colotte , LORIA, Vandoeuvre-les-Nancy, France
pp. II1057-II1060

Combined acoustic echo and noise reduction using GSVD-based optimal filtering (Abstract)

S. Doclo , Dept. of Electr. Eng., Katholieke Univ., Leuven, Belgium
pp. II1061-II1064

A proposed likelihood transformation for speaker verification (Abstract)

D. Tran , Sch. of Comput., Canberra Univ., ACT, Australia
pp. II1069-II1072

The use of sub-band cepstrum in speaker verification (Abstract)

P. Sivakumaran , Hertfordshire Univ., Hatfield, UK
pp. II1073-II1076

Generation of optimum signature base sequences for speech signals (Abstract)

B.S. Yarman , Dept. of Electron. Eng., Isik Univ., Maslak-Istanbul, Turkey
pp. II1077-II1080

Effective speaker adaptations for speaker verification (Abstract)

Sungjoo Ahn , Dept. of Electron. Eng., Korea Univ., Seoul, South Korea
pp. II1081-II1084

GSM speech coding and speaker recognition (Abstract)

L. Besacier , Inst. of Microtechnol., Neuchatel Univ., Switzerland
pp. II1085-II1088

User validation for mobile telephones (Abstract)

M.J. Carey , Ensigma Ltd., Chepstow, UK
pp. II1093-II1096

Speaker verification: minimizing the channel effects using autoassociative neural network models (Abstract)

S.P. Kishore , Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., Madras, India
pp. II1101-II1104

LDA derived cepstral trajectory filters in adverse environmental conditions (Abstract)

M. Lieb , Philips GmbH Forschungslab., Aachen, Germany
pp. II1105-II1108

Maximum likelihood joint estimation of channel and noise for robust speech recognition (Abstract)

Yunxin Zhao , Dept. of Comput. Eng. & Comput. Sci., Missouri Univ., Columbia, MO, USA
pp. II1109-II1112

PCA-PMC: a novel use of a priori knowledge for fast parallel model combination (Abstract)

R. Sarikaya , Robust Speech Process. Lab., Colorado Univ., Boulder, CO, USA
pp. II1113-II1116

Asynchrony in multi-band speech recognition (Abstract)

C. Cerisara , LORIA, Henri Poincare Univ., Vandoeuvre-les-Nancy, France
pp. II1121-II1124

Residual noise compensation for robust speech recognition in nonstationary noise (Abstract)

Kaisheng Yao , Dept. of Electr. & Electron. Eng., Hong Kong Univ. of Sci. & Technol., Clear Water Bay, China
pp. II1125-II1128

Maximum likelihood discriminant feature spaces (Abstract)

G. Saon , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. II1129-II1132

Blind speech separation of moving speakers in real reverberant environments (Abstract)

A. Koutvas , Dept. of Electr. & Comput. Eng., Patras Univ., Greece
pp. II1133-II1136

Mixed excitation linear prediction coding of wideband speech at 8 kbps (Abstract)

Weiran Lin , Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
pp. II1137-II1140

High quality embedded wideband speech coding using an inherently layered coding paradigm (Abstract)

S.A. Ramprashad , Lucent Technol. Bell Labs., Murray Hill, NJ, USA
pp. II1145-II1148

A 16-kbit/s bandwidth scalable audio coder based on the G.729 standard (Abstract)

K. Koishida , Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
pp. II1149-II1152

A 14 kb/s wideband speech coder with a parametric highband model (Abstract)

A. McCree , DSP Solutions R&D Center, Texas Instrum. Inc., Dallas, TX, USA
pp. II1153-II1156

Hi-BIN: an alternative approach to wideband speech coding (Abstract)

R. Taori , Digital Signal Process. Group, Philips Res. Lab., Eindhoven, Netherlands
pp. II1157-II1160

A high-fidelity speech and audio codec with low delay and low complexity (Abstract)

Juin-Hwey Chen , Speech Technol. Group, Lucent InterNetworking Syst., Red Bank, NJ, USA
pp. II1161-II1164

Stochastic-algebraic wideband LSF quantization (Abstract)

S. Ragot , Dept. of Electr. & Comput. Eng., Sherbrooke Univ., Que., Canada
pp. II1169-II1172

A silence compression algorithm for multi-rate/dual-bandwidth MPEG-4 CELP standard (Abstract)

M. Serizawa , C&C Media Res. Labs., NEC Corp., Kawasaki, Japan
pp. II1173-II1176

Speaker identification in mismatch training and testing conditions (Abstract)

C. Alonso-Martinez , Univ. Politecnica de Catalunya, Barcelona, Spain
pp. II1181-II1184

An iterative technique for training speaker verification systems (Abstract)

W.M. Campbell , Human Interface Lab., Motorola Inc., Tempe, AZ, USA
pp. II1185-II1188

Search-space reduction for fast, optimal HMM decoding in speaker verification (Abstract)

Qi Li , Multimedia Commun. Res. Lab., Lucent Technol. Bell Labs., Murray Hill, NJ, USA
pp. II1189-II1192

A two-stage scoring method combining world and cohort models for speaker verification (Abstract)

W.D. Zhang , Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., China
pp. II1193-II1196

Evolutive HMM for multi-speaker tracking system (Abstract)

S. Meignier , LIA/CERI, Avignon Univ., France
pp. II1201-II1204

A novel rank-based classifier combination scheme for speaker identification (Abstract)

H. Altincay , Dept. of Electr. & Electron. Eng., Middle East Tech. Univ., Ankara, Turkey
pp. II1209-II1212

Probabilistic simulation of human-machine dialogues (Abstract)

K. Scheffler , Dept. of Eng., Cambridge Univ., UK
pp. II1217-II1220

Fundamental performance analysis for spoken dialogue systems based on a quantitative simulation approach (Abstract)

Bor-Shen Lin , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
pp. II1221-II1224

Parser adaptation via Householder transform (Abstract)

Xiaoqiang Luo , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. II1225-II1228

CU FOREX: a bilingual spoken dialog system for foreign exchange enquiries (Abstract)

H.M. Meng , Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Shatin, China
pp. II1229-II1232

Fast reinforcement learning of dialog strategies (Abstract)

D. Goddeau , Cambridge Res. Lab., Compaq Comput. Corp., MA, USA
pp. II1233-II1236

Confidence measures for dialogue management in the CU Communicator system (Abstract)

R. San-Segundo , Center for Spoken Language Understanding, Colorado Univ., Boulder, CO, USA
pp. II1237-II1240

Time-frequency signal decomposition using energy mixture models (Abstract)

M. Coates , Dept. of Electr. & Comput. Sci., Rice Univ., Houston, TX, USA
pp. II633-II636

Optimal estimation of non-stationary phase and amplitude processes (Abstract)

C. Andrieu , Dept. of Eng., Cambridge Univ., UK
pp. II637-II640

Improved frequency marginal estimates for time-frequency distributions (Abstract)

S. Aviyente , Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
pp. II641-II644

SNR analysis of time-frequency distributions (Abstract)

Weifeng Mu , Dept. of Electr. & Comput. Eng., Villanova Univ., PA, USA
pp. II645-II648

Data-driven time-frequency classification techniques applied to tool-wear monitoring (Abstract)

B.W. Gillespie , Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
pp. II649-II652

A fast Gabor spectrogram (Abstract)

Shie Qian , DSP Group, Nat. Instrum. Corp., Austin, TX, USA
pp. II653-II656

Adaptive instantaneous frequency estimation of multi-component FM signals (Abstract)

Z.M. Hussain , Signal Processing Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia
pp. II657-II660

IF estimation of linear FM signals corrupted by multiplicative and additive noise: a time-frequency approach (Abstract)

B. Barkat , Signal Processing Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia
pp. II661-II664

Nontrivial analytic signals with positive instantaneous frequency and band-limited amplitude (Abstract)

M.I. Doroslovacki , Dept. of Electr. & Comput. Eng., George Washington Univ., Washington, DC, USA
pp. II669-II672

Enhancing weak signal components in time-frequency distributions by wavelet pre-processing (Abstract)

Mingui Sun , Dept. of Neurosurgery & Electr. Eng., Pittsburgh Univ., PA, USA
pp. II673-II676

A new method for estimating the instantaneous frequency based on maximum likelihood (Abstract)

F.A.C. de Bastos , Inst. Militar de Engenharia, Rio Janeiro, Brazil
pp. II677-II680

Hybrid linear/quadratic time-frequency attributes (Abstract)

R. Baraniuk , Dept. of Electr. & Comput. Eng., Rice Univ., Houston, TX, USA
pp. II681-II684

Wavelet packets based features selection for voiceless plosives classification (Abstract)

E. Lukasik , Inst. of Comput. Sci., Poznan Univ. of Technol., Poland
pp. II689-II692

A high resolution time frequency representation with significantly reduced cross-terms (Abstract)

A.K. Ozdemir , Dept. of Electr. & Electron. Eng., Bilkent Univ., Ankara, Turkey
pp. II693-II696

An efficient algorithm to extract components of a composite signal (Abstract)

O. Arikan , Dept. of Electr. & Electron. Eng., Bilkent Univ., Ankara, Turkey
pp. II697-II700

Markov chain Monte Carlo data association for target tracking (Abstract)

N. Bergman , Dept. of Electr. Eng., Linkoping Univ., Sweden
pp. II705-II708

A new approach to period estimation (Abstract)

D.D. Muresan , Dept. of Electr. Eng., Cornell Univ., Ithaca, NY, USA
pp. II709-II712

H/sub /spl infin// smoothing (Abstract)

E. Blanco , Univ. Claude Bernard, Villeurbanne, France
pp. II713-II716

A modified Baum-Welch algorithm for hidden Markov models with multiple observation spaces (Abstract)

P.M. Baggenstoss , Naval Underwater Warfare Center, Newport, RI, USA
pp. II717-II720

Least squares deconvolution in wavelet domain for 1/f driven LTI systems (Abstract)

M.I. Izzetoglu , Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
pp. II721-II724

Bayesian detection of transient signals in colored noise (Abstract)

Yufei Huang , Dept. of Electr. & Comput. Eng., State Univ. of New York, Stony Brook, NY, USA
pp. II725-II728

Detection of frequency modulated signals in Rayleigh fading channels based on time-frequency distributions (Abstract)

T.L. Nguyen , Signal Processing Res. Centre, Queensland Univ. of Technol., Brisbane, Qld., Australia
pp. II729-II732

Detection of signal number based on statistics of maximum likelihood (Abstract)

M. Suzuki , Res. Inst. for Electron. Sci., Hokkaido Univ., Sapporo, Japan
pp. II733-II736

An efficient square-root algorithm for BLAST (Abstract)

B. Hassibi , Lucent Technol. Bell Labs., Murray Hill, NJ, USA
pp. II737-II740

Synthesis of vibrato singing (Abstract)

Y. Meron , Dept. of Inf. & Commun. Eng., Tokyo Univ., Japan
pp. II745-II748

Music summarization using key phrases (Abstract)

B. Logan , Res. Labs., Compaq Comput. Corp., Cambridge, MA, USA
pp. II749-II752

Musical instrument recognition using cepstral coefficients and temporal features (Abstract)

A. Eronen , Signal Process. Lab., Tampere Univ. of Technol., Finland
pp. II753-II756

Sound analysis using MPEG compressed audio (Abstract)

G. Tzanetakis , Dept. of Comput. Sci., Princeton Univ., NJ, USA
pp. II761-II764

Separation of harmonic sound sources using sinusoidal modeling (Abstract)

T. Virtanen , Signal Process. Lab., Tampere Univ. of Technol., Finland
pp. II765-II768

Model-based sound synthesis of tanbur, a Turkish long-necked lute (Abstract)

C. Erkut , Lab. of Acoust. & Audio Signal Processing, Helsinki Univ. of Technol., Espoo, Finland
pp. II769-II772

Acoustic sound from the electric guitar using DSP techniques (Abstract)

M. Karjalainen , Lab. of Acoust. & Audio Signal Processing, Helsinki Univ. of Technol., Espoo, Finland
pp. II773-II776

Practical and efficient implementation of the Levinson algorithm for multichannel sound reproduction (Abstract)

J.J. Lopez , Dept. de Comunicaciones, Univ. Politecnica de Valencia, Spain
pp. II777-II780

A new robust system for 3D audio using loudspeakers (Abstract)

D.B. Ward , Sch. of Electr. Eng., New South Wales Univ., Kensington, NSW, Australia
pp. II781-II784

Common acoustical-poles/zeros modeling for 3D sound processing (Abstract)

M.C. Chen , Dept. of Commun. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
pp. II785-II788

Study on combining multi-channel echo cancellers with beamformers (Abstract)

M. Kallinger , Dept. of Telecommun., Bremen Univ., Germany
pp. II797-II800

A new adaptive algorithm for stereophonic acoustic echo canceller (Abstract)

Yang-Won Jung , Dept. of Electr. & Comput. Eng., Yonsei Univ., Seoul, South Korea
pp. II801-II804

Nonlinear acoustic echo cancellation with fast converging memoryless preprocessor (Abstract)

A. Stenger , Telecommun. Lab., Erlangen-Nurnberg Univ., Germany
pp. II805-II808

A new sampling of echo paths in North American networks (Abstract)

K.C. Ho , Dept. of Electr. Eng., Missouri Univ., Columbia, MO, USA
pp. II809-II812

Multichannel active noise control algorithms using inverse filters (Abstract)

F.Yu.M. Bouchard , Sch. of Inf. Technol. & Eng., Ottawa Univ., Ont., Canada
pp. II825-II828

Time domain recursive deconvolution in sound reproduction (Abstract)

A. Gonzalez , Dept. de Commun., Univ. Politecnica de Valencia, Spain
pp. II833-II836

Some practical insights in multichannel active noise control equalization (Abstract)

M. De Diego , Dept. of Comunicaciones, Univ. Politecnica de Valencia, Spain
pp. II837-II840

A preconditioned LMS algorithm for rapid adaptation of feedforward controllers (Abstract)

S.J. Elliott , Inst. of Sound & Vibration Res., Southampton Univ., UK
pp. II845-II848

Simulation of hearing impairment based on the Fourier time transformation (Abstract)

J. Chalupper , Inst. for Human-Machine Commun., Tech. Univ. of Munich, Germany
pp. II857-II860

Binaural sound localization in an artificial neural network (Abstract)

C. Schauer , Dept. of Neuroinf., Ilmenau Tech. Univ., Germany
pp. II865-II868

Bias of feedback cancellation algorithms based on direct closed loop identification (Abstract)

J. Hellgren , Dept. of Neurosci. & Locomotion, Linkoping Univ., Sweden
pp. II869-II872

Multiple frequency harmonics analysis and synthesis of audio signals (Abstract)

A. Jbira , Centre for Commun. Syst. Res., Surrey Univ., Guildford, UK
pp. II873-II876

A 6Kbps to 85Kbps scalable audio coder (Abstract)

T.S. Verma , Lab. of Acoustics & Audio Signal Processing, Helsinki Univ. of Technol., Espoo, Finland
pp. II877-II880

Audio coding using a psychoacoustic pre- and post-filter (Abstract)

B. Edler , Multimedia Commun. Res. Lab., AT&T Bell Labs., Murray Hill, NJ, USA
pp. II881-II884

Lossless coding of MPEG-1 Layer III encoded audio streams (Abstract)

F. Golchin , Sch. of Microelectron. Eng., Griffith Univ., Brisbane, Qld., Australia
pp. II885-II888

A design of lossy and lossless scalable audio coding (Abstract)

T. Moriya , NTT LSI Labs., Tokyo, Japan
pp. II889-II892

Perceptual bit allocation for low rate coding of narrowband audio (Abstract)

H. Najafzadeh , Dept. of Electr. & Comput. Eng., McGill Univ., Montreal, Que., Canada
pp. II893-II896

Evaluation of a warped linear predictive coding scheme (Abstract)

A. Harma , Lab. of Acoustics & Audio Signal Processing, Helsinki Univ. of Technol., Espoo, Finland
pp. II897-II900

Exploiting time and frequency masking in consistent sinusoidal analysis-synthesis (Abstract)

R. Vafin , Dept. of Speech Commun. & Music Acoust., R. Inst. of Technol., Stockholm, Sweden
pp. II901-II904

Frame erasure concealment using sinusoidal analysis-synthesis and its application to MDCT-based codecs (Abstract)

V.N. Parikh , Speech Technol. Group, Lucent InterNetworking Syst., Red Bank, NJ, USA
pp. II905-II908

Passive acoustic source localization for video camera steering (Abstract)

Yiteng Huang , Center for Image & Signal Processing, Georgia Inst. of Technol., Atlanta, GA, USA
pp. II909-II912

Multiband warped filter equalizer design for loudspeaker systems (Abstract)

Wang Peng , Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore
pp. II913-II916

The effect of polarity inversion of speech on human perception and data hiding as an application (Abstract)

S. Sakaguchi , Dept. of Electr. & Electron. Eng., Sophia Univ., Tokyo, Japan
pp. II917-II920

A fast subband room response simulator (Abstract)

F. Jabloun , Electr. & Comput. Eng. Dept., McGill Univ., Montreal, Que., Canada
pp. II925-II928

Concatenating syllables for response generation in spoken language applications (Abstract)

A. Arvaniti , Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Shatin, China
pp. II933-II936

Segment pre-selection in decision-tree based speech synthesis systems (Abstract)

R.E. Donovan , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. II937-II940

Spectral modification for concatenative speech synthesis (Abstract)

J. Wouters , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
pp. II941-II944

Transition-based speech synthesis using neural networks (Abstract)

G. Corrigan , Motorola Labs., Schaumburg, IL, USA
pp. II945-II948

Stochastic modeling of spectral adjustment for high quality pitch modification (Abstract)

A. Kain , Center for Spoken Language Understanding, Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
pp. II949-II952

Voice quality conversion in TD-PSOLA speech synthesis (Abstract)

Xuejing Sun , Dept. of Commun. Sci. & Disorders, Northwestern Univ., Evanston, IL, USA
pp. II953-II956

On the implementation of the harmonic plus noise model for concatenative speech synthesis (Abstract)

Y. Stylianou , SIPS, AT&T Bell Labs., Florham Park, NJ, USA
pp. II957-II960

On-line incremental speaker adaptation with automatic speaker change detection (Abstract)

Zhi-Peng Zhang , Dept. of Comput. Sci., Tokyo Inst. of Technol., Japan
pp. II961-II964

Full covariance modelling and adaptation in sub-bands (Abstract)

B. Doherty , Sch. of Electr. & Electron. Eng., Queen's Univ., Belfast, UK
pp. II969-II972

Hierarchical Bayes approach to adapting delta- and delta-delta cepstra (Abstract)

A.C. Surendran , Lucent Technol. Bell Labs., Murray Hill, NJ, USA
pp. II973-II976

On-line Bayesian speaker adaptation using tree-structured transformation and robust priors (Abstract)

Shaojun Wang , Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana, IL, USA
pp. II977-II980

Speaker adaptation based on combination of MAP estimation and weighted neighbor regression (Abstract)

Lei He , Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
pp. II981-II984

Robust estimation for rapid speaker adaptation using discounted likelihood techniques (Abstract)

A. Gunawardana , Center for Language & Speech Procesing, Johns Hopkins Univ., Baltimore, MD, USA
pp. II985-II988

Fast speaker adaptation of large vocabulary continuous density HMM speech recognizer using a basis transform approach (Abstract)

C. Boulis , Dept. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece
pp. II989-II992

A generalization of the maximum a posteriori training algorithm for mixture priors (Abstract)

E.R. Buhrke , Human Interface lab., Motorola Inc., Naperville, IL, USA
pp. II993-II996

Linear regression under maximum a posteriori criterion with Markov random field prior (Abstract)

Xintian Wu , Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
pp. II997-I1000
93 ms
(Ver )