S65 1374 Page 1 of 55
`
`GOOGLE EXHIBIT 1009
`
`Osy
`
`HN
`
`au
`
`Page 1 of 55
`
`GOOGLE EXHIBIT 1009
`
`

`

`1996 IEEE International Conference on Acoustics,
`Speech, &Signal Processing
`
`Conference Proceedings
`
`May7 - 10, 1996
`Atlanta, Georgia USA
`
`Institute of Electrical and Electronic Engineers
`
`ICASSP- 96
`Atlanta
`
`AVYTTTTIom |
`
`Sponsored bythe
`Signal Processing Society of the
`
`Page 2 of 55
`
`Page 2 of 55
`
`

`

`LCASS#)
`
`
`The 1996 IEEE International Conference on
`Acoustics, Speech, and Signal Processing
`Conference Proceedings
`_
`
`»
`
`Sponsored by the Signal Processing Society of the Institute of Electrical and
`Electronics Engineers
`
`May 7-10, 1996
`Marriott Marquis Hotel
`Atlanta, Georgia, USA
`
`Page 3 of 55
`
`Page 3 of 55
`
`

`

`The 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing
`Conference Proceedings
`
`Copyright and Reprint Permission: Abstracting is permitted with credit to the source. Libraries are permitted to photocopy
`beyondthe limit of U.S. copyright law for private use of patrons those articles in this volumethat carry a codeat the bottom
`ofthe first page, provided the per-copy fee indicated in the codeis paid through Copyright Clearance Center, 222 Rosewood
`Drive, Danvers, MA 01923. For other copying, reprint or republication permission, write to IEEEa
`Ci =
`[KIEE HY
`_
`YO
`65_T3%,
`V DIGG bE
`
`Copyrights Manager, IEEE Service Center, 445 Hoes Lane, P.O. Box 1331, Piscataway, NJ
`08855-1331. All rights reserved. Copyright 1996by the Institute of Electrical and Electronics
`Engineers, Inc.
`
`96CH35903
`IEEE Catalog Number:
`ISBN 0-7803-3192-3 (softhound)
`ISBN 0-7806-3193-1 (casebound edition)
`ISBN 0-7803-3194-X (microfiche)
`ISBN 0-7803-3195-8 (CD-ROM)
`Library of Congress:
`84-645 139
`
`Additional Proceedings (hard-copy and CD-ROM)maybe ordered from:
`
`IEEE Service Center
`445 Hocs Lane
`P.O, Box 1331
`Piscataway, NJ 08855-1331
`1-800-678-IEEE
`
`i
`
`Page 4 of 55
`
`Page 4 of 55
`
`

`

`Volume 1
`
`TABLE OF CONTENTS
`
`SP1 Robust Recognition: Signals and Features
`Feature Parameter Curve Method for High Performance NN-based Speech Recognition .........scssssseersssreencseeeserenenensnsensns I-1
`D. Chen, S. Zhu, T: Huang - Chinese Academy of Sciences, China
`
`Volume I
`
`On the Use of Residual Cepstrum im Speech Recognition—.....cccsssceesscccsusesereeusereuanenseeeseueeeeeussesenseenensees sisdebesebenesexeass1-5
`J. He, L. Liu, G. Palm - University of Ulm, Germany
`
`RobustDistant Talking Speech Recognition—....sssecccessseseeesnecsenees SetueddsevaaaacerNeaaTeeae's Serer ere ress sescvccceseveseeeol-21
`Q. Lin, C. Che, D. Yuk, L. Jin - CAIP Center, Rutgers University, USA
`B. Vries, J. Pearson - David SarnoffResearch Center, USA
`J. Flanagan - Rutgers University, USA
`
`HMM.-BasedSpeech Recognition Using State-Dependent, Linear Transforms on Mel-Warped DFT Features
`C. Rathinavelu, L. Deng - University of Waterloo, Canada
`
` ...ssssccecessevseees I-9
`
`Mixed Malvar-Wavelets for Non-Stationary Signal Representation .......00sssse0e+ ibid pahdoases ddsndeetuscndaennsepasenthanasspicasssatessl-13
`J. Thripuraneni, W. Lou, V. DeBrunner - The University of Oklahoma, USA
`
`Experiments on a Parametric Nonlinear Spectral Warping for an HMM-based Speech Recognizer ...........ssscccesesccsesoveeeee I-L7
`D. Mashao - Brown University, USA
`
`Time-Frequency Representation Based Cepstral Processing For Speech Recognition .........ssssscccecesseseeesseceessevensanseeeasee I-25
`A. Fineberg, K. Yu - Motorola Lexicus, USA
`
`Knowledge-Based Parameters for Speech HMM Recognition ...........ccececsersentesee seelanes STP TTTT saaaaanesenaewesaseaieas seeeeseeed-29
`C. Espy- Wilson, N. Bitar - Boston University, USA
`oe
`
`A PhonemeSimilarity Based ASR Front-End .....sccsscesecsseeensneceeeanecerenseeeseneurssenseeeteuesnseneuaneneneceueseteeeecesssseeesseesees «I-33
`T. Applebaum, P. Morin, B. Hanson - Speech Technology Laboratory, USA
`
`A Model of Dynamic Auditory Perception andits Application to Robust Speech Recognition ....4......0..sesesssseseesreenssenseeneI-37
`B. Strope, A. Alwan - University of California at Los Angeles, USA
`
`SP2 Robust Recognition: Large Vocabulary
`Independent Calculation of Power Parameters on PMC Method............. debaeebaue haeelendbancuersdetebencis Wa tiaTeTbias te tebaeaTETeRats:[-41
`Hf. Yamamoto, M. Yamada, T. Kosaka, ¥. Komori, ¥. Ohora - Canon Inc., Japan
`
`Noisy Speech Recognition Using Variance Adapted Likelihood Measure—...csssesssecssssveneccseenscseesensesssnsseserseseeneesssenseses “G5
`J. Chien, L. Lee, H. Wang - National Tsing Hua University, ROC
`
`An Improved Noise Compensation Algorithm for Speech Recognition in Noise .....sscsssseecsseserenerersesseveenensensensserenssereneesd-AO
`R. Yang, P. Haavisto - Nokia Research Center, Finland
`
`Improved Speech Recognition via Speaker Stress Directed Classification ..cccccescsesesecsseensecnecsveceeensevenensresasseeeeeesecnaeeee1-53
`B. Womack, J. Hansen - Duke University, USA
`
`High-Accuracy Connected Digit Recognition for Mobile Applications
`S. Gupta, F Soong, R. Haimi-Cohen - AT&T Bell Labs, USA
`
`..ccccccesesecenseecuseeuceeuseseeeeeersuseseneeeeeeaeeneneaseeeaazerI-57
`
`Feature Extraction Based on Zero-Crossings with Peak Amplitudes for Robust Speech Recognition in Noisy Environments... I-61
`D. Kim, J. Jeong, J. Kim, S. Lee - Korea Advanced Institute of Science and Technology, ROK
`
`Improving Environmental Robustness in Large Vocabulary Speech Recognition .......:+s000+ sePeNvereusuevereeneneevausesereesserenens 1-65
`P. Woodland, M. Gales, D, Pye - Cambridge University, UK
`
`Noise and Room Acoustics Distorted Speech Recognition by HMM Composition ....sisscssssesseensecesssssereeeesssvessseneeesserenneedQ9
`S. Nakamura, T. Takiguchi, K. Shikano - Nara Institute of Science and Technology, Japan
`
`Developments in Continuous Speech Dictation Using the 1995 ARPA NAB News Task ....cssccssccssreeeesseeeseneneenseeeeereesseres «I-73
`J. Gauvain, L. Lamel, G. Adda, D. Matrouf - LIMSI-CNRS, France
`
`Evaluation of the Root-Normalized Front-End (RN-LFCC) for Speech Recognition in Wireless GSM Network Environments I-77
`P. Lockwood, S. Dufour, C. Glorion - MATRA Communications, France
`
`Page 5 of 55
`
`Page 5 of 55
`
`

`

`VolumeI
`[aecacoy
`
`SP3 Speaker Recognition
`Speaker Background Models for Connected Digit Password Speaker Verification—.ssssseseesssrasenssernensrerereess eaeeeeee nesI-81
`A. Rosenberg, S. Parthasarathy - AT&T Bell Laboratories, USA
`
`CohortSelection and Word GrammarEffects on Speaker Recognition .....sssccceseeeseerenenensans oad hayannaden sscuanctennen seeneeneeree el=B85
`J. Colombi, D. Ruck - AFIT/ENG, USA,
`T. Anderson - AL/CFBA, USA,
`S. Rogers - AFIT/ENG, USA,
`M. Oxley - AFIT/ENC, USA
`
`Discriminative Training of GMM for Speaker Identification .........csssesccnseeteoneesescausonscasccesssguuaqavensnssnvgsunsencsssdiiii .-. 1-89
`C. Martin Del Alamo, J. Caminero Gil, C. De La Torre, L. Hernandez Gomez - Telefonica I+D, Spain
`Subword-based Text-dependent Speaker Verification System with User-Selectable Passwords—..sssssssssseseseserersennnrnnanens veee1-93
`M. Sharma, R. Mammone - Rutgers University, USA
`
`Robust Methods of Updating Model and A Priori Threshold in Speaker Verification
`T. Matsui, T. Nishitani, S. Furui - NTT Human Interface Laboratories, Japan
`
`...sessecssesesssessaseseneenes Sewbeaensaaaewaveene1-97
`
`A FurtherInvestigation of AR-Vector Models for Text-Independent Speaker Identification ..........secccccsreseeserrenneenrenaans I-101
`I. Magrin-Chagnolleau, J. Wilke, F. Bimbot - CNRS, France
`
`Speaker Identification via Support Vector Classifiers ........sccscsssnsessesseeeetenes sesbesssaseeeresaeys ceaseeeesenceceetsenerenenseeeeeeese n=LOS
`M. Schmidt - BBN, USA
`
`Speaker Verification Using Mixture Likelihood Profiles Extracted from Speaker Independent Hidden Markov Models
`A. Setlur, R. Sukkar, M. Gandhi - AT&T Beil Laboratories, USA
`
`......1-109
`
`The Effects of Handset Variability on Speaker Recognition Performance: Experiments on the Switchboard Corpus ......... 1-113
`D. Reynolds - MIT Lincoln Laboratory, USA
`
` ......:ss0csessseesenesneees sasbesesnensceveusssusensss neseuaenageeasyyeiias sussecesecesececssoeh@117
`Speaker Recognition in Reverberant Enclosures
`P. Castellano, §. Sridharan, D. Cole - Signal Processing Research Centre, Australia
`
`Speech Recognition: Noise and Environment
`SP4
`Using a Transcription Graph for Large Vocabulary Continuous Speech Recognition ..........ssseeeeereeeneresas eeaseeeeeneesceneeees -I-121
`Z. Li, D, O'Shaughnessy - INRS-Telecommunications, Canada
`Fast and Accurate Recognition ofVery-Large-Vocabulary Continuous MandarinSpeech for Chinese Language with Improved
`Segmental Probability Modeling ........ sibaas vias bie toueks! sn WAM eR WA MeNeaNATENDAES ONaReNEMAEREET EABOcoee seceescrecescsevesscsecsccsessssecesevalLZ5
`J. Shen, S. Hwang - National Taiwan University, ROC
`L, Lin-shan - Academia Sinica, ROC
`
`Decoding Optimal State Sequence with Smooth State Likelihoods.......... es cncavecesssescaseusagsausasarecarauscererssessensntanee anaaeven 1-129
`I. Zeljkovic - AT&T Bell Laboratories, USA
`
`Improvements on the Pronunciation Prefix Tree Search Organization .......seccsccssesssssssvstsesveressseeassssseoonnssseversrrereseenes1-133
`FE. Alleva, X. Huang, M. Hwang - Microsoft Corporation, USA
`
`Minimizing Search Errors Due to Delayed Bigrams in Real-Time Speech Recognition Systems
`M. Woszczyna - University of Karlruhe, Germany, M. Finke - University of Karlsruhe, Germany
`
`......:ssscseessesssessrereess seveee 1-137
`
`Real-Time Recognition of Broadcast Radio Speech .........064 peeecaseneapecscccaesseconecesenreoonersroncssssessesceesauan songs Fiveveapyievel1-141
`G. Cook, J. Christie, P. Clarkson, S. Cooper, M. Hochberg, D. Kershaw, R. Logan, S. Renals, A. Robinson,
`C. Seymour, S. Waterhouse, P. Zolfaghari - Cambridge University, UK
`Spontaneous Dialogue Speech Recognition Using Cross-Word Context Constrained Word Graphs..... secencaavanebbeavaeba sevesed-145
`T. Shimizu, H. Yamamoto, H. Masataki, S. Matsunaga, Y. Sagisaka - ATR - ITL, Japan
`
`......... oa sadeunietaviead sisieicuasvaesswachoanaesseveeee [-149
`Efficient Evaluation of the LYVCSR Search Space Using the NOWAYDecoder
`S. Renals - University of Sheffield, UK, M. Hochberg - University of Cambridge, UK
`Developments in Large Vocabulary, Continuous Speech Recognition of German ......... aqanananpeenagnasiendiandbepanbe Sdaaacessnes . 1-153
`M. Adda-Decker, G. Adda, L. Lamel, J. Gauvain - LIMSI-CNRS, France
`
`Speech Recognition on Mandarin Call Home: A Large-Vocabulary, Conversational, and Telephone Speech Corpus_....++..1-157
`ELiu, M. Picheny, P. Srinivasa, M. Monkowski, J. Chen - IBM T.J. Watson Research Center, USA
`
`xii
`
`Page 6 of 55
`
`Page 6 of 55
`
`

`

`Volume I
`2Seolaea.
`
`Multilingual Stochastic n-Gram Class Language Models_......:.ssccsecccorsootonsnseausenansusvencceassasesseaceeesssseeeaaeeeeeegsaeenauee 1-161
`M. Jardino - LIMSI-CNRS, France
`
`SP5 Speech-Recognition: Language Modeling IIl
`
`A Variable-Length Category-Based N-Gram Language Model
`T. Niesler, P. Woodland - Cambridge University, UK
`
` ......ssscsssoscessssevecsctersescerensectsncscusteccecseseuccecescucersuanes 1-164
`
`Improving N-Gram Models by Incorporating Enhanced Distributions ............000.. orn sbesseceseceseserccencreccacsensoccess bbdaued 1-168
`P. OBoyle, J. Ming, J. McMahon, J. Smith - Queen's University of Belfast, UK
`
`A Novel Word Clustering Algorithm Based on Latent Semantic Analysis ......:sssecsesssencssccnensceteseenseenenesceenensctecescuanaaseeT-172
`J. Bellegarda, J. Butzberger, Y. Chow, N. Coccaro, D. Naik - Interactive Media Group, Apple Computer USA
`
`Statistical Natural Language Understanding.......s0ssscssseresssessecerenee Aseeeeeeeeaseneeransenunrsesenaes
`sevessscenecssceeeeasl=176
`M. Epstein, K. Papineri, S. Roukos, T. Ward - IBM TJ. Watson Research Center, USA,S.‘Della Pietra - Renaissance:Technologies,"USA
`Clustering Wordsfor Statistical Language Models Based on Contextual Word Similarity .......s.cccesssseseeseseneesee 1-180
`A. Farhat, J. Isabelle, D. O'Shaughnessy - INRS-Telecommunications, Canada
`
`Domain Word Translation By Space-Frequency Analysis of Context Length Histograms ............ seseeeneeeereneeeesecesarseseeeeel-LO4
`P. Fung - Columbia University, USA
`
`Variable-Order N-Gram Generation by Word-class Splitting and Consecutive Word Sequence Grouping ........sseseeseseres oes 1-188
`H. Masataki, Y. Sagisaka - ATR Interpreting Telecommunications Research Laboratories, Japan
`
`Back-off Method for N-Gram Smoothing Based on Binomial Posteriori Distribution ...........0ccssscostesvessscscanscens sacocccsvceee 1-192
`T. Kawabata, M. Tamoto - NTT Basic Research Labs, Japan
`
`Ergodic Multigram HMMIntegrating Word Segmentation and Class Tagging for Chinese Language Modeting oovdébersueriie 1-196
`
`H. Law, C. Chan - The University of Hong Kong, Hong Kong
`
`SP6 Low-Rate Speech Coding
`A 2.4 kbit/s MELP Coder Candidate for the New U.S. Federal Standard .........:.cccsccccseeseseeesscyecsessscsannscccsancensecasseeenes 1-200
`A, McCree - Texas Instruments, USA, K. Truong - Atlanta Signal Processors, Inc, USA, E. George -“Texas Instruments, USA
`T. Barnwell - Atlanta Signal Processors, Inc., USA, V. Viswanathan - Texas Instruments, USA
`
`Harmonic- Stochastic eXcitation (HSX) Speech Coding Below 4Kbits ...,....ss0sssseeessssueeeee acsusneecdenscsnenscerssseascesenssscccel~204
`C. Laflamme, R. Salami, R. Matmti, J. Adoul - University of Sherbrooke, Canada
`
`A High Quality MBE-LPC-FE Speech Coderat 2.4kbps and 1.2kbps_.....s.sseeeseee dae igavsasedavaceeswonssaccrsncasscossesersceaerssensl-20S
`T. Wang, K. Tang, C. Feng - Tsinghua University, China
`
`A Low-Complexity Waveform Interpolation Coder .......scessccserseressesenanes cannes TURPEAEENUG DOR eEHugNarNReAeKancrdesesanenveqeenqayarenel-212
`W. Kleijn, ¥. Shoham, D. Sen, R. Hagen - AT&T Bell Laboratories, USA
`
`Mixed-Domain Codingof Speech at 3 KDpS ...csssssseeseseereeess Sbencen head enadseadeeaveccaadvensdaansbbasascieebeacdiebedidudbedeacstebedss eeel-216
`J. De Martin - Politecnico di Torino, Italy
`A. Gersho - University of California at Santa Barbara, USA
`
`Source Driven/Variable Bit Rate Protoype Interpolation Coding ......ssscssserevesssenessoneeenens deneteveuensanteennsveasennoaretesttensel-220
`C. Xydeas, B. Cao - University ofManchester, UK
`
`A New Approachto Very Low-Rate Speech Coding Using Temporal Decomposition ..........cssssssceeeecsessceneeerneseeseesssesees1-224
`S. Ghaemmaghami, M. Deriche - Queensland University of Technology, Australia
`
`A Variable Frame Pitch Estimator and Test Results ....,......scscvessossscsesenercsnecceceecseecnenseeceseanercessssdeesenseeeseaneretesseecees1-228
`X. Qian, R. Kumaresan - University ofRhede Island, USA
`
`Robust Method of Measurement of Fundamental Frequency by ACLOS - AutoCorrelation of Log Spectrum -
`N. Kunieda, T. Shimamura, J. Suzuki - Satiama University, Japan
`
`........ssseesee0J-232
`
`...........sccessseseeessneeesensreenensnneverensrepapereeenencvaneusnaenenenetstanseeseeeseereneneneene1-236
`Lag-Indexed VQ for Pitch Filter Coding
`5. McClellan - University ofAlabama-Birmingham, USA
`J. Gibson - Texas A&M University, USA
`
`xii
`
`Page 7 of 55
`
`Page 7 of 55
`
`

`

`Volume I
`[aneeeaeee
`SP7 Wideband Coding and Emerging Techniques
`Embedded Algebraic Vector Quantizer (EAVQ) with Application to Wideband Speech Coding «......ccssssseeseseeeseeseetsecsees 1-240
`M. Xie, J. Adoul - University of Sherbrooke, Canada
`
`The Two-Dimensional Discrete Cosine Transform Applied to Speech Data ..........ccseccecseenseerennterstenessesssssussesenessceweneos 1-244
`L. Baghai-Ravary, S. Beet, M. Tokhi - University of Sheffield, UK
`
`Real-Time High Accurate Cell Loss Recovery Technique For Speech Over ATM Networks
`K. Matsumoto - NTT LSI Laboratories, Japan
`
`.....sssssssecsessseseeesssesssneeeeeesees1-248
`
`Predictive Fractal Interpolation Mapping: Differential Speech Coding at Low Bit Rates ........csssccssssesssseessssssreorssonsaeses1-251
`Z. Wang - University of Waterloo, Canada
`
` ..........:scsecessrseenensneeesasacessessccensscreneeesusseseuseeesanaaes1-255
`16kbit/s Wideband Speech Coding Based on Unequal Subbands
`J. Paulus, J. Schmitzler - IND, Aachen University of Technology, Germany
`
`Low Delay IIR QMFBankswith High Perceptive Quality for Speech Processing
`T. Kleinmann, A. Lacroix - University of Frankfurt, Germany
`
` .......sseressssssesssessessterescescssnensececeeeaaen1-259
`
`Demodulators for AM-FM Models of Speech Signals: A Comparison—...ssscserssesscceeerseensssseneneseseneaeenccesansaneunensaucunnsens 1-263
`S. Lu, P. Doerschuk - Purdue University, USA
`
`Synthesis and Coding of Continuous Speech with the Nonlinear Oscillator Model
`G. Kubin - Vienna University of Technology, Austria
`
`........-.ccsssescsssssssersessensessseennsnenenenseas1-267
`
`Variable Frame Rate Parameter Encoding via Adaptive Frame Selection Using Dynamic Programming—..ssssssrsssseseeessnees I-271
`E. George, A. McCree, V. Viswanathan - Texas Instruments, Inc., USA
`
`Transform Predictive Coding of Wideband Speech Signals ............sssccccsssscssssersscaserseccessesecsarsveasareceseasssensassseeseneaee-275
`J. Chen - AT&T Bell Labs, USA
`D. Wang - Georgia Institute af Technology, USA
`
`SP8__Topic Identification and Spoken Information Retrieval
`A System for Unrestricted Topic Retrieval From Radio News Broadcasts—....sssssesssereseeevsnnsssnerseeserensoecsscsooeasenseeeas eres1-279
`D. James - Union Bank of Switzerland, Switzerland
`
`Automated Generation of N-Best Pronunciations of Proper NOUNS—...ssecccerereeceensssceeeenseeeesseeveeeasseeaenererensmenreenennseanee1-283
`N. Deshmukh, M. Weber, J. Picone - Mississippi State University, USA
`
`An Efficient Voice Retrieval System for Very-Large-Vocabulary Chinese Textual Databases with a Clustered Language Model «1-287
`S. Lin - National Taiwan University, ROC
`L. Chien, K. Chen, L. Lee - Academia Sinica, ROC
`
`Concept-based Phrase Spotting Approach for Spontaneous Speech Understanding—.......sssecereeereressreeneeeeeeeesereeaenenenens1-291
`T. Kawahara, N. Kitaoka, S. Doshita - Kyoto University, Japan
`
`A Dictionary-Based Method for Determining Topics in Text and Transcribed Speech I-295
`P. Schone, D. Nelson - DepartmentofDefense, USA
`
`Keyword Spotting for Video Soundtrack Indexing ....ccssssseesersrrovserserssnrvenssecenttcenenseseaanensgeenseseenaaceseceusequcacauseaenees1-299
`P. Gelin, C. Wellekens - Institut Eurecom, France
`
`Improvements in Switchboard Recognition and Topic Identification ..........1..:ssccrereessenenesneseanensnseemneserenenassauamaannns sree1-303
`B. Peskin, S, Connolly, L. Gillick, 5. Lowe, D. McAllaster, V. Nagesha, P. van Mulbregt, S. Wegmann - Dragon Systems, Inc., USA
`
`Statistical Models for Topic Identification Using Phoneme Substrimgs
`J. Wright - University of Bristol, UK
`M. Carey, E. Parris - ENSIGMA Limited, UK
`
`..........scccosessesesseeeresesenneeseeanaaaesenueaaeeeeaneanens +«+.1-307
`
`.....1.:.seesseuee
`Robust Talker-Independent Audio Document Retrieval
`G. Jones, J. Foote, K. Spark Jones, S. Young - Cambridge University, UK
`
`seeeeeneneneceeeeeeaeeeanerauausesueneaaesrenanesten tans sedeessenee I-311
`
`Unsupervised Topic Clustering of Switchboard Speech Messages ......ssscccscosocosecossonsestsensesenensserennsarenenanaveneemsnnsnmacree1-315
`B. Carlson - MIT Lincoin Laboratory, USA
`
`xiv
`
`Page 8 of 55
`
`Page 8 of 55
`
`

`

`Volume I
`SSSeSenee
`SP9 Robust Recognition: Compensation and Normalization
`Speaker Recognition and Speaker Normalization by Projection to Speaker Subspace
`........... sists WeacetenstiatanycerangaiepenTe 1-319
`¥. Ariki, S. Tagashira, M. Nishijima - Ryukoku University, Japan
`
`...cccccccsccenscccnnccssccecesaccceresseseneneeesicddeceucsaudeeuvcvnbsevssagseceersvouscl=aaed
`Compensated Mel Frequency Cepstrum Coefficients
`R. Vergin, D. O'Shaughnessy, V. Gupia - IWRS-Telecommunications, Canada
`
`Adaptation Method Based on HMM Composition and EM Algorithm ....... sid suanesdsyeqedsasyererere paces sesasscesseasssnenenseesnssd@Gol
`Y, Minami, S. Furui - NTT Human Interface Laboratories, Japan
`
`SNR-Normalisation for Robust Speech Recognition ......cscssscsecssssesevenscseeenencseeeaeseceeesscceaeeesecsuasshesuanenecuenenseaeeseeenene T-331
`T. Claes, D, Van Compernolle - KU Leuven, Belgium
`
`Towards Robustness to Fast Speech in ASR vissessssscsessseseassesscnecseesssesecseeseaae db wev areas uebaenvoasaatae renee T YET 1-335
`N. Mirghafori, E. Foster, N. Morgan - International Computer Science Institute, USA
`
`Speaker Normalization on Conversational Telephone Speech ......cccsscscscscseccecsscessecsecsnccconanseeeensescsnsserereneesteceeeseeeesseL=339
`S. Wegmann, D. McAllaster, J. Orloff, B. Peskin - Dragon Systems, USA
`
`Speaker and Gender Normalization for Continuous-Density Hidden Markov Models_
`A. Acero, X. Huang - Microsoft Corporation, USA
`
`....... eeaseuspensyense pens ssensecesusecsesgensdtae.
`
`A Parametric Approach to Vocal Tract Length Normalization
`E. Eide, H. Gish - BBN Systems and Technologies, USA
`
`...ccccccccsseccecsescsueescsnsenessesenesesseasseeereaeseueee Wiss enecssves «1-346
`
`A Study on Speech Recognition for Children and the Elderly ...............0ssssse0 Spossscecesuateusttss Se oosesccdadassdauas Keaweaspaadel*QO
`J. Wilpon - AT&T Bell Labs, USA
`C. Jacobsen - TeleDanmark/Jydsk Telefon, Denmark
`
`Speaker Normalization Using Efficient Frequency Warping Procedures
`L. Lee - Massachusetts Institute of Technology, USA
`R. Rose - AT&T Bell Laboratories, USA
`
`seesaneneneceeenssaseneneesennsseeeaseessenaseaiensensesgas seve353
`
`Speech Synthesis
`SP10
`A Fast Stochastic Parser for Determining Phrase Boundaries for Text-to-Speech Synthesis
`R. Sharman - IBM Laboratories, U.K.
`J. Wright - University of Bristol, U_K,
`
`.
`...scsssesecescscsssessceececseseessceseesdG57
`
`Speech Concatenation and Synthesis Using an Overlap-add Sinusoidal Model
`M. Macon, M. Clements - Georgia Institute of Technology, USA
`
`......+ sssveuveresssersessseessserssessserssesscesssessanl-GOd
`
`Voice Conversion Using Partitions of Spectral Feature Space ....sse0s000 seb beds UediexedkeatedeweatetsiadebadanteaNatevead vecdvaaeversvecenvil-3O65
`W. Verhelst, J. Mertens - Vrije Universiteit Brussel, Belgium
`
`Determination of Vocal-Tract Shapes from Formant Frequencies Based on Perturbation Theory and Interpolation Method 1-369
`Z. Yu, P. Ching - Chinese University of Hong Kong, Hong Kong
`
`Unit Selection in a Concatenative Speech Synthesis System Using a Large Speech Database ......ssssssssscssssseccsssscesscessesessel373
`A. Hunt, A. Black - ATR Interpreting Telecommunications Research Laboratories, Japan
`
`Parametric Hybrid Source Models for Voiced and Voiceless Fricative Consonants ...ssssssssssssseessscseeessssssessavecsensasansessceel-O77
`5. Narayanan - AT&T Bell Laboratories, USA
`A. Alwan - University of California at Los Angeles, USA
`
`High Quality Speech Synthesis Using Context-Dependent Syllabic Units .......cessssesesscesseseneeeaes eee tereseraeeeereeneeererelOO
`T. Saito, Y. Hashimoto, M. Sakamoto - IBM, Japan
`
`Articulatory Copy Synthesis Using a Nine Parameter Vocal Tract Model .........c0ssesessecseeeseeeees isd esteancastiscewicereswesaeeiensel-3O5S
`C. Goodyear, D. Wei - University ofLiverpool, UK
`
`Speech Synthesis Using HMMswith Dynamic Features ...........csscsscsssscecscessenscnensnsvscntenetasuensenenensestersesepersesenanaeee 1-389
`T. Masuko, K. Tokuda, T. Kobayashi, S. Imai - Tokyo Institute of Technology, Japan
`
`Interpolating V/UV Mixture Functions of a Harmonic Model for Concatenative Speech Synthesis .......... seesserseeesnserenrssed#SOS
`K. Lam, C. Chan - City University of Hong Kong, Hong Kong
`
`xv
`
`Page 9 of 55
`
`Page 9 of 55
`
`

`

`Volume I
`Sea|
`SP11
`Speech Recognition: Language Modelling I
`An Efficient Top-Down Parsing Algorithm for Understanding Speech by Using Stochastic Syntactic and Semantic Models ...1-397
`H. Stahl, J. Muller, M. Lang - Munich University of Technology, Germany
`
`..... oc eantenbaanas dbendveeaesdadeensenens se neueeaneeesenseasenenerenensceses 1-401
`Data-Driven Discourse Modeling for Semantic Interpretation
`F. Caminero-Gil, J. Alvarez-Cercadillo, C. Crespo-Casas, D. Tapias-Merino - Telefonica 1+D, Spain
`
`Statistical Language Modeling for Speech Disfluencies
`A. Stolcke, E. Shriberg - SRI International, USA
`
`...secescsserceeeseerensnereeanseenee sabe Ute Uae beaaaTCeRe Cece TaRET ELE oer seveeeeeee1-405
`
`savesensesceseccscorsovccnsvecctsavenccsceracees eed409
`JANUSII-Translation of Spontaneous Conversational Speech ..ssesssseereeenseees
`A. Weibel, M. Finke, D. Gates, M. Wosczyna, M. Gavalda, T. Kemp, A. Lavie, L Levin, M."Maier- University ofKarlsruhe,“Germany
`
`Language Model Acquisition From a Text Corpus for Speech Understanding ..+ssss+eessrereerssenees seeeeensensenanenseeneeeseetensersod@413
`T. Matsuoka - NTT Human Interface Laboratories, Japan
`R. Hasson - Eurecom Institute, France
`M.Barlow, S. Furui - NTT Human Interface Laboratories, Japan
`
`A Class Based Language Modelfor Speech Recognition .........:ssesceesseeee et ecvesescees anna ReaaeeasewaebE scesdienerwenienedeneiernene1-416
`W. Ward, S. Issar - Carnegie Mellon University, USA
`
` ........cessrsesrersnveseesaccueseuasturreusiees1-419
`AnIntegrated Model of Acoustics and Language Using Semantic Classification Trees
`E. Noth, R. DeMori, J. Fischer, A. Gebhard, S. Harbeck, R. Kompe - Universitat Erlangen-Nurnberg, Germany
`R. Kuhn, H. Niemann, M. Mast - Centre de Recherche Informatique de Montreal, Canada
`
`Combining Stochastic and Linguistic Language Models for Recognition of Spontaneous Speech ............++ Ras MaDvieTesaeraese AALS
`W. Eckert, F Gallwitz, H. Niemann - Universitat Erlangen-Nurnberg, Germany
`
`Error Correction via a Post-Processor for Continuous Speech Recognition ......:..ccessecseeessevee savscebecsdsonsdivstusessessasacess 1-427
`E. Ringger, J. Allen - University ofRochester, USA
`
`Integration of Concept-Driven Semantic Interpretation with Speech Recognition ............ co eeensenane sscesonneenensecscnnesessssins1-431
`A. Nogai, ¥. Ishikawa, K. Nakajima - Mitsubishi Electric Corporation, Japan
`
`Speech Recognition Acoustic Modeling
`SP12
`A Second-Order HMM for High Performance Word and Phoneme-Based Continuous Speech Recognition ......1...ceeesereee . 1-435
`J.-F. Mari, D. Fohr, J.-C. Junqua - CRIN-CNRS & INRIA, France
`
`Evaluation of Segmental Unit Input HMM ....... sonvesestoscessensecesodhpeeneasanse seacevsceaeiisisie ersten sescacceenserevenel-4]39
`S. Nakagawa, K. Yamamoto - Toyohashi University of Technology, Japan
`
`Design of a Speech Recognition System Based on Non-Uniform Segmental Units
`M. Bacchiani - ATR Interpreting Telecommunications Research Laboratories, Japan
`M. Ostendorf - Boston University, USA
`Y. Sagisaka - ATR Interpreting Telecommunications Research Laboratories, Japan
`K. Paliwal - Griffith University, Australia
`
`..........+sidinada seibaadp iasuadsadeiniaecies sasseeenel-443
`
`Modeling Speech Variability with Segmental HMMS_........+seceeseeeeeeeeeseene SaaaaSaesiee cae NdaviaddenteedidedveseteusdthcteevsevsteteiasI-447
`W. Holmes, M. Russell - DRA Malvern, UK
`
`Context-Dependent Units for Vocabulary-Independent Spanish Speech Recognition .......+ssssssressserenensssereearerenensees vesee 16451
`L, Villarrubia, L. Gomez, J. Elvira, J. Torrecilla - Telefonica I+D, Spain
`
`Context-Dependent Acoustic Models For Chinese Speech Recognition ........... pee ececeercosseves ots creoceneseesen ditserederseoeseeseres- 1455
`B. Ma,T. Huang, B. Xu, X. Zhang, F. Qu - Chinese Academy of Sciences, China
`
`Automatic Recognition of Danish Natural Numbers for Telephone Applications ............ ssveaaceeree cee cvecec ctslasauesy saveseeeeeesebA59
`C. Jacobsen - TeleDanmark/Jydsk Telefon, Denmark
`J. Wilpon - AT&T Bell Laboratories, USA
`
`Explicit Modeling of Coarticulation in a Statistical Speech Recognizer ......cssssssssscssessecenenseceenseeeeeneeeesrsensenssaseseserens sed463
`R. Chen, L. Jamieson - Purdue University, USA
`
`Tied-Structure HMM Based on Parameter Correlation for Efficient Model Training .............+e1esseeseeeeeus pseaenaenseuaceencan® 1-467
`S. Takahashi, S. Sagayama - NTT Human Interface Laboratories, Japan
`A Semi-Continuous Stochastic Trajectory Model for Phoneme-Based Continuous Speech Recognition
`O. Siohan, ¥. Gong - CRIN-CNRS & INRIA Lorraine, France
`
`........0 sssnensevessseseel-471
`
`xvi
`
`Page 10 of 55
`
`Page 10 of 55
`
`

`

`Volume I
`|ieeee
`SP13
`Speech Coding Quality Assessment
`Automatic Evaluation of Speaker Recognizability of Coded Speech ........cccesseeeessceseceseneeeeeees steneeaeenencescereerenens soserenel=475
`K. Assaleh - Motorola, USA
`
`A Perceptually-Based Objective Measure for Speech Coders Using Abductive Network—......ec..seeeees0e édevedsensensensaasanieesd-479
`M. Meky, T. Saadawi - City University of New York, USA
`
`Objectively Measured Descriptors Applied to Speaker Characterization ......:ss:eesesssseneesTT Ter ery Te steseseeeseseeel483
`B. Necioglu, M. Clements, T. Barnwell - Georgia Institute of Technology, USA
`
`_........ diedeve teen caearaiTleineene eee se pdseesaeueecscsvecsusescucscsasseceseseel=497
`Objective Speech Quality Measure for Cellular Phone
`K. Lam, O. Au, C. Chan, K. Hui, S. Lau - Hong Kong University ofScience and Technology, Hong one
`
`Vector Quantization Techniques for Output-Based Objective Speech Quality ......css:sscneess Tbeaeueobechecneseneneses aeanecesenceesesl-491
`C. Jin, R. Kubichek - University of Wyoming, USA
`
`Objective Measures for Speech Quality Assessment in Wireless Communication’s ......:sesssvssecseceseneseccscnscscesecanscssecseecesd-495
`A. Bayya, M. Vis - US West Advanced Technologies, USA
`
`Performance Assessmentof4.8 kbit/s AMBE Coding Under Aeronautical Environmental Conditions.......ssssecsseceeseseaessses 1-499
`S. Campos Neto, F. Corcoran, J. Phipps, S. Dimolitsas - COMSAT, USA
`
`Normalization of Cellular Telephone Speech for Recognition by Adaptive Vector Quantization —.....csesssssssseesecasesececeeesseeel-SO3
`R. Rajasekaran, M. Sonmez - Texas Instruments, Inc., USA
`J. Baras - University ofMaryland at College Park, USA
`
`Speech Recognition Out-of-Vocabulary Modeling and Rejection
`SP14
`Efficient Decoding and Training Procedures for Utterance Verification in Continuous Speech Recognition| sevceneseecesoevceeerL-SO7
`E. Lleida, R. Rose - ATT Bell Laboratories, USA
`
`Confidence Measures for the SWITCHBOARD Database ........... sisbeedacedacseceedevusteacsuaes Fiipenebedspecasaaseceenpserenesserersers I-511
`S. Cox, R. Rose - AT&T Bell Labs, USA
`x
`
`A Phone-Dependent Confidence Measure for Utterance Rejection............+s0scse0e+ neg evi gesunyeNstevasdeesseeneusvesshervess socesereee T-515
`Z. Rivlin, M. Cohen, V. Abrash, T. Chung - SRI International, USA
`
`Utterance Verification of Keyword Strings Using Word-Based Minimum Verification Error (WB-MVE)Training_............1-516
`R. Sukkar, A. Setlur M. Rahim, C. Lee - AT&T Bell Laboratories, USA
`
`...........6 teveoceceveens WI-3585
`Discriminative Utterance Verification Using MinimumString Verification Error (MSVE) Training
`M. Rahim, C. Lee, B. Juang, W. Chou - AT&T Bell Laboratories, USA (at time ofprinting this paper wasplaced in Volume 6)
`Murray Hill, NJ, USA
`
`Fast Implementation Methods for Viterbi-based Word-Spotting
`K. Knill, S. Young - Cambridge University, UK
`
`..sccsccssessessssceaneueeee subiseadsde seanesdenarenneaieNcieaae ssesesenesD-522
`
`Improving Wordspotting Performance with Artificially Generated Data ......::cseeeccseeesecseeeneeseceeeeceeeeeets siuesvaectestssniee-I-526
`E. Chang, R. Lippmann- Corona Corporation, USA
`
`Modelling Unknown Wordsin Spontaneous Speechi......cc:sssccsssesernee ed euesvacaVonsucdabsesusecetqauevacss isagecsqansaunasacanepagersbsass 1-530
`T. Kemp - University of Karlsruhe, Germany
`A. Jusek - University of Bielefeld, Germany
`
`..........ccesscceeceesseeeeseveeaseres iSaeadkvaedcRuaceagesegeecdeespueceatetas 1-534
`Improved Modeling of OOV Wordsin Spontaneous Speech.
`P. Fetter, A. Kaltenmeier, T. Kuhn, P. Regel-Brietzmann- Research Center Daimler-Benz, Germany
`
`Two-Pass Strategy for Continuous Speech Recognition with Detection and Transcription of Unknown Words
`S. Matsunaga, H. Sakamoto - ATR Interpreting Telecommunications Research Laboratories, USA
`
` ...sssesssesseeeee-538
`
`SP15_ Topics in Speech Coding
`A Modified Generalised Lloyd Algorithm for VQ Codebook Design ..........c0ssssseecsscvescereoe oo cneNakenanes senessestenseneeneetsevens 1-542
`C. Chen, S. Koh, P. Sivaprakasapillai - Nanyang Technological University, Singapore
`
`RobustClassification of Speech Based on the Dyadic Wavelet Transform with Application to CELP Coding .....:0000seses00001-546
`J. Stegmann, G. Shroeder, K. Fischer - Deutsche Telekom, Germany
`
`xvii
`
`Page 11 of 55
`
`Page 11 of 55
`
`

`

`VolumeI
`eeePy|
`Optimal Wavelet Packets for Low-Delay Audio Coding ....++--+s--sss+seseeeeeseee svisbedaverevealaevacascuke ican 1-550
`P. Philippe, F. Mo