Area 3: Speech Processing (SP)

Session:            SP-L2
Time: 15:30 - 17:30, Tuesday, June 6, 2000
Location: Sadirvan A - Hilton Hotel
Title: ACOUSTIC MODEL ADAPTATION FOR ASR
Chair: Ananth Sankar, Nuance, USA
1. Paper ID: 838 ON-LINE INCREMENTAL SPEAKER ADAPTATION WITH AUTOMATIC SPEAKER CHANGE DETECTION, Z.-P. Zhang, S. Furui, Tokyo Institute of Technology, Japan, K. Ohtsuki, NTT, Japan.
2. Paper ID: 1277 JOINT MAXIMUM A POSTERIORI ESTIMATION OF TRANSFORMATION AND HIDDEN MARKOV MODEL PARAMETERS, O. Siohan, Lucent Technologies, USA, C. Chesta, Politecnico di Torino, Italy, C.-H. Lee, Lucent Technologies, USA.
3. Paper ID: 2235 FULL COVARIANCE MODELLING AND ADAPTATION IN SUB-BANDS, B. Doherty, S. Vaseghi, P. McCourt, The Queen's University of Belfast, United Kingdom.
4. Paper ID: 2826 HIERARCHICAL BAYES APPROACH TO ADAPTING DELTA- AND DELTA-DELTA CEPSTRA, A. Surendran, Lucent Technologies, USA.
5. Paper ID: 2891 ON-LINE BAYESIAN SPEAKER ADAPTATION USING TREE-STRUCTURED TRANSFORMATION AND ROBUST PRIORS, S. Wang, University of Illinois at Urbana-Champaign, USA, Y. Zhao, University of Missouri-Columbia, USA.
6. Paper ID: 354 SPEAKER ADAPTATION BASED ON COMBINATION OF MAP ESTIMATION AND WEIGHTED NEIGHBOR REGRESSION, L. He, J. Wu, D. Fang, W. Wu, Tsinghua University, People's Republic of China.
7. Paper ID: 1718 ROBUST ESTIMATION FOR RAPID SPEAKER ADAPTATION USING DISCOUNTED LIKELIHOOD TECHNIQUES, A. Gunawardana, W. Byrne, The Johns Hopkins University, USA.
8. Paper ID: 3630 FAST SPEAKER ADAPTATION OF LARGE VOCABULARY CONTINUOUS DENSITY HMM SPEECH RECOGNIZER USING A BASIS TRANSFORM APPROACH, C. Boulis, V. Digalakis, Technical University of Crete, Greece.

Session:            SP-L3
Time: 09:00 - 12:00, Wednesday, June 7, 2000
Location: Convention Center Lower Hall (L3)
Title: ACOUSTIC MODELING I
Chair: Hermann Ney, RWTH, Germany
1. Paper ID: 1846 A GENERALIZATION OF THE MAXIMUM A POSTERIORI TRAINING ALGORITHM FOR MIXTURE PRIORS, E. Buhrke, C. Liu, Motorola, USA.
2. Paper ID: 388 LINEAR REGRESSION UNDER MAXIMUM A POSTERIORI CRITERION WITH MARKOV RANDOM FIELD PRIOR, X. Wu, Oregon Graduate Institute of Science and Technology, USA, Y. Yan, Intel Corporation, USA.
3. Paper ID: 617 EFFICIENT ML TRAINING OF CDHMM PARAMETERS BASED ON PRIOR EVOLUTION, POSTERIOR INTERVENTION AND FEEDBACK, Q. Huo, N. Smith, B. Ma, The University of Hong Kong, Hong Kong, China.
4. Paper ID: 3811 ASYNCHRONOUS-TRANSITION HMM, S. Matsuda, M. Nakai, H. Shimodaira, S. Sagayama, Japan Advanced Institute of Science and Technology, Japan.
5. Paper ID: 3544 FACTORED SPARSE INVERSE COVARIANCE MATRICES, J. Bilmes, University of Washington, USA.
6. Paper ID: 1062 SUB-STATE TYING IN TIED MIXTURE HIDDEN MARKOV MODELS, L. Gu, K. Rose, University of California, Santa Barbara, USA.
7. Paper ID: 1927 UNIFIED FRAME AND SEGMENT BASED MODELS FOR AUTOMATIC SPEECH RECOGNITION, H.-W. Hon, K. Wang, Microsoft Corporation, USA.
8. Paper ID: 3436 USE OF HIGHER LEVEL LINGUISTIC STRUCTURE IN ACOUSTIC MODELING FOR SPEECH RECOGNITION, I. Shafran, M. Ostendorf, University of Washington, USA.
9. Paper ID: 1929 MANDARIN ACCENT ADAPTATION BASED ON CONTEXT-INDEPENDENT/CONTEXT-DEPENDENT PRONUNCIATION MODELING, M. Liu, B. Xu, T. Huang, Y. Deng, C. Li, Chinese Academy of Sciences, People's Republic of China.
10. Paper ID: 1446 TOWARDS LANGUAGE INDEPENDENT ACOUSTIC MODELING, W. Byrne, The Johns Hopkins University, USA, P. Beyerlein, Philips Research Laboratories, The Netherlands, J. Huerta, Carnegie Mellon University, USA, S. Khudanpur, The Johns Hopkins University, USA, B. Marthi, University of Toronto, Canada, J. Morgan, West Point, USA, N. Peterek, Charles University, Czech Republic, J. Picone, Mississippi State University, USA, D. Vergyri, The Johns Hopkins University, USA, W. Wang, Rice University, USA.

Session:            SP-L4
Time: 15:30 - 17:30, Wednesday, June 7, 2000
Location: Sadirvan A - Hilton Hotel
Title: SPEECH ENHANCEMENT I
Chair: Abeer Alwan, University of California at Los Angeles, USA
1. Paper ID: 478 IMPOVING THE PERFORMANCE OF A SMALL MICROPHONE ARRAY AT LOW FREQUENCIES USING CRITICAL BAND AND LPC CODEBOOKS, Y. Cao, S. Sridharan, Queensland University of Technology, Australia.
2. Paper ID: 1692 SPEECH DEREVERBERATION AND NOISE REDUCTION WITH A COMBINED MICROPHONE ARRAY APPROACH, J. Gonzalez-Rodriguez, J. Sanchez-Bote, J. Ortega-Garcia, Universidad Politecnica de Madrid, Spain.
3. Paper ID: 1848 EXPLORING PERMUTATION INCONSISTENCY IN BLIND SEPARATION OF SPEECH SIGNALS IN A REVERBERANT ENVIRONMENT, M. Ikram, Georgia Institute of Technology, USA, D. Morgan, Lucent Technologies, USA.
4. Paper ID: 4021 INTELLIGIBILITY ASSESSMENT OF A MULTI-BAND SPEECH ENHANCEMENT SCHEME, A. Hussain, University of Dundee, United Kingdom.
5. Paper ID: 627 SPEECH ENHANCEMENT USING NONLINEAR MICROPHONE ARRAY WITH NOISE ADAPTIVE COMPLEMENTARY BEAMFORMING, H. Saruwatari, S. Kajita, K. Takeda, F. Itakura, Nagoya University, Japan.
6. Paper ID: 2520 LOCALIZATION OF MULTIPLE SOUND SOURCES BASED ON A CSP ANALYSIS WITH A MICROPHONE ARRAY, T. Nishiura, Nara Institute of Science and Technology, Japan, T. Yamada, University of Tsukuba, Japan, S. Nakamura, K. Shikano, Nara Institute of Science and Technology, Japan.
7. Paper ID: 661 AUTOMATIC ENHANCEMENT OF SPEECH INTELLIGIBILITY, V. Colotte, Y. Laprie, LORIA, France.
8. Paper ID: 3710 COMBINED ACOUSTIC ECHO AND NOISE REDUCTION USING GSVD-BASED OPTIMAL FILTERING, S. Doclo, M. Moonen, Katholieke Universiteit Leuven, Belgium, E. De Clippel, Philips ITCL, Belgium.

Session:            SP-L5
Time: 09:00 - 12:00, Thursday, June 8, 2000
Location: Convention Center Lower Hall (L3)
Title: SPEAKER RECOGNITION I
Chair: Doug Reynolds, MIT Lincoln Laboratory, USA
1. Paper ID: 1258 SPEAKER-CENTRIC SCORE NORMALISATION AND TIME PATTERN ANALYSIS FOR CONTINUOUS SPEAKER VERIFICATION, R. Auckenthaler, University of Swansea, United Kingdom, M. Carey, Ensigma Ltd., United Kingdom, J. Mason, University of Wales Swansea, United Kingdom.
2. Paper ID: 2089 A PROPOSED LIKELIHOOD TRANSFORMATION FOR SPEAKER VERIFICATION, D. Tran, M. Wagner, University of Canberra, Australia.
3. Paper ID: 2381 THE USE OF SUB-BAND CEPSTRUM IN SPEAKER VERIFICATION, P. Sivakumaran, A. Ariyaeeinia, University of Hertfordshire, United Kingdom.
4. Paper ID: 3945 GENERATION OF OPTIMUM SIGNATURE BASE SEQUENCES FOR SPEECH SIGNALS, B. Yarman, ISIK University, Turkey, R. Akdeniz, Trakya University, Turkey.
5. Paper ID: 2151 EFFECTIVE SPEAKER ADAPTATIONS FOR SPEAKER VERIFICATION, S. Ahn, Korea University, South Korea, S. Kang, Seokyeong University, South Korea, H. Ko, Korea University, South Korea.
6. Paper ID: 1236 GSM SPEECH CODING AND SPEAKER RECOGNITION, L. Besacier, CLIPS/IMAG, France, S. Grassi, A. Dufaux, M. Ansorge, F. Pellandini, Institute of Microtechnology, Switzerland.
7. Paper ID: 2854 SPEAKER RECOGNITION USING G.729 SPEECH CODEC PARAMETERS, T. Quatieri, R. Dunn, D. Reynolds, Massachusetts Institute of Technology, USA, J. Campbell, US Department of Defense, USA, E. Singer, Massachusetts Institute of Technology, USA.
8. Paper ID: 2301 USER VALIDATION FOR MOBILE TELEPHONES, M. Carey, Ensigma Ltd., United Kingdom, R. Auckenthaler, University of Swansea, United Kingdom.
9. Paper ID: 3532 AN INSTANTIABLE SPEECH BIOMETRICS MODULE WITH NATURAL LANGUAGE INTERFACE: IMPLEMENTATION IN THE TELEPHONY ENVIRONMENT, J. Navratil, J. Kleindienst, S. Maes, IBM, USA.
10. Paper ID: 1192 SPEAKER VERIFICATION: MINIMIZING THE CHANNEL EFFECTS USING AUTOASSOCIATIVE NEURAL NETWORK MODELS, S. Kishore, B. Yegnanarayana, Indian Institute of Technology, India.

Session:            SP-L6
Time: 15:30 - 17:30, Thursday, June 8, 2000
Location: Convention Center Lower Hall (L3)
Title: ROBUST RECOGNITION I
Chair: Yifan Gong, Texas Instruments, USA
1. Paper ID: 1671 LDA DERIVED CEPSTRAL TRAJECTORY FILTERS IN ADVERSE ENVIRONMENTAL CONDITIONS, M. Lieb, R. Haeb-Umbach, Philips Forschungslaboratorien, Germany.
2. Paper ID: 907 MAXIMUM LIKELIHOOD JOINT ESTIMATION OF CHANNEL AND NOISE FOR ROBUST SPEECH RECOGNITION, Y. Zhao, University of Missouri-Columbia, USA.
3. Paper ID: 3059 PCA-PMC: A NOVEL USE OF A PRIORI KNOWLEDGE FOR FAST PARALLEL MODEL COMBINATION, R. Sarikaya, J. Hansen, University of Colorado at Boulder, USA.
4. Paper ID: 3380 FEATURE EXTRACTION USING NON-LINEAR TRANSFORMATION FOR ROBUST SPEECH RECOGNITION ON THE AURORA DATABASE, S. Sharma, Oregon Graduate Institute of Science and Technology, USA, D. Ellis, International Computer Science Institute, USA, S. Kajarekar, P. Jain, H. Hermansky, Oregon Graduate Institute of Science and Technology, USA.
5. Paper ID: 1191 ASYNCHRONY IN MULTI-BAND SPEECH RECOGNITION, C. Cerisara, D. Fohr, J.-P. Haton, LORIA, France.
6. Paper ID: 1944 RESIDUAL NOISE COMPENSATION FOR ROBUST SPEECH RECOGNITION IN NONSTATIONARY NOISE, K. Yao, Tsinghua University, People's Republic of China, B. Shi, Hong Kong University of Science and Technology, Hong Kong, China, P. Fung, Hong Kong University of Science and Technology , Hong Kong, China, Z. Cao, Tsinghua University, People's Republic of China.
7. Paper ID: 1747 MAXIMUM LIKELIHOOD DISCRIMINANT FEATURE SPACES, G. Saon, M. Padmanabhan, R. Gopinath, S. Chen, IBM T.J. Watson Research Center, USA.
8. Paper ID: 2892 BLIND SPEECH SEPARATION OF MOVING SPEAKERS IN REAL REVERBERANT ENVIRONMENTS, A. Koutras, E. Dermatas, G. Kokkinakis, University of Patras, Greece.

Session:            SP-L7
Time: 15:30 - 18:00, Thursday, June 8, 2000
Location: Sadirvan A - Hilton Hotel
Title: WIDEBAND SPEECH CODING
Chair: Peter Kroon, Lucent Technologies, USA
1. Paper ID: 162 MIXED EXCITATION LINEAR PREDICTION CODING OF WIDEBAND SPEECH AT 8KBPS, W. Lin, S.-N. Koh, X. Lin, Nanyang Technological University, Singapore.
2. Paper ID: 3835 AN EMBEDDED SINUSOIDAL TRANSFORM CODEC WITH MEASURED PHASES AND SAMPLING RATE SCALABILITY, G. Aguilar, Lucent Technologies, USA, J.-H. Chen, Lucent InterNetworking Systems, USA, R. Dunn, R. McAulay, Massachusetts Institute of Technology, USA, X. Sun, W. Wang, R. Zopf, Lucent Technologies, USA.
3. Paper ID: 912 HIGH QUALITY EMBEDDED WIDEBAND SPEECH CODING USING AN INHERENTLY LAYERED CODING PARADIGM, S. Ramprashad, Lucent Technologies, USA.
4. Paper ID: 1444 A 16-KBIT/S BANDWIDTH SCALABLE AUDIO CODER BASED ON THE G.729 STANDARD, K. Koishida, V. Cuperman, A. Gersho, University of California, Santa Barbara, USA.
5. Paper ID: 3109 A 14 KB/S WIDEBAND SPEECH CODER WITH A PARAMETRIC HIGHBAND MODEL, A. McCree, Texas Instruments, USA.
6. Paper ID: 665 HI-BIN: AN ALTERNATIVE APPROACH TO WIDEBAND SPEECH CODING, R. Taori, R. Sluijter, A. Gerrits, Philips Research Laboratories, The Netherlands.
7. Paper ID: 4062 A HIGH-FIDELITY SPEECH AND AUDIO CODEC WITH LOW DELAY AND LOW COMPLEXITY, J.-H. Chen, Lucent Technologies, USA.
8. Paper ID: 1946 A MULTI-RATE WIDEBAND SPEECH CODEC ROBUST TO BACKGROUND NOISE, A. Murashima, M. Serizawa, K. Ozawa, NEC Corporation, Japan.
9. Paper ID: 1441 STOCHASTIC-ALGEBRAIC WIDEBAND LSF QUANTIZATION, S. Ragot, Université de Sherbrooke, Canada, R. Lefebvre, R. Salami, J.-P. Adoul, University of Sherbrooke, Canada.
10. Paper ID: 1199 A SILENCE COMPRESSION ALGORITHM FOR MULTI-RATE/DUAL-BANDWIDTH MPEG-4 CELP STANDARD, M. Serizawa, H. Ito, T. Nomura, NEC Corporation, Japan.

Session:            SP-L8
Time: 09:00 - 12:00, Friday, June 9, 2000
Location: Convention Center Lower Hall (L3)
Title: SPEAKER RECOGNITION II
Chair: M. Demirekler, Middle East Technical University, Turkey
1. Paper ID: 1628 A SPEAKER TRACKING SYSTEM BASED ON SPEAKER TURN DETECTION FOR NIST EVALUATION, J.-F. Bonastre, Laboratoire Informatique d'Avignon, France, P. Delacourt, Eurecom, France, C. Fredouille, T. Merlin, Laboratoire Informatique d'Avignon, France, C. Wellekens, Eurecom, France.
2. Paper ID: 1648 SPEAKER IDENTIFICATION IN MISMATCH TRAINING AND TESTING CONDITIONS, C. Alonso-Martinez, M. Faundez-Zanuy, Escola Universitaria Politecnica de Mataro, Spain.
3. Paper ID: 1709 AN ITERATIVE TECHNIQUE FOR TRAINING SPEAKER VERIFICATION SYSTEMS, W. Campbell, Motorola, USA.
4. Paper ID: 1880 SEARCH-SPACE REDUCTION FOR FAST, OPTIMAL HMM DECODING IN SPEAKER VERIFICATION, Q. Li, Lucent Technologies, USA.
5. Paper ID: 2227 A TWO-STAGE SCORING METHOD COMBINING WORLD AND COHORT MODELS FOR SPEAKER VERIFICATION, W. Zhang, M.-W. Mak, The Hong Kong Polytechnic University, Hong Kong, China, M. He, Ocean University of Qingdao, Hong Kong, China.
6. Paper ID: 2320 BEHAVIOR OF A BAYESIAN ADAPTATION METHOD FOR INCREMENTAL ENROLLMENT IN SPEAKER VERIFICATION, C. Fredouille, Laboratoire Informatique d'Avignon, France, J. Mariethoz, Dalle Molle Institute of Perceptual Artificial Intelligence, Switzerland, C. Jaboulet, J. Hennebert, UBS, Switzerland, J.-F. Bonastre, Laboratoire Informatique d'Avignon, France, C. Mokbel, Universite de St. Joseph, Lebanon, F. Bimbot, IRISA, France.
7. Paper ID: 2665 EVOLUTIVE HMM FOR MULTI-SPEAKER TRACKING SYSTEM, S. Meignier, J.-F. Bonastre, C. Fredouille, T. Merlin, Universite d' Avignon, France.
8. Paper ID: 2835 SPEAKER RECOGNITION IN TWO-SPEAKER DATA: RECENT RESULTS FROM DRAGON SYSTEMS, F. Weber, B. Peskin, M. Newman, L. Gillick, Dragon Systems, Inc., USA.
9. Paper ID: 2861 A NOVEL RANK-BASED CLASSIFIER COMBINATION SCHEME FOR SPEAKER IDENTIFICATION, H. Altincay, M. Demirekler, Middle East Technical University, Turkey.
10. Paper ID: 3067 IMPROVED NORMALIZATION WITHOUT RECOURSE TO AN IMPOSTOR DATABASE FOR SPEAKER VERIFICATION, M. Hebert, S. Peters, Nuance Communications, USA.

Session:            SP-L9
Time: 13:30 - 15:00, Friday, June 9, 2000
Location: Convention Center Lower Hall (L2)
Title: SPOKEN LANGUAGE DIALOGUE
Chair: Roberto Pieraccini, SpeechWorks, USA
1. Paper ID: 1049 PROBABILISTIC SIMULATION OF HUMAN-MACHINE DIALOGUES, K. Scheffler, S. Young, University of Cambridge, United Kingdom.
2. Paper ID: 1151 FUNDAMENTAL PERFORMANCE ANALYSIS FOR SPOKEN DIALOGUE SYSTEMS BASED ON A QUANTITATIVE SIMULATION APPROACH, B.-S. Lin, National Taiwan University, Taiwan, L.-S. Lee, Institute of Information Science, Academia Sinica, Taiwan.
3. Paper ID: 1819 PARSER ADAPTATION VIA HOUSEHOLDER TRANSFORM, X. Luo, IBM T.J. Watson Research Center, USA.
4. Paper ID: 2494 CU FOREX: A BILINGUAL SPOKEN DIALOG SYSTEM FOR FOREIGN EXCHANGE ENQUIRIES, H. Meng, The Chinese University of Hong Kong, Hong Kong, China, S. Lee, SpeechWorks International Ltd., USA, C. Wai, The Chinese University of Hong Kong, Hong Kong, China.
5. Paper ID: 2895 FAST REINFORCEMENT LEARNING OF DIALOG STRATEGIES, D. Goddeau, Compaq Computer Corporation, USA, J. Pineau, Carnegie Mellon University, USA.
6. Paper ID: 697 CONFIDENCE MEASURES FOR DIALOGUE MANAGEMENT IN THE CU COMMUNICATOR SYSTEM, R. San-Segundo, Universidad Politecnica de Madrid, Spain, B. Pellom, W. Ward, University of Colorado at Boulder, USA, J. Pardo, Universidad Politecnica de Madrid, Spain.

Session:            SP-P1
Time: 15:15 - 17:00, Tuesday, June 6, 2000
Location: Ballroom - Hilton Hotel (P6)
Title: ACOUSTIC MODELING II
Chair: Ramesh Gopinath, IBM, USA
1. Paper ID: 1033 TIED POSTERIORS: AN APPROACH FOR EFFECTIVE INTRODUCTION OF CONTEXT DEPENDENCY IN HYBRID NN/HMM LVCSR, J. Rottland, Duisburg University, Germany, G. Rigoll, Gerhard-Mercator-University Duisburg, Germany.
2. Paper ID: 1248 DISCRIMINATIVE RESOLUTION ENHANCEMENT IN ACOUSTIC MODELLING, J. Duchateau, K. Demuynck, P. Wambacq, Katholieke Universiteit Leuven, Belgium.
3. Paper ID: 1978 A SEGMENTAL-FEATURE HMM USING PARAMETRIC TRAJECTORY MODEL, Y.-S. Yun, Y.-H. Oh, Korea Advanced Institute of Science and Technology, South Korea.
4. Paper ID: 2353 SOFT GPD FOR MINIMUM CLASSIFICATION ERROR RATE TRAINING, B. Shi, Hong Kong University of Science and Technology, Hong Kong, China, K. Yao, Z. Cao, Tsinghua University, People's Republic of China.
5. Paper ID: 2846 HETEROGENEOUS LEXICAL UNITS FOR AUTOMATIC SPEECH RECOGNITION: PRELIMINARY INVESTIGATIONS, I. Bazzi, J. Glass, Massachusetts Institute of Technology, USA.
6. Paper ID: 967 ACOUSTIC MODELING FOR CHINESE SPEECH RECOGNITION: A COMPARATIVE STUDY OF MANDARIN AND CANTONESE, S. Gao, T. Lee, Y. Wong, The Chinese University of Hong Kong, People's Republic of China, B. Xu, Chinese Academy of Sciences, People's Republic of China, P. Ching, The Chinese University of Hong Kong, People's Republic of China, T. Huang, Chinese Academy of Sciences, People's Republic of China.
7. Paper ID: 845 AN EFFECTIVE ACOUSTIC MODELING OF NAMES BASED ON MODEL INDUCTION, T. Kim, Korea University, South Korea, S. Kang, Seokyeong University, South Korea, H. Ko, Korea University, South Korea.
8. Paper ID: 3770 A NEW PHONETIC TIED-MIXTURE MODEL FOR EFFICIENT DECODING, A. Lee, T. Kawahara, Kyoto University, Japan, K. Takeda, Nagoya University, Japan, K. Shikano, Nara Institute of Science and Technology, Japan.
9. Paper ID: 1647 AGGLOMERATIVE VS. TREE-BASED CLUSTERING FOR THE DEFINITION OF MULTILINGUAL SET OF TRIPHONES, B. Imperl, Z. Kacic, B. Horvat, A. Zgank, University of Maribor, Slovenia.
10. Paper ID: 3030 INTEGRATING DYNAMIC SPEECH MODALITIES INTO CONTEXT DECISION TREES, C. Fugen, I. Rogina, University of Karlsruhe, Germany.

Session:            SP-P2
Time: 09:00 - 12:00, Wednesday, June 7, 2000
Location: Ballroom - Hilton Hotel (P5)
Title: TOPICS IN SPEECH PROCESSING - PART 1: SPEECH SYNTHESIS & ANALYSIS; PART 2: SPEECH ANALYSIS
Chair: Robert Donovan, IBM, USA
1. Paper ID: 509 A NOVEL APPROACH TO THE FULLY AUTOMATIC EXTRACTION OF FUJISAKI MODEL PARAMETERS, H. Mixdorff, Dresden University of Technology, Germany.
2. Paper ID: 1896 ROBUST GENERATION OF SYMBOLIC PROSODY BY A NEURAL CLASSIFIER BASED ON AUTOASSOCIATORS, A. Muller, H. Zimmermann, R. Neuneier, Siemens, Germany.
3. Paper ID: 4052 IMPROVING INTONATIONAL PHRASING WITH SYNTACTIC INFORMATION, P. Koehn, University of Southern California, USA, S. Abney, J. Hirschberg, M. Collins, AT&T Labs, USA.
4. Paper ID: 2361 AUTOMATIC LEARNING OF NUMERAL GRAMMARS FOR MULTI-LINGUAL SPEECH SYNTHESIZERS, G. Flach, Dresden University of Technology, Germany, M. Holzapfel, Siemens, Germany, C. Just, A. Wachtler, M. Wolff, Dresden University of Technology, Germany.
5. Paper ID: 3894 TIME AND FREQUENCY SCALE MODIFICATION OF SPEECH SIGNALS, B. Ninness, S. Henriksen, University of Newcastle, Australia.
6. Paper ID: 716 SPEECH RECONSTRUCTION FROM MEL FREQUENCY CEPSTRAL COEFFICIENTS AND PITCH FREQUENCY, D. Chazan, R. Hoory, G. Cohen, M. Zibulski, IBM Research, Israel.
7. Paper ID: 2526 IMPROVING THE ROBUSTNESS OF WAVELET TRANSFORM FOR EPOCH DETECTION, Y. Lam, R. Luk, F. Chung, The Hong Kong Polytechnic University, Hong Kong, China.
8. Paper ID: 1466 A WEIGHTED AUTOCORRELATION METHOD FOR PITCH EXTRACTION OF NOISY SPEECH, H. Kobayashi, T. Shimamura, Saitama University, Japan.
9. Paper ID: 2735 PERFORMANCE OF THE PITCH-SCALED HARMONIC FILTER AND APPLICATIONS IN SPEECH ANALYSIS, P. Jackson, C. Shadle, University of Southampton, United Kingdom.
10. Paper ID: 3745 SPEECH PARAMETER GENERATION ALGORITHMS FOR HMM-BASED SPEECH SYNTHESIS, K. Tokuda, T. Yoshimura, Nagoya Institute of Technology, Japan, T. Masuko, T. Kobayashi, Tokyo Institute of Technology, Japan, T. Kitamura, Nagoya Institute of Technology, Japan.
11. Paper ID: 2311 UNSUPERVISED ESTIMATION OF THE HUMAN VOCAL TRACT LENGTH OVER SENTENCE LEVEL UTTERANCES, B. Necioglu, The MITRE Corporation, USA, M. Clements, T. Barnwell, III, Georgia Institute of Technology, USA.
12. Paper ID: 3743 MULTIVARIATE-STATE HIDDEN MARKOV MODELS FOR SIMULTANEOUS TRANSCRIPTION OF PHONES AND FORMANTS, M. Hasegawa-Johnson, University of Illinois at Urbana-Champaign, USA.
13. Paper ID: 4085 ON THE MUTUAL INFORMATION BETWEEN FREQUENCY BANDS IN SPEECH, M. Nilsson, S. Vang Andersen, W. Kleijn, Royal Institute of Technology, Sweden.
14. Paper ID: 3273 STUDY OF TALKER INDIVIDUALITY BY USING ARX SPEECH ANALYSIS-SYNTHESIS-EDITING SYSTEM, W. Zhu, K. Matsui, Matsushita Electric Industrial Co., Ltd., Japan, H. Kasuya, Utsunomiya University, Japan.
15. Paper ID: 2863 LINGUISTIC PROPERTIES OF NON-NATIVE SPEECH, L. Mayfield Tomokiyo, Carnegie Mellon University, USA.
16. Paper ID: 328 VISUAL APPROACH FOR AUTOMATIC PITCH PERIOD ESTIMATION, Z. Sen, K. Shirai, Waseda University, Japan.
17. Paper ID: 887 ROBUST PITCH TRACKING FOR PROSODIC MODELING IN TELEPHONE SPEECH, C. Wang, S. Seneff, Massachusetts Institute of Technology, USA.
18. Paper ID: 2670 PERCEPTUAL EFFECTS OF COARTICULATION IN FRICATIVES, S. Fernandez, S. Feijoo, R. Balsa, N. Barros, University of Santiago de Compostela, Spain.
19. Paper ID: 2774 MEL-SCALED DISCRETE WAVELET COEFFICIENTS FOR SPEECH RECOGNITION, J. Gowdy, Z. Tufekci, Clemson University, USA.
20. Paper ID: 1222 ON-LINE SPEAKING RATE ESTIMATION USING GAUSSIAN MIXTURE MODELS, R. Faltlhauser, T. Pfau, G. Ruske, Technische Universität München, Germany.

Session:            SP-P3
Time: 15:15 - 17:00, Wednesday, June 7, 2000
Location: Ballroom - Hilton Hotel (P5)
Title: LOW BIT RATE SPEECH CODING
Chair: Alan McCree, Texas Instruments, USA
1. Paper ID: 397 WAVEFORM EXTRACTION FOR PERFECT RECONSTRUCTION IN WI CODING, V. Ruoppila, University of Sherbrooke, Canada, M. Tammi, J. Saarinen, Tampere University of Technology, Finland.
2. Paper ID: 782 HIGH QUALITY ENHANCED WAVEFORM INTERPOLATIVE CODING AT 2.8 KBPS, O. Gottesman, A. Gersho, University of California, Santa Barbara, USA.
3. Paper ID: 1121 ANALYSIS-BY-SYNTHESIS MULTIMODE HARMONIC SPEECH CODING AT 4 KB/S, C. Li, V. Cuperman, University of California, Santa Barbara, USA.
4. Paper ID: 1864 SPEECH CODING WITH AN ANALYSIS-BY-SYNTHESIS SINUSOIDAL MODEL, C. Etemoglu, V. Cuperman, A. Gersho, University of California, Santa Barbara, USA.
5. Paper ID: 3143 A 1200 BPS SPEECH CODER BASED ON MELP, T. Wang, K. Koishida, V. Cuperman, A. Gersho, SignalCom, Inc., USA, J. Collura, National Security Agency, USA.
6. Paper ID: 3190 A 4 KB/S HYBRID MELP/CELP CODER WITH ALIGNMENT PHASE ENCODING AND ZERO PHASE EQUALIZATION, J. Stachurski, A. McCree, Texas Instruments, USA.
7. Paper ID: 4074 PERCEPTUAL PHASE REDUNDANCY IN SPEECH, D.-S. Kim, Samsung Advanced Institute of Technology, South Korea.
8. Paper ID: 1891 A COMBINED WI AND MELP CODER AT 5.2 KBPS, J. Skoglund, R. Cox, AT&T Labs, USA, J. Collura, National Security Agency, USA.
9. Paper ID: 127 A BACKGROUND NOISE REDUCTION TECHNIQUE BASED ON SINUSOIDAL SPEECH CODING SYSTEMS, S. Yeldener, J. Rieser, COMSAT Laboratories, USA.
10. Paper ID: 3325 VARIABLE RATE MULTI-MODE EXCITATION CODING OF SPEECH AT 2.4KBPS, S. Wang, Atmel Corporation, USA.

Session:            SP-P4
Time: 15:15 - 17:00, Wednesday, June 7, 2000
Location: Ballroom - Hilton Hotel (P6)
Title: TOPICS IN SPEECH RECOGNITION I
Chair: Philip Loizou, University of Texas, Dallas, USA
1. Paper ID: 1998 SPEECH/NON-SPEECH CLASSIFICATION USING MULTIPLE FEATURES FOR ROBUST ENDPOINT DETECTION, W.-H. Shin, B.-S. Lee, Y.-K. Lee, J.-S. Lee, LG Corporate Institute of Technology, South Korea.
2. Paper ID: 1587 SPEECH RECOGNITION FOR A DISTANT MOVING SPEAKER BASED ON HMM COMPOSITION AND SEPARATION, T. Takiguchi, IBM Tokyo Research Laboratory, Japan, S. Nakamura, K. Shikano, Nara Institute of Science and Technology, Japan.
3. Paper ID: 2274 HANDS-FREE SPEECH RECOGNITION USING A FILTERED CLEAN CORPUS AND INCREMENTAL HMM ADAPTATION, M. Matassoni, M. Omologo, D. Giuliani, ITC-irst, Italy.
4. Paper ID: 3320 HMM ADAPTATION AND MICROPHONE ARRAY PROCESSING FOR DISTANT SPEECH RECOGNITION, J. Kleban, Rutgers University, USA, Y. Gong, Texas Instruments, USA.
5. Paper ID: 2356 COMPARING ACOUSTIC FEATURES FOR ROBUST ASR IN FIXED AND CELLULAR NETWORK APPLICATIONS, F. de Wet, B. Cranen, J. de Veth, L. Boves, University of Nijmegen, The Netherlands.
6. Paper ID: 2741 ANCHORING HYPOTHESIS AND ITS APPLICATION TO TONE RECOGNITION OF CHINESE CONTINUOUS SPEECH, J.-S. Zhang, K. Hirose, The University of Tokyo, Japan.
7. Paper ID: 980 STRATEGIES FOR AUTOMATIC SEGMENTATION OF AUDIO DATA, T. Kemp, M. Schmidt, M. Westphal, A. Waibel, University of Karlsruhe, Germany.
8. Paper ID: 1738 A METHOD FOR DIRECT AUDIO SEARCH WITH APPLICATIONS TO INDEXING AND RETRIEVAL, S. Johnson, P. Woodland, University of Cambridge, United Kingdom.
9. Paper ID: 135 THE STUDY ON DISTRIBUTED SPEECH RECOGNITION SYSTEM, W. Zhang, L. He, Intel Corporation, People's Republic of China, Y.-L. Chow, Lernout & Hauspie, Singapore, R. Yang, Y. Su, Intel Corporation, People's Republic of China.
10. Paper ID: 3367 CONVERSATIONAL SPEECH RECOGNITION USING ACOUSTIC AND ARTICULATORY INPUT, K. Kirchhoff, University of Washington, USA, G. Fink, G. Sagerer, University of Bielefeld, Germany.

Session:            SP-P5
Time: 09:00 - 12:00, Thursday, June 8, 2000
Location: Ballroom - Hilton Hotel (P5)
Title: TOPICS IN SPEECH CODING - PART 1; PART 2
Chair: Raymond Chen, Lucent Technologies, USA
1. Paper ID: 96 HARMONIC EXPONENTIAL MODELING OF TRANSITIONAL SPEECH SEGMENTS, J. Jensen, S. Jensen, E. Hansen, Aalborg University, Denmark.
2. Paper ID: 1993 VARIABLE DIMENSIONAL ALGEBRAIC CELP CODING OF PROTOTYPE WAVEFORMS, J. Sohn, W. Sung, Seoul National University, South Korea.
3. Paper ID: 2668 LOW-RATE QUANTIZATION OF SPECTRUM PARAMETERS, T. Eriksson, Chalmers University of Technology, Sweden, H.-G. Kang, AT&T Labs, USA, P. Hedelin, Chalmers University of Technology, Sweden.
4. Paper ID: 3060 RECURSIVE LPC SPECTRUM CODING - A CLASSIFIED VQ APPROACH, F. Norden, J. Samuelsson, P. Hedelin, Chalmers University of Technology, Sweden.
5. Paper ID: 4146 ROBUST APPLICATION OF DISCRETE ALL-POLE MODELING TO SINUSOIDAL TRANSFORM CODING, D. Molyneux, M.-S. Ho, B. Cheetham, University of Manchester, United Kingdom.
6. Paper ID: 272 PREDICTIVE AND MEL-SCALE BINARY VECTOR QUANTIZATION OF VARIABLE DIMENSION SPECTRAL MAGNITUDE, Y. Cho, University of Surrey, United Kingdom, M. Kim, Samsung Advanced Institute of Technology, South Korea, A. Kondoz, University of Surrey, United Kingdom.
7. Paper ID: 374 ENCODING SINUSOIDAL AMPLITUDES WITH A MINIMUM PHASE RATIONAL MODEL, N. Malik, W. Holmes, University of New South Wales, Australia.
8. Paper ID: 944 PHASE AND TRANSIENT MODELING FOR HARMONIC+NOISE SPEECH CODING, E. Yu, C.-F. Chan, City University of Hong Kong, Hong Kong, China.
9. Paper ID: 2101 LINEAR PREDICTION INCORPORATING SIMULTANEOUS MASKING, J. Lukasiak, I. Burnett, J. Chicharo, University of Wollongong, Australia, M. Thomson, Motorola, Australia.
10. Paper ID: 4112 A FRAME INTERPRETATION OF SINUSOIDAL CODING AND WAVEFORM INTERPOLATION, W. Kleijn, Royal Institute of Technology, Sweden.
11. Paper ID: 3875 OPTIMIZED ESTIMATION OF SPECTRAL PARAMETERS FOR THE CODING OF NOISY SPEECH, R. Martin, I. Wittke, P. Jax, Institute of Communication Systems and Data Processing, Germany.
12. Paper ID: 1784 IMPROVED FRAME ERASURE CONCEALMENT FOR CELP-BASED CODERS, J. De Martin, Politecnico di Torino, Italy, T. Unno, V. Viswanathan, Texas Instruments, USA.
13. Paper ID: 709 A CELP-BASED HYBRID DIGITAL-ANALOG (HDA) JOINT SOURCE-CHANNEL SPEECH CODER, N. Phamdo, U. Mittal, State University of New York at Stony Brook, USA.
14. Paper ID: 1077 PITCH-SYNCHRONOUS LINEAR-PREDICTION ANALYSIS BY SYNTHESIS WITH REDUCED PULSE DENSITIES, D. Guerchi, Y. Qian, P. Mermelstein, Universite du Quebec, Canada.
15. Paper ID: 1497 SHAPED FIXED CODEBOOK SEARCH FOR CELP CODING AT LOW BIT RATES, E. Erzin, Lucent Technologies, USA.
16. Paper ID: 2757 DIGITAL WATERMARKING OF SPEECH SIGNALS FOR THE NATIONAL GALLERY OF THE SPOKEN WORD, F. Ruiz, J. Deller, Jr., Michigan State University, USA.
17. Paper ID: 3546 DISPERSED-PULSE CODEBOOK AND ITS APPLICATION TO A 4KB/S SPEECH CODER, K. Yasunaga, Matsushita Research Institute Tokyo, Inc., Japan, H. Ehara, K. Yoshida, Matsushita Communication Industrial Co., Ltd., Japan, T. Morii, Matsushita Research Institute Tokyo, Inc., Japan.
18. Paper ID: 3637 JOINT SOURCE - CHANNEL MMSE-DECODING OF SPEECH PARAMETERS, S. Heinen, P. Vary, Aachen University of Technology, Germany.
19. Paper ID: 3126 SPEECH QUALITY OBJECTIVE ASSESSMENT USING NEURAL NETWORK, Q. Fu, K. Yi, Xidian University, People's Republic of China, M. Sun, University of Pittsburgh, USA.
20. Paper ID: 648 THE PERCEPTUAL ANALYSIS MEASUREMENT SYSTEM FOR ROBUST END-TO-END SPEECH QUALITY ASSESSMENT, A. Rix, M. Hollier, BT, United Kingdom.

Session:            SP-P6
Time: 09:00 - 12:00, Thursday, June 8, 2000
Location: Ballroom - Hilton Hotel (P6)
Title: TOPICS IN LVCSR I - PART 1: FAST DECODING AND ADAPTATION; PART 2
Chair: Michael Picheny, IBM, USA
1. Paper ID: 1453 RAPID LIKELIHOOD CALCULATION OF SUBSPACE CLUSTERED GAUSSIAN COMPONENTS, A. Aiyer, Stanford University, USA, M. Gales, University of Cambridge, United Kingdom, M. Picheny, IBM , USA.
2. Paper ID: 3718 PITCH TRACKING AND TONE FEATURES FOR MANDARIN SPEECH RECOGNITION, H. Huang, F. Seide, Philips Innovation Center, Taiwan.
3. Paper ID: 1411 BOOSTING GAUSSIAN MIXTURES IN AN LVCSR SYSTEM, G. Zweig, IBM, USA, M. Padmanabhan, IBM T.J. Watson Research Center, USA.
4. Paper ID: 3948 USING SIMD INSTRUCTIONS FOR FAST LIKELIHOOD CALCULATION IN LVCSR, S. Kanthak, Aachen University of Technology, Germany, K. Schutz, AXYS Design Automation for Embedded Systems, Germany, H. Ney, Aachen University of Technology, Germany.
5. Paper ID: 873 FAST DECODING IN LARGE VOCABULARY NAME DIALING, J. Suontausta, J. Hakkinen, O. Viikki, Nokia Research Center, Finland.
6. Paper ID: 1741 ON THE INCREMENTAL ADDITION OF REGRESSION CLASSES FOR SPEAKER ADAPTATION, J. McDonough, V. Venkataramani, W. Byrne, The Johns Hopkins University, USA.
7. Paper ID: 1755 INTER-CLASS MLLR FOR SPEAKER ADAPTATION, S.-J. Doh, R. Stern, Carnegie Mellon University, USA.
8. Paper ID: 3313 MODEL ADAPTATION IN LINE SPECTRUM DOMAIN, A.-T. Yu, H.-C. Wang, National Tsing Hua University, Taiwan.
9. Paper ID: 3558 MAP ADAPTATION WITH SUBSPACE REGRESSION CLASSES AND TYING, K.-M. Wong, B. Mak, Hong Kong University of Science and Technology, Hong Kong, China.
10. Paper ID: 1001 DUCODER - THE DUISBURG UNIVERSITY LVCSR STACKDECODER, D. Willett, C. Neukirchen, G. Rigoll, Gerhard-Mercator-University Duisburg, Germany.
11. Paper ID: 1937 PROGRESSIVE 2-PASS DECODER FOR REAL-TIME BROADCAST NEWS CAPTIONING, T. Imai, A. Kobayashi, S. Sato, H. Tanaka, A. Ando, NHK Science and Technical Research Laboratories, Japan.
12. Paper ID: 3688 TURKISH LVCSR: TOWARDS BETTER SPEECH RECOGNITION FOR AGGLUTINATIVE LANGUAGES, K. Carki, P. Geutner, T. Schultz, University of Karlsruhe, Germany.
13. Paper ID: 3829 PERFORMANCE OF LVCSR WITH MORPHEME-BASED AND SYLLABLE-BASED RECOGNITION UNITS, O.-W. Kwon, ETRI, South Korea.
14. Paper ID: 2312 EMPLOYING HETEROGENEOUS INFORMATION IN A MULTI-STREAM FRAMEWORK, H. Christensen, B. Lindberg, O. Andersen, Aalborg University, Denmark.
15. Paper ID: 2908 DICTATION OF MULTIPARTY CONVERSATION USING STATISTICAL TURN TAKING MODEL AND SPEAKER MODEL, N. Murai, T. Kobayashi, Waseda University, Japan.
16. Paper ID: 3733 AUTOMATIC SPEECH SUMMARIZATION BASED ON WORD SIGNIFICANCE AND LINGUISTIC LIKELIHOOD, C. Hori, S. Furui, Tokyo Institute of Technology, Japan.
17. Paper ID: 393 STATISTICAL KNOWLEDGE BASED FRAME SYNCHRONOUS SEARCH STRATEGIES IN CONTINUOUS SPEECH RECOGNITION, Z. Song, F. Zheng, W. Wu, Tsinghua University, People's Republic of China.
18. Paper ID: 563 USING POSTERIOR WORD PROBABILITIES FOR IMPROVED SPEECH RECOGNITION, F. Wessel, R. Schlüter, H. Ney, Aachen University of Technology, Germany.
19. Paper ID: 1048 VARIABLE WORD RATE N-GRAMS, Y. Gotoh, S. Renals, University of Sheffield, United Kingdom.
20. Paper ID: 1131 INTEGRATING DETAILED INFORMATION INTO A LANGUAGE MODEL, R. Zhang, E. Black, A. Finch, Y. Sagisaka, ATR Laboratories, Japan.

Session:            SP-P7
Time: 15:15 - 17:00, Thursday, June 8, 2000
Location: Ballroom - Hilton Hotel (P6)
Title: FEATUE EXTRACTION
Chair: Kuldip Paliwal, Griffith University, Australia
1. Paper ID: 3408 AN OPTIMAL BHATTACHARYYA CENTROID ALGORITHM FOR GAUSSIAN CLUSTERING WITH APPLICATIONS IN AUTOMATIC SPEECH RECOGNITION, L. Rigazio, B. Tsakam, J.-C. Junqua, Panasonic Technologies, Inc., USA.
2. Paper ID: 655 EAR-MODEL DERIVED FEATURES FOR AUTOMATIC SPEECH RECOGNITION, R. de Mori, Universite d' Avignon, France, D. Albesano, R. Gemello, F. Mana, CSELT, Italy.
3. Paper ID: 657 BITSTREAM-BASED FEATURE EXTRACTION FOR WIRELESS SPEECH RECOGNITION, H. Kim, R. Cox, AT&T Labs, USA.
4. Paper ID: 695 A FUZZY APPROACH FOR THE EQUALIZATION OF CEPSTRAL VARIANCES, W.-W. Hung, Ming-Chi Institute of Technology, Taiwan, H.-C. Wang, National Tsing Hua University, Taiwan.
5. Paper ID: 987 A NEW APPROACH TO DISCRIMINATIVE FEATURE EXTRACTION USING MODEL TRANSFORMATION, M. Thomae, DaimlerChrysler AG, Germany, G. Ruske, T. Pfau, Technische Universität München, Germany.
6. Paper ID: 2330 A MARKOV RANDOM FIELD BASED MULTI-BAND MODEL, G. Gravier, M. Sigelle, G. Chollet, CNRS-ENST, France.
7. Paper ID: 3141 AUDITORY-BASED SPEECH PROCESSING BASED ON THE AVERAGE LOCALIZED SYNCHRONY DETECTION, A. Ali, J. Van der Spiegel, University of Pennsylvania, USA, P. Mueller, Corticon, Inc., USA.
8. Paper ID: 3324 DATA-DRIVEN RASTA FILTERS IN REVERBERATION, M. Shire, B. Chen, University of California, Berkeley, USA.
9. Paper ID: 3434 SPEECH FEATURE EXTRACTION USING INDEPENDENT COMPONENT ANALYSIS, J.-H. Lee, Korea Advanced Institute of Science and Technology, South Korea, H.-Y. Jung, Electronics and Telecommunications Research Institute, South Korea, T.-W. Lee, University of California, San Diego, USA, S.-Y. Lee, Korea Advanced Institute of Science and Technology, South Korea.
10. Paper ID: 3476 TANDEM CONNECTIONIST FEATURE EXTRACTION FOR CONVENTIONAL HMM SYSTEMS, H. Hermansky, Oregon Graduate Institute of Science and Technology, USA, D. Ellis, International Computer Science Institute, USA, S. Sharma, Oregon Graduate Institute of Science and Technology, USA.

Session:            SP-P8
Time: 09:00 - 12:00, Friday, June 9, 2000
Location: Ballroom - Hilton Hotel (P5)
Title: TOPICS IN LVCSR II - PART 1: LANGUAGE MODELING & SEARCH TECHNIQUES; PART 2: PRONUNCIATION & LANGUAGE MODELING
Chair: Rafid Sukkar, Lucent Technologies, USA
1. Paper ID: 1922 A UNIFIED CONTEXT-FREE GRAMMAR AND N-GRAM MODEL FOR SPOKEN LANGUAGE PROCESSING, Y.-Y. Wang, M. Mahajan, X. Huang, Microsoft Corporation, USA.
2. Paper ID: 2012 INTEGRATING A CONTEXT-DEPENDENT PHRASE GRAMMAR IN THE VARIABLE N-GRAM FRAMEWORK, M.-H. Siu, Hong Kong University of Science and Technology, Hong Kong, China, M. Ostendorf, University of Washington, USA.
3. Paper ID: 1960 PUTTING IT ALL TOGETHER: LANGUAGE MODEL COMBINATION, J. Goodman, Microsoft Corporation, USA.
4. Paper ID: 880 TOWARDS A LARGE-VOCABULARY FRENCH VOCAL DICTATION BASED ON A SIZE-INDEPENDENT LANGUAGE-MODEL SEARCH USING THE INRS RECOGNIZER, H. Tolba, D. O'Shaughnessy, Universite du Quebec, Canada.
5. Paper ID: 2366 LARGE VOCABULARY DECODING AND CONFIDENCE ESTIMATION USING WORD POSTERIOR PROBABILITIES, G. Evermann, P. Woodland, University of Cambridge, United Kingdom.
6. Paper ID: 2169 EFFICIENT INTEGRATION OF MULTIPLE PRONUNCIATIONS IN A LARGE VOCABULARY DECODER, H. Schramm, X. Aubert, Philips Research Laboratories, Germany.
7. Paper ID: 3268 TRANSCRIPTION AND INDEXATION OF BROADCAST DATA, J.-L. Gauvain, L. Lamel, Y. de Kercadio, G. Adda, CNRS, France.
8. Paper ID: 3918 A BASELINE FOR THE TRANSCRIPTION OF ITALIAN BROADCAST NEWS, F. Brugnara, M. Cettolo, M. Federico, D. Giuliani, ITC-irst, Italy.
9. Paper ID: 3956 RECENT IMPROVEMENTS OF THE RWTH LARGE VOCABULARY SPEECH RECOGNITION SYSTEM ON SPONTANEOUS SPEECH, A. Sixtus, S. Molau, S. Kanthak, R. Schlüter, H. Ney, Aachen University of Technology, Germany.
10. Paper ID: 3766 FRENCH LARGE VOCABULARY RECOGNITION WITH CROSS-WORD PHONOLOGY TRANSDUCERS, G. Boulianne, J. Brousseau, P. Ouellet, P. Dumouchel, Centre de recherche informatique de Montréal, Canada.
11. Paper ID: 587 PRONUNCIATION AMBIGUITY VS PRONUNCIATION VARIABILITY IN SPEECH RECOGNITION, M. Saraclar, S. Khudanpur, The Johns Hopkins University, USA.
12. Paper ID: 1842 LEXICAL MODELING OF NON-NATIVE SPEECH FOR AUTOMATIC SPEECH RECOGNITION, K. Livescu, J. Glass, Massachusetts Institute of Technology, USA.
13. Paper ID: 2669 DATA - DRIVEN GENERATION OF PRONUNCIATION DICTIONARIES IN THE GERMAN VERBMOBIL PROJECT - DISCUSSION OF EXPERIMENTAL RESULTS, M. Eichner, M. Wolff, Dresden University of Technology, Germany.
14. Paper ID: 3644 AUTOMATIC GENERATION OF PHONE SETS AND LEXICAL TRANSCRIPTIONS, R. Singh, B. Raj, R. Stern, Carnegie Mellon University, USA.
15. Paper ID: 973 SELECTING ARTICLES FROM THE LANGUAGE MODEL TRAINING CORPUS, D. Klakow, Philips Research Laboratories, Germany.
16. Paper ID: 1367 SYNTACTIC HEADS IN STATISTICAL LANGUAGE MODELING, J. Wu, S. Khudanpur, The Johns Hopkins University, USA.
17. Paper ID: 1980 A UNIFIED APPROACH TO STATISTICAL LANGUAGE MODELING FOR CHINESE, J. Gao, H.-F. Wang, M. Li, K.-F. Lee, Microsoft Corporation, People's Republic of China.
18. Paper ID: 3730 POLYPHONE DECISION TREE SPECIALIZATION FOR LANGUAGE ADAPTATION, T. Schultz, University of Karlsruhe, Germany, A. Waibel, Carnegie Mellon University, USA.
19. Paper ID: 1326 ENHANCED LANGUAGE MODELLING WITH PHONOLOGICALLY CONSTRAINED MORPHOLOGICAL ANALYSIS, A. Fang, M. Huckvale, University College, London, United Kingdom.
20. Paper ID: 660 LONG RANGE LANGUAGE MODELS FOR FREE SPELLING RECOGNITION, F. Thiele, B. Rueber, D. Klakow, Philips Research Laboratories, Germany.

Session:            SP-P9
Time: 09:00 - 12:00, Friday, June 9, 2000
Location: Ballroom - Hilton Hotel (P6)
Title: TOPICS IN ASR - PART 1: ROBUSTNESS; PART 2: ACOUSTIC MODELING
Chair: Jean-Claude Junqua, Panasonic Laboratory, USA
1. Paper ID: 339 MODEL-BASED FEATURE ENHANCEMENT FOR NOISY SPEECH RECOGNITION, C. Couvreur, H. Van hamme, Lernout & Hauspie, Belgium.
2. Paper ID: 526 ROBUST SPEECH RECOGNITION USING NEAR-FIELD SUPERDIRECTIVE BEAMFORMING WITH POST-FILTERING, I. McCowan, Queensland University of Technology, Australia, C. Marro, L. Mauuary, France Telecom, France.
3. Paper ID: 784 NOISY SPEECH RECOGNITION USING NOISE REDUCTION METHOD BASED ON KALMAN FILTER, M. Fujimoto, Y. Ariki, Ryukoku University, Japan.
4. Paper ID: 819 STATISTICAL ESTIMATION OF UNRELIABLE FEATURES FOR ROBUST SPEECH RECOGNITION, P. Renevey, A. Drygajlo, Swiss Federal Institute of Technology, Switzerland.
5. Paper ID: 346 HANDS-FREE VOICE ACTIVATION OF PERSONAL COMMUNICATION DEVICES, S. Bou-Ghazale, A. Asadi, Conexant Systems Inc., USA.
6. Paper ID: 594 AN ACOUSTIC MEASURE FOR PREDICTING RECOGNITION PERFORMANCE DEGRADATION, K. Takeda, M. Kondo, F. Itakura, Nagoya University, Japan.
7. Paper ID: 839 LOW COMPLEXITY SPEAKER INDEPENDENT COMMAND WORD RECOGNITION IN CAR ENVIRONMENTS, S. Riis, Nokia Mobile Phones, Inc., Denmark, O. Viikki, Nokia Research Center, Finland.
8. Paper ID: 625 SPEECH RECOGNITION BASED ON SPACE DIVERSITY USING DISTRIBUTED MULTI-MICROPHONE, Y. Shimizu, S. Kajita, K. Takeda, F. Itakura, Nagoya University, Japan.
9. Paper ID: 989 A NOVEL APPROACH TO ROBUST SPEECH ENDPOINT DETECTION IN CAR ENVIRONMENTS, L.-S. Huang, C.-H. Yang, Panasonic Taiwan Laboratories Co., Ltd., Taiwan.
10. Paper ID: 1292 DETECTING THE END OF SPELLINGS USING STATISTICS ON RECOGNIZED LETTER SEQUENCES FOR SPELLED NAMES RECOGNITION, S. Hanel, D. Jouvet, France Telecom, France.
11. Paper ID: 1610 DECISION TREE BASED MANDARIN TONE MODEL AND ITS APPLICATION TO SPEECH RECOGNITION, Y. Cao, Y. Deng, H. Zhang, T. Huang, B. Xu, Chinese Academy of Sciences, People's Republic of China.
12. Paper ID: 1557 DETECTION OF PROSODIC WORD BOUNDARIES BY STATISTICAL MODELING OF MORA TRANSITIONS OF FUNDAMENTAL FREQUENCY CONTOURS AND ITS USE FOR CONTINUOUS SPEECH RECOGNITION, K. Hirose, K. Iwano, The University of Tokyo, Japan.
13. Paper ID: 713 PARAMETER OPTIMIZATION FOR VOCAL TRACT LENGTH NORMALIZATION, P. Dognin, A. El-Jaroudi, University of Pittsburgh, USA, J. Billa, GTE Internetworking/BBN Technologies, USA.
14. Paper ID: 2985 RETRIEVAL OF BROADCAST NEWS SPEECH IN MANDARIN CHINESE COLLECTED IN TAIWAN USING SYLLABLE-LEVEL STATISTICAL CHARACTERISTICS, B. Chen, H.-M. Wang, L.-S. Lee, Institute of Information Science, Academia Sinica, Taiwan.
15. Paper ID: 934 WORD-LEVEL RATE OF SPEECH MODELING USING RATE-SPECIFIC PHONES AND PRONUNCIATIONS, J. Zheng, H. Franco, F. Weng, SRI International, USA, A. Sankar, Nuance Communications, USA, H. Bratt, SRI International, USA.
16. Paper ID: 3800 SPECIALIZED ACOUSTIC MODELS FOR HYPERARTICULATED SPEECH, H. Soltau, A. Waibel, University of Karlsruhe, Germany.
17. Paper ID: 3264 ON THE USE OF VARIABLE FRAME RATE ANALYSIS IN SPEECH RECOGNITION, Q. Zhu, A. Alwan, University of California, Los Angeles, USA.
18. Paper ID: 739 A PROBABILISTIC UNION MODEL FOR SUB-BAND BASED ROBUST SPEECH RECOGNITION, J. Ming, F. Smith, The Queen's University of Belfast, United Kingdom.
19. Paper ID: 3726 ROBUST SPEECH RECOGNITION OVER IP NETWORKS, B. Milner, S. Semnani, BT, United Kingdom.
20. Paper ID: 4096 FAST SPEAKER ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR AUTOMATIC SPEECH RECOGNITION, S. Dupont, L. Cheboub, Polytechnique de Mons, Belgium.

Session:            SP-P10
Time: 13:30 - 15:00, Friday, June 9, 2000
Location: Ballroom - Hilton Hotel (P5)
Title: CONFIDENCE MEASURES/REJECTION
Chair: Mark Clements, Geogia Institute of Technology, USA
1. Paper ID: 1894 WORD AND PHONE LEVEL ACOUSTIC CONFIDENCE SCORING, S. Kamppari, T. Hazen, Massachusetts Institute of Technology, USA.
2. Paper ID: 1651 CONTEXTUAL CONFIDENCE MEASURES FOR CONTINUOUS SPEECH RECOGNITION, G. Hernandez-Abrego, J. Marino, Universidad Politecnica de Cataluña, Spain.
3. Paper ID: 2324 CONFIDENCE MEASURE AND INCREMENTAL ADAPTATION FOR THE REJECTION OF INCORRECT DATA, N. Moreau, D. Charlet, D. Jouvet, France Telecom, France.
4. Paper ID: 1834 ROBUST OUT-OF-VOCABULARY REJECTION FOR LOW-COMPLEXITY SPEAKER INDEPENDENT SPEECH RECOGNITION, C. Broun, W. Campbell, Motorola, USA.
5. Paper ID: 3958 META-MODELS FOR CONFIDENCE ESTIMATION IN SPEECH RECOGNITION, S. Dasmahapatra, S. Cox, University of East Anglia, United Kingdom.
6. Paper ID: 3148 EVALUATION OF VARIOUS CONFIDENCE-BASED STRATEGIES FOR ISOLATED WORD REJECTION, E. Tsiporkova, F. Vanpoucke, H. Van hamme, Lernout & Hauspie, Belgium.
7. Paper ID: 1782 USE OF WORD LEVEL SIDE INFORMATION TO IMPROVE SPEECH RECOGNITION, D. Vergyri, The Johns Hopkins University, USA.
8. Paper ID: 2338 CONFIDENCE MEASURE BASED LANGUAGE IDENTIFICATION, F. Metze, T. Kemp, T. Schaaf, T. Schultz, H. Soltau, University of Karlsruhe, Germany.
9. Paper ID: 1966 A NEW KEYWORD SPOTTING APPROACH BASED ON ITERATIVE DYNAMIC PROGRAMMING, M. Silaghi, Swiss Federal Institute of Technology, Lausanne, Switzerland, H. Bourlard, Dalle Molle Institute of Perceptual Artificial Intelligence, Switzerland.
10. Paper ID: 1006 FRAME DISCRIMINATIVE AND CONFIDENCE-DRIVEN ADAPTATION FOR LVCSR, F. Wallhoff, D. Willett, G. Rigoll, Gerhard-Mercator-University Duisburg, Germany.

Session:            SP-P11
Time: 13:30 - 15:00, Friday, June 9, 2000
Location: Ballroom - Hilton Hotel (P6)
Title: SPEECH ENHANCEMENT II
Chair: Richard Cox, AT&T Laboratories, USA
1. Paper ID: 156 AN ADAPTIVE SUBSPACE APPROACH FOR SPEECH ENHANCEMENT, S. Gazor, A. Rezayee, Queen's University, Canada.
2. Paper ID: 674 NARROWBAND TO WIDEBAND CONVERSION OF SPEECH USING GMM BASED TRANSFORMATION, K.-Y. Park, H. Kim, Pusan National University, South Korea.
3. Paper ID: 705 SIGNAL/NOISE KLT BASED APPROACH FOR ENHANCING SPEECH DEGRADED BY COLORED NOISE, U. Mittal, N. Phamdo, State University of New York at Stony Brook, USA.
4. Paper ID: 1266 LOW-BAND EXTENSION OF TELEPHONE-BAND SPEECH, G. Miet, Philips Consumer Corporation, France, A. Gerrits, Philips Research Laboratories, The Netherlands, J.-C. Valière, CNRS, France.
5. Paper ID: 1833 A HYBRID SPEECH ENHANCEMENT SYSTEM BASED ON HMM AND SPECTRAL SUBTRACTION, M. Ghoreishi, H. Sheikhzadeh, AmirKabir University of Technology, Iran.
6. Paper ID: 2935 ENHANCEMENT OF SPEECH BASED ON NON-PARAMETRIC ESTIMATION OF A TIME VARYING HARMONIC REPRESENTATION, S. Dubost, O. Cappe, Ecole Nationale Superieure des Telecommunications, France.
7. Paper ID: 3026 INTEGRATED NOISE REDUCTION AND ECHO CANCELLATION FOR IS-136 SYSTEMS, F. Basbug, K. Swaminathan, S. Nandkumar, Hughes Network Systems, USA.
8. Paper ID: 268 AN IMPROVED CUMULANT-BASED BLIND SPEECH SEPARATION METHOD, Y. Su, L. He, R. Yang, Intel Corporation, People's Republic of China.
9. Paper ID: 3709 IMPULSIVE NOISE SUPPRESSION USING NEURAL NETWORKS, I. Potamitis, N. Fakotakis, G. Kokkinakis, University of Patras, Greece.
10. Paper ID: 3782 QUANTILE BASED NOISE ESTIMATION FOR SPECTRAL SUBTRACTION AND WIENER FILTERING, V. Stahl, A. Fischer, R. Bippus, Philips Research Laboratories, Germany.

Go to top of the page

Go to Schedule of Sessions