The Community for Technology Leaders
Acoustics, Speech, and Signal Processing, IEEE International Conference on (1999)
Phoenix, AZ, USA
Mar. 15, 1999 to Mar. 19, 1999
ISBN: 0-7803-5041-3
TABLE OF CONTENTS

Connected digit recognition using short and long duration models (Abstract)

C. Chesta , Dipt. di Autom. e Inf., Politecnico di Torino, Italy
pp. 557-560

Discriminative training via linear programming (Abstract)

K.A. Papineni , IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
pp. 561-564

Efficient speech recognition using subvector quantization and discrete-mixture HMMs (Abstract)

S. Tsakalidis , Dept. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece
pp. 569-572

A unified approach of incorporating general features in decision tree based acoustic modeling (Abstract)

W. Reichl , Lucent Technol., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 573-576

Irrelevant variability normalization in learning HMM state tying from data based on phonetic decision-tree (Abstract)

Qiang Huo , Dept. of Comput. Sci. & Inf. Syst., Hong Kong Univ., Hong Kong
pp. 577-580

On the use of support vector machines for phonetic classification (Abstract)

P. Clarkson , Res. Lab., Compaq Comput. Corp., Cambridge, MA, USA
pp. 585-588

High quality word graphs using forward-backward pruning (Abstract)

A. Sixtus , Luhrstuhl fur Inf., Tech. Hochschule Aachen, Germany
pp. 593-596

Improved spelling recognition using a tree-based fast lexical match (Abstract)

C.D. Mitchell , Lucent Technol., AT&T Bell Labs., Naperville, IL, USA
pp. 597-600

A syllable-synchronous network search algorithm for word decoding in Chinese speech recognition (Abstract)

Fang Zheng , Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
pp. 601-604

A fast, sequential decoding algorithm with application to speaker verification (Abstract)

Qi Li , Multimedia Commun. Res. Lab., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 605-608

Dynamic programming search techniques for across-word modelling in speech recognition (Abstract)

K. Beulen , Lehrstuhl fur Inf., Tech. Hochschule Aachen, Germany
pp. 609-612

Single-tree method for grammar-directed search (Abstract)

L. Nguyen , BBN Technol., GTE Internetworking, Cambridge, MA, USA
pp. 613-616

Selection criteria for hypothesis driven lexical adaptation (Abstract)

P. Geutner , Interactive Syst. Labs., Karlsruhe Univ., Germany
pp. 617-620

Using non-word lexical units in automatic speech understanding (Abstract)

M. Penagarikano , Dept. Electr. y Electron., Pais Vasco Univ., Lejona, Spain
pp. 621-624

Message-driven speech recognition and topic-word extraction (Abstract)

K. Ohtsuki , NTT Human Interface Labs., Kanagawa, Japan
pp. 625-628

PROFER: predictive, robust finite-state parsing for spoken language (Abstract)

E.C. Kaiser , Center for Spoken Language Understanding, Oregon Graduate Inst., Portland, OR, USA
pp. 629-632

Acoustic and syntactical modeling in the ATROS system (Abstract)

D. Llorens , Unitat Predepartmental d'Inf., Univ. Jaume I, Castello, Spain
pp. 641-644

Towards a robust real-time decoder (Abstract)

J. Davenport , BBN Technol., GTE Internetworking, Cambridge, MA, USA
pp. 645-648

A statistical text-to-phone function using ngrams and rules (Abstract)

W.M. Fisher , Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
pp. 649-652

Linguistic mapping in LSF space for low-bit rate coding (Abstract)

J.J. Parry , TITR Whisper Labs., Wollongong Univ., NSW, Australia
pp. 653-656

Predictive multiple-scale lattice VQ for LSF quantization (Abstract)

A. Vasilache , Signal Process. Lab., Tampere Univ. of Technol., Finland
pp. 657-660

A rootfinding algorithm for line spectral frequencies (Abstract)

J. Rothweiler , Sanders, Hudson, NH, USA
pp. 661-664

MVDR based all-pole models for spectral coding of speech (Abstract)

M.N. Murthi , Dept. of Electr. & Comput. Eng., California Univ., San Diego, La Jolla, CA, USA
pp. 669-672

Performance bounds for LPC spectrum quantization (Abstract)

P. Hedelin , Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
pp. 677-680

Channel optimized predictive VQ (Abstract)

J. Linden , Inf. Theory, Chalmers Univ. of Technol., Goteborg, Sweden
pp. 681-684

A more efficient and optimal LLR for decoding and verification (Abstract)

S. Doshita , Human Language Technol. Center, Univ. of Sci. & Technol., Clear Water Bay, Hong Kong
pp. 689-692

Utterance verification using prosodic information for Mandarin telephone speech keyword spotting (Abstract)

Yeou-Jiunn Chen , Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan
pp. 697-700

Advances in confidence measures for large vocabulary (Abstract)

A. Wendemuth , Philips Res. Lab., Aachen, Germany
pp. 705-708

Buried Markov models for speech recognition (Abstract)

J.A. Bilmes , Int. Comput. Sci. Inst., Berkeley, CA, USA
pp. 713-716

Speech recognition experiments using multi-span statistical language models (Abstract)

J.R. Bellegarda , Spoken Language Group, Apple Comput. Inc., Cupertino, CA, USA
pp. 717-720

Spoken language variation over time and state in a natural spoken dialog system (Abstract)

A.L. Gorin , Dept. of Speech Res., AT&T Bell Labs., Florham Park, NJ, USA
pp. 721-724

Using smoothed K-TSS language models in continuous speech recognition (Abstract)

A. Varona , Dept. de Electr. y Electron., Pais Vasco Univ., Bilbao, Spain
pp. 729-732

Interfacing a CDG parser with an HMM word recognizer using word graphs (Abstract)

M.P. Harper , Sch. of Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA
pp. 733-736

Robust dialogue-state dependent language modeling using leaving-one-out (Abstract)

F. Wessel , Lehrstuhl fur Inf., Tech. Hochschule Aachen, Germany
pp. 741-744

On-line algorithms for combining language models (Abstract)

A. Kalai , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
pp. 745-748

Fast speaker adaptation using a priori knowledge (Abstract)

R. Kuhn , Speech Technol. Lab., Panasonic Technol. Inc., Santa Barbara, CA, USA
pp. 749-752

Speaker adaptation using maximum likelihood model interpolation (Abstract)

Zuoying Wang , Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
pp. 753-756

Speaker adaptation with all-pass transforms (Abstract)

J. McDonough , Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA
pp. 757-760

Improved methods for vocal tract normalization (Abstract)

L. Welling , Tech. Hochschule Aachen, Germany
pp. 761-764

Using AR HMM state-dependent filtering for speech enhancement (Abstract)

D. Matrouf , Lab. d'Inf. pour la Mecanique et les Sci. de l'Ingenieur, CNRS, Orsay, France
pp. 785-788

Speech enhancement using voice source models (Abstract)

A. Yasmin , Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
pp. 797-800

Adaptive decorrelation filtering for separation of co-channel speech signals from m>2 sources (Abstract)

Kuan-Chieh Yen , Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana, IL, USA
pp. 801-804

Audio signal noise reduction using multi-resolution sinusoidal modeling (Abstract)

D.V. Anderson , Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 805-808

Background model design for flexible and portable speaker verification systems (Abstract)

O. Siohan , Lucent Technol., AT&T Bell Labs., Murray Hill, NJ, USA
pp. 825-828

Corpora for the evaluation of speaker recognition systems (Abstract)

Qi Li , Dept. of Defense, Ft. Meade, MD, USA
pp. 829-832

An experimental study of speaker verification sensitivity to computer voice-altered imposters (Abstract)

B.L. Pellom , Robust Speech Process. Lab., Duke Univ., Durham, NC, USA
pp. 837-840

A new cohort normalization using local acoustic information for speaker verification (Abstract)

T. Isobe , Lab. for Inf. Technol., NTT Data Corp., Kanagawa, Japan
pp. 841-844

On the use of orthogonal GMM in speaker recognition (Abstract)

L. Liu , Dept. of Speech & Hearing Sci., Arizona State Univ., Tempe, AZ, USA
pp. 845-848

Reusable binary-paired partitioned neural networks for text-independent speaker identification (Abstract)

S.A. Zahorian , Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
pp. 849-852

Implicit decimation for FIR systems and its application to acoustic echo cancellation (Abstract)

W.A. Frank , Mobile Phones Dept., Siemens AG, Munich, Germany
pp. 865-868

A block least squares approach to acoustic echo cancellation (Abstract)

E. Woudenberg , Human Inf. Process. Lab., Adv. Telecommun. Res., Kyoto, Japan
pp. 869-872

A postfilter for echo and noise reduction avoiding the problem of musical tones (Abstract)

S. Gustafsson , Inst. of Commun. Syst. & Data Process., Tech. Hochschule Aachen, Germany
pp. 873-876

Nonlinear acoustic echo cancellation with 2nd order adaptive Volterra filters (Abstract)

A. Stenger , Telecommun. Lab., Erlangen-Nurnberg Univ., Germany
pp. 877-880

On the poor robustness of sound equalization in reverberant environments (Abstract)

B.D. Radlovic , Dept. of Eng., Australian Nat. Univ., Canberra, ACT, Australia
pp. 881-884

On the performance of a local active noise control system (Abstract)

M. de Diego , Dept. of Comunicaciones, Univ. Politecnica de Valencia, Spain
pp. 885-888

On the utilization of overshoot effects in low-delay audio coding (Abstract)

A. Harma , Lab. of Acoust. & Audio Signal Process., Helsinki Univ. of Technol., Espoo, Finland
pp. 893-896

An algorithm for compression of wideband diverse speech and audio signals (Abstract)

T.R. Trinkaus , Center for Signal & Image Process., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 901-904

A new forward masking model and its application to perceptual audio coding (Abstract)

Yuan-Hao Huang , Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
pp. 905-908

Best wavelet-packet bases for audio coding using perceptual and rate-distortion criteria (Abstract)

M. Erne , Signal & Inf. Process. Lab., Fed. Inst. of Technol., Zurich, Switzerland
pp. 909-912

Improving perceptual coding of narrowband audio signals at low rates (Abstract)

H. Najafzadeh-Azghandi , Dept. of Electr. & Comput. Eng., McGill Univ., Montreal, Que., Canada
pp. 913-916

Subband-domain filtering of MPEG audio signals (Abstract)

C.A. Lanciani , Center for Signal & Image Process., Georgia Inst. of Technol., Atlanta, GA, USA
pp. 917-920

Adaptive feedback cancelling in subbands for hearing aids (Abstract)

S. Wyrsch , Inst. for Signal & Inf. Process., Fed. Inst. of Technol., Zurich, Switzerland
pp. 921-924

Bias analysis in continuous adaptation systems for hearing aids (Abstract)

M.G. Siqueira , Dept. of Electr. Eng., California Univ., Los Angeles, CA, USA
pp. 925-928

Multi-pitch and periodicity analysis model for sound separation and auditory scene analysis (Abstract)

M. Karjalainen , Lab. of Acoust. & Audio Signal Process., Helsinki Univ. of Technol., Espoo, Finland
pp. 929-932

'Perfect reconstruction' time-scaling filterbanks (Abstract)

T.F. Quatieri , Lincoln Lab., MIT, Lexington, MA, USA
pp. 945-948

An event-based method for microphone array speech enhancement (Abstract)

M.S. Brandstein , Div. of Eng. & Appl. Sci., Harvard Univ., Cambridge, MA, USA
pp. 953-956

A direct method to computational acoustics (Abstract)

R. Rabenstein , Telecommun. Lab., Erlangen-Nurnberg Univ., Germany
pp. 957-960

Spatial frequency response surfaces: an alternative visualization tool for head-related transfer functions (HRTFs) (Abstract)

C.I. Cheng , Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
pp. 961-964

An adaptable ellipsoidal head model for the interaural time difference (Abstract)

R.O. Duda , Dept. of Electr. Eng., San Jose State Univ., CA, USA
pp. 965-968

Visualizing the performance of large-aperture microphone arrays (Abstract)

H.F. Silverman , Div. of Eng., Brown Univ., Providence, RI, USA
pp. 969-972

Reduction of the dispersion error in the interpolated digital waveguide mesh using frequency warping (Abstract)

L. Savioja , Lab. of Acoust. & Audio Signal Process., Helsinki Univ. of Technol., Espoo, Finland
pp. 973-976

Plucked-string synthesis algorithms with tension modulation nonlinearity (Abstract)

V. Valimaki , Lab. of Acoust. & Audio Signal Process., Helsinki Univ. of Technol., Espoo, Finland
pp. 977-980

Sinusoidal modeling using frame-based perceptually weighted matching pursuits (Abstract)

T.S. Verma , Dept. of Electr. Eng., Stanford Univ., CA, USA
pp. 981-984

A switched parametric and transform audio coder (Abstract)

S.N. Levine , Dept. of Electr. Eng., Stanford Univ., CA, USA
pp. 985-988

Perception-based residual analysis-synthesis system (Abstract)

Y.H. Lam , Dept. of Electron. & Electr. Eng., Strathclyde Univ., Glasgow, UK
pp. 989-992

A fixed-point recursive digital oscillator for additive synthesis of audio (Abstract)

T. Hodes , Comput. Sci. Div., California Univ., Berkeley, CA, USA
pp. 993-996

Frequency recovery of narrow-band speech using adaptive spline neural networks (Abstract)

A. Uncini , Dipt. di Elettronica e Autom., Ancona Univ., Italy
pp. 997-1000

Diphone multi-trajectory subspace models (Abstract)

K. Reinhard , Dept. of Eng., Cambridge Univ., UK
pp. 1001-1004

Speaker recognition with a MLP classifier and LPCC codebook (Abstract)

D. Rodriguez-Porcheron , Univ. Politecnica de Catalunya, Barcelona, Spain
pp. 1005-1008

Using boosting to improve a hybrid HMM/neural network speech recognizer (Abstract)

H. Schwenk , Int. Comput. Sci. Inst., Berkeley, CA, USA
pp. 1009-1012

Oriented soft localized subspace classification (Abstract)

T. Balachander , Dept. of Electr. & Comput. Eng., Cincinnati Univ., OH, USA
pp. 1017-1020

Multi-category classification by kernel based nonlinear subspace method (Abstract)

E. Maeda , NTT Basic Res. Labs., Atsugi, Japan
pp. 1025-1028

Ensemble classification by critic-driven combining (Abstract)

D.J. Miller , Dept. of Electr. Eng., Pennsylvania State Univ., University Park, PA, USA
pp. 1029-1032

Global asymptotic convergence of nonlinear relaxation equations realised through a recurrent perceptron (Abstract)

D.P. Mandic , Dept. of Electr. & Electron. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
pp. 1037-1040

A neural network for data association (Abstract)

M. Winter , CNRS, Sophia-Antipolis, France
pp. 1041-1044

Training MLPs layer-by-layer with the information potential (Abstract)

Dongxin Xu , Comput. NeuroEng. Lab., Florida Univ., Gainesville, FL, USA
pp. 1045-1048

Time series prediction via neural network inversion (Abstract)

Lian Yan , Dept. of Electr. Eng., Pennsylvania State Univ., University Park, PA, USA
pp. 1049-1052

Partial likelihood for estimation of multi-class posterior probabilities (Abstract)

T. Adali , Dept. of Comput. Sci. & Electr. Eng., Maryland Univ., Baltimore, MD, USA
pp. 1053-1056

Sequential Bayesian computation of logistic regression models (Abstract)

M. Niranjan , Dept. of Eng., Cambridge Univ., UK
pp. 1065-1068

Blind separation of temporomandibular joint sound signals (Abstract)

Y. Guo , Sch. of Mech. & Production Eng., Nanyang Technol. Inst., Singapore
pp. 1069-1072

Generalized anti-Hebbian learning for source separation (Abstract)

Hsiao-Chun Wu , Dept. of Electr. & Comput. Eng., Florida Univ., Gainesville, FL, USA
pp. 1073-1076

Sparse basis selection, ICA, and majorization: towards a unified perspective (Abstract)

K. Kreutz-Delgado , Dept. of Electr. & Comput. Eng., California Univ., San Diego, La Jolla, CA, USA
pp. 1081-1084

Two spatio-temporal decorrelation learning algorithms and their application to multichannel blind deconvolution (Abstract)

S. Choi , Sch. of Electr. & Electron. Eng., Chungbuk Nat. Univ., South Korea
pp. 1085-1088

Adaptive paraunitary filter banks for principal and minor subspace analysis (Abstract)

S.C. Douglas , Dept. of Electr. Eng., Southern Methodist Univ., Dallas, TX, USA
pp. 1089-1092

Experiments in topic indexing of broadcast news using neural networks (Abstract)

C. Neukirchen , Dept. of Comput. Sci., Gerhard-Mercator-Univ., Duisberg, Germany
pp. 1093-1096

Texture edge detection by feature encoding and predictive model (Abstract)

Jyh-Charn Liu , Dept. of Comput. Sci., Texas A&M Univ., College Station, TX, USA
pp. 1105-1108

Edge characterization using a model-based neural network (Abstract)

Hau-San Wong , Dept. of Electr. Eng., Sydney Univ., NSW, Australia
pp. 1109-1112

License-plate localization by using vector quantization (Abstract)

S. Rovetta , Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
pp. 1113-1116

Neural network based person identification using EEG features (Abstract)

M. Poulos , Dept. of Inf., Univ. of Piraeus, Greece
pp. 1117-1120

Sonar discrimination of cylinders from different angles using neural networks (Abstract)

L.N. Andersen , Dept. of Math. Modelling, Tech. Univ., Lyngby, Denmark
pp. 1121-1124

A neural network based transcoder for MPEG2 video compression (Abstract)

H.C. Fu , Dept. of Comput. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
pp. 1125-1128

Author Index (Abstract)

pp. 1129-1141
90 ms
(Ver 3.1 (10032016))