3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`AND TECHNOLOGY- Berlin. Germany, 21-23 September 1993
`
`EUROSPEECH 93
`
`EUROSPEECH '93
`
`PROCEEDINGS
`
`UB/TIB Hannover
`
`89
`
`~lilfil~lf~lilllllllllllllllllllillllll
`
`VOLUME2
`
`Petitioner Apple Inc.
`Ex. 1008, Cover
`
`

`

`EUROSPEECH 93 ·
`
`3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`AND .TECHNOLOGY- Berlin, Germany, 21-23 September 1993
`
`,,, :'' ,': ,~; ;;,?::' ::;:'?~~d:~~~77'~'
`
`21.23 Time-Varing Manner on Fonnant Trajectories of Chinese Diphthong
`- J.Cao, Chinese Academy of Social Sciences, Beijing, China
`
`Coffee Break:
`
`11.00 - 11.20 hrs
`
`PROCEEDINGS VOLUME 2
`
`Room A
`
`11.20 - 12.40 hrs
`
`Session 22: Speech Coding IV
`Time and Place:
`Chairperson: H. Leung, MIT, USA
`22.1 High-Quality Speech Coding at 2.4 Kbps Based on Time-Frequency Interpolation
`- Y. Shoham, AT&T Bell Laboratories, USA
`22.2 Coding of Speech Signal by Fractal Techniques
`- L. Marcato, E. Mumolo, Universita' di Trieste, Italy
`22.3 A New Reference Signal for Evaluating the Quality of Speech Coded at Low Bit-Rates
`- N. Asanuma, H. Nagabuchi, NIT Human Interface Lab, Telecommunication
`Networks Laboratories, Japan
`22.4 A Psychophysical Study of Fourier Phase and Amplitude Coding of Speech
`-C. Ma, D. 0' Shaughnessy, INRS-Telecommunications, Canada
`
`Room B
`
`Session 23: Phonetics ll
`11.20 - 13.00 hrs
`Time and Place:
`Chairperson: L. Nord, KTH Stockholm, Sweden
`23.1 Data-Driven Indentification of Poly- and Mono-Phonemes for Four European Languages
`- 0. Andersen(*), P. Dalsgaard(* ), W. Barry(**), (*) University of Aalborg, Denmark,
`(**) Universitiit des Saar/andes, Germany
`23.2 Reversible Letter-to-Sound Sound to-Letter Generation Based on Parsing
`Word Morphology
`- S. Hunnicutt, H. Meng, S. Seneff, V.W. Zue, MIT, USA
`23.3 The Role of Context in the Automatic Recognition of Stressed Syllables
`-J. Moore, P. Roach, University of Leeds, UK
`23.4 Metrical Structure and the Perception of Time-Compressed Speech
`-D. Young(*), G.T.M. Altmann(*), A. Cutler(**), D. Norris(**),(*) Sussex University,
`(**) MRC Applied Psychology Unit, Cambridge, UK
`23.5 Are Stress and Phonemic String Processed Separately? Evidence from Speech illusions
`- V. Pasdeloup, J. Morais, R. Kolinsky, Universite Libre de Bruxelles, Belgium
`
`Session 24: Prosody IT: Analysis and Modelling ofF 0 Contours
`Time and Place:
`11.20 - 13.00 hrs
`Chairperson: L. Boves, University of Nijmegen, The Netherlands
`24.1 On the Automatic Classification of Pitch Movements
`-L. ten Bosch, Institute for Perception Research, The Netherlands
`
`Roome
`
`735
`
`741
`
`745
`
`749
`
`753
`
`759
`
`763
`
`767
`
`771
`
`775
`
`781
`
`XXII
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxii
`
`

`

`3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`AND TECHNOLOGY- Berlin, Germany, 21-23 September 1993
`
`EUROSPEECH 93
`
`24.2 Modelling of Intonation Contours at the Sentence Level Using CHMMs and the 1961
`O'Connor and Arnold Scheme
`- U. Jensen(*), R. K. Moore(**), P. Dalsgaard(* ), B. Lindberg(*),
`(*) Aalborg University, Denmark,(**) Defence Research Agency Malvern, UK
`24.3 Automatic Recognition of Intonation from F0 Contours Using the
`Rise/Fall/Connection Model
`- P. Taylor, ATR Interpreting Telecomm. Labs, Kyoto, Japan
`24.4 A Pitch Contour Analysis Guided by Prosodic Event Detection;
`-E. Geoffrois, NIT Human Interface Lab., Telecomm. Networks Lab., Tokyo, Japan
`24.5 Analysis and Synthesis of Pitch Movements in a Read Polish Text
`-G. Demenko,l. Nowak, J. lmiolczyk, Polish Academy of Sciences, Poland
`
`RoomD
`
`Session 25: Improved Algorithms for HMMs IT
`Time and Place:
`11.20 - 13.00 hrs
`Chairperson: A. Noll, aspect, Hamburg, Germany
`25.1 Optimization of an HMM-Based Continuous Speech Recognizer
`-F. Class, A. Kaltenmeier, P. Regel-Brietzmann, Daimler-Benz AG, Ulm, Germany
`25.2 Linear and Nonlinear Prediction for Speech Recognition with Hidden Markov Models
`- M. Saerens(* ), H. Bourlard(** ), (*) Universite Libre de Bruxelles,
`(**) Lernout & Hauspie Speech Products, Belgium
`Segmental Post-Processing of theN-Best Solutions in a Speech Recognition System
`-MN. Lokbani, D. Jouvet, J. Monne, France Telecom, CNET!LAAITSS!RCP, France
`25.4 A Study of On-Line Bayesian Adaptation for HMM-Based Speech Recognition
`- T. Matsuoka, C.-H. Lee, AT&T Bell Laboratories, USA
`25.5 Hidden Markov Models Using Shared Vector Linear Predictors
`- BA. Maxwell, P.C. Woodland, Cambridge University, UK
`
`25.3
`
`Room E
`
`Session 26: Speech Recognition in Noise
`Time and Place:
`11.20 - 13.00 hrs
`Chairperson: G. Chollet, TELECOM Paris, France
`26.1 Noise Adaptation: Speech Recognition by Auditory Models and Human Listeners
`- WA. Ainsworth, G.F. Meyer, Keele University, UK
`26.2 Adapting an HMM-Based Recogniser for Noisy Speech Enhanced by Spectral Subtraction
`-JA. Nolazco Flores, SJ. Young, Cambridge University, UK
`Speech Recognition Under the Unstationary Noise Based on the Noise Markov Model and
`Spectral-Subtraction
`- T. Kobayashi, R. Mine, K. Shirai, Waseda University, Japan
`26.4 HMM Recognition in Noise Using Parallel Model Combination
`-MJ.F. Gales, SJ. Young, University of Cambridge, UK
`Selectively Trained Neural Networks for Connected Word Recognition in Noisy
`Environments
`- L. Buniet(* ), D. Fohr(* ), Y. Anglade(* ),J-C. Junqua(** ), J-M. Pierre!(*),
`(*) CRIN-CNRS & INRIA, France,(**) Panasonic, USA
`
`26.3
`
`26.5
`
`785
`
`789
`
`793
`
`797
`
`803
`
`807
`
`811
`
`815
`
`819
`
`825
`
`829
`
`833
`
`837
`
`841
`
`XXIII
`Petitioner Apple Inc.
`Ex. 1008, p. xxiii
`
`

`

`EUROSPEECH 93
`
`3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION\
`AND TECHNOLOGY- Berlin, Germany, 21-23 September t993.:.' ;
`..
`..:,,,;: ::,pi;t;i!;:iJ;,{
`
`RoomF
`
`Session 27: Speaker Independency
`11.20 - 12.40 hrs
`Time and Place:
`Chairperson: E. Paulus, Technical University of Braunschweig, Germany
`27.1 A Baseline of a Speaker Independent Continuous Speech Recognizer of Italian
`-B. Angelini, F. Brugnara D. Falavigna, D. Giuliani, R. Gretter, M. Omologo,
`Istituto per Ia Ricerca Scientifica e Tecnologica, Italy
`27.2 Word Lookahead Scheme for Cross-Word Right Context Models in a Stack Decoder
`-L.R. Bahl, P.V. de Souza, P.S. Gopalakrishnan, D. Nahamoo,M. Picheny, IBM,
`T.J. Watson Research Center, USA
`27.3 Recognition of Obstruent Phonemes in Speaker-Independent Fluent Speech Using a
`Hierarchical Approach
`- D .B. Grayden, M.S. S cordilis, The University of Melbourne, Australia
`27.4 A Continuous Speech Recognition System Using Phonotactic Constraints
`-B. Plannerer, G. Ruske, TU Munchen, Germany
`
`847
`
`851
`
`855
`
`859
`
`865
`
`869
`
`873
`
`877
`
`881
`
`885
`
`889
`
`893
`
`897
`
`Room G
`
`Session 28: Speech Synthesis
`Poster Session 4
`11.20 - 13.00 hrs
`Time and Place:
`Chairperson: J. Sotscheck, TELEKOM Berlin, Germany
`28.1
`Joint Arabic-Hebrew Speech Synthesis System
`- M. Ouadou(* ), A. Rajouani(* ), M. Zyoute (* ), J. Rosenfeld(**), M. Najim(*** ),
`(*) LEESA, Maroc, (**) U niversite de Bordeaux, (***) ENSERB, France
`Improvements of the Spanish Version of the Multivox Text-to-Speech System
`-E.L. L6pez-Gonzalo(*), G. Olaszy(**), G. Nemeth(***),(*) Universidad Politecnica
`de Madrid, Spain,(**) Hungarian Academy of Science,(***) Technical University of
`Budapest, Hungary
`28.3 Generating Intonation for Swedish Text-to-Speech Conversion Using a Quantitative
`Model for the F0 Contour
`- M. Ljungqvist(* ), H. Fujisaki(** ),(*) Infovox AB, Sweden, (**) Science University
`of Tokyo, Japan
`28.4 PHRIITS - A Text-to-Speech Synthesizer for the Gennan Language
`- P. Meyer(*), H.W. Ruhl(* ), R. Kruger(*), M. Kugler(*), L.LM. Vogten(** ),
`A. Dirksen**), K. Belhoula(*** ), (*)PH/UPS Kommunikations Industrie AG,
`Germany,(**) Institute for Perception Research, Eindhoven, The Netherlands,
`(***) Ruhr-U niversitiit Bochum, Germany
`28.5 Rule-Based Grapheme-to-Phoneme Conversion of Names
`- K. Belhoula, Ruhr-Universitiit Bochum, Germany
`28.6 A Prototype Text-to-Speech System for Scottish Gaelic
`-J.R. Murray, MM. Black, University of Dundee, UK
`28.7 A Text-to-Speech System for Polish
`- J. Imiolczyk, I. Nowak, G. Demenko, Polish Academy of Science, Poland
`Intelligibility as a Function of Speech Coding Method for Template-Based Speech
`Synthesis
`- M. Macchi, M.J. Altom, D. Kahn, S. Singhal, M. Spiegel, Bel/core, USA
`28.9 Pronunciation and Text Nonnalisation in Applied Text-to-Speech Systems
`- M. Gaved, British Telecom Res. Labs., Ipswich, UK
`
`28.2
`
`28.8
`
`XXIV
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxiv
`
`

`

`3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`AND TECHNOLOGY- Berlin, Germany, 21-23 September 1993
`
`EUROSPEECH 93
`
`28.10 Evaluating Synthesised Prosody in Simulations of an Automated Telephone Enquiry
`Service
`- J. House(*), C. MacDermid(** ), S. McGlashan(**), A. Simpson(**), N. Youd(*** ),
`(*) UCL, (**) University of Surrey, (***) Logica Cambridge, UK
`28.11 Speech Synthesis in Dialogue Systems
`- K. Morton, M. Tatham, University of Essex, UK
`28.12 Applying Analysis of Human Emotional Speech to Enhance Synthetic Speech
`-E. Abadjieva, I.R. Murray, J.L. Arnott, University of Dundee, UK
`28.13 A Generic Front-End for Text-to-Speech Synthesis Systems
`-E. Lewis(*), M. Tatham(**),(*) Bristol University,(**) Essex University, UK
`28.14 Experiments with Silent-E and Affix Correspondences in Stochastic Phonographic Transduction
`- R.W.P. Luk, R.I. Damper, University of Southampton, UK
`28.15 Phoneme-Dependent Speech Synthesis in the Time and Frequency Domains
`-G. Fries, DBP Telekom, Germany
`28.16 Speech Synthesis Experiments with the Glove Synthesiser
`-I. Karlsson, L. Neovius, KTH Stockholm, Sweden
`28.17 Auditory Detection of Discontinuities in Synthesis-by-Concatenation
`- V. Kraft, Ruhr-Universitiit Bochum, Germany
`28.18 Effects of the Phase Jitters on Naturalness of Synthesized Speech
`- Y.-K. Lee, S.-K. Ahn, Central Research Laboratory Glodstar Co. Ltd., Korea
`28.19 Letter-to-Sound Rules for the Welsh Language
`-B. Williams, CSTR, Edinburgh, UK
`
`Break for lunch:
`
`13.00 - 14.00 hrs
`
`Room A
`
`Session 29: Dialogue Structure I
`14.00 -15.40 hrs
`Time and Place:
`Chairperson: S. McGlashan, University of Surrey, UK
`29.1 Dialogue Design Principles - Key for Usability of Voice Processing
`-C. Muller, F. Runge, Telekom, Forschungs- u. Technologiezentrum, Berlin, Germany
`29.2 Wizard-of-Oz and the Trade-Off between Naturalness and Recogniser Constraints
`-H. Dybkjter, N.O. Bernsen, L. Dybkjter, Roskilde University, Denmark
`29.3 Dialogue Analysis and Generation: A Theory for Modelling Natural English Dialogue
`-C. Jones, R. Garigliano, University of Durham, UK
`29.4 Features of Naive Callers' Dialogues with a Simulated Speech Understanding and
`Dialogue System
`-C. MacDermid, University of Surrey, UK
`29.5 Referring to Actions in Man-Machine Command Dialogues
`-F. Duermael, B. Gaiffe, CRIN-CNRS, France
`
`Session 30: Language Modelling I
`Time and Place:
`14.00 - 15.40 hrs
`Chairperson: R. Billi, CSELT Torino, Italy
`30.1
`Issues in Large Scale Statistical Language Modelling
`-R. Zhao, P. Kenny, P. Labute, D. O'Shauhgnessy, INRS-Telecommunications, Canada
`
`Room B
`
`901
`
`905
`
`909
`
`913
`
`917
`
`921
`
`925
`
`929
`
`933
`
`937
`
`943
`
`947
`
`951
`
`955
`
`959
`
`965
`
`XXV
`Petitioner Apple Inc.
`Ex. 1008, p. xxv
`
`

`

`30.3
`
`30.2 A Data-Driven Case for a Spontaneous Speech Grammar
`- R. Garigliano, K. Johnson, R.J. Collingham, Durham University, UK
`Improved Oustering Techniques for Oass-Based Statistical Language Modelling
`- R. Kneser, H. Ney, Philips GmbH Forschungslaboratorien Aachen, Germany
`30.4 A Consolidated Language Model for Speech Recognition
`-J H. Wright, GJ.F. Jones, H. Lloyd-Thomas, University of Bristol, UK
`30.5 Empirical Acquisition of Word and Phrase Classes in the ATIS Domain
`-M.K. McCandless, J.R. Glass, M.l.T., USA
`
`Roome
`
`Session 31: Prosody ill: Prosodic Parameter Manipulation
`Time and Place:
`14.00-15.40 hrs
`Chairperson: G. Bruce, Lund University, Sweden
`31.1 New Frequency Domain Prosodic Modification Techniques
`- E.R. Banga, C. Garcia-Mateo, E.T.S.l. Telecomunicaci6n, Vigo, Spain
`31.2 A Prosody Modification Approach for Auditory User Feedback in the SPELL
`Pronunciation Teaching System
`-HD. Wang(*), D. Degryse(*), F. Carraro(**), (*) OROS, France, (**)Alcatel Face,
`Italy
`31.3 A Speech Prosody Conversion System with a High Quality Speech Analysis-Synthesis
`Method
`- T. Takagi, E. Miyasaka, NHK Science and Technical Research Labs, Japan
`31.4 On the Perceived Serial Position of Discourse Units
`-M. Swerts, R. Collier, /PO, The Netherlands
`31.5 Enhanced Pitch Tracking and the Processing of F0 Contours for Computer Aided
`Intonation Teaching
`-P.C. Bagshaw, SM. Hiller, M.A. Jack, CSTR, Edinburgh, UK
`
`Session 32: New Architectures for Neural Networks
`Time and Place:
`14.00 - 15.00 hrs
`Chairperson: D. Beroule, UMSI-CNRS, France
`32.1
`Improved DVQ Algorithm for Speech Recognition: A New Adaptive Learning Rule
`with Neurons Annihilation
`-C. Tadj, F. Poirier, Telecom Paris, France
`32.2 Speaker-Independent 212 Word Recognition Using CombNET-II
`- T. Sasaki, T. Kitamura, A. Iwata, Nagoya Institute of Technology, Japan
`32.3 Learning Direct Acoustic-to-Semantic Mappings through Simple Recurrent Networks
`-M.A. Castano, E. Vidal, F. Casacuberta, Universidad Politecnica de Valencia, Spain
`
`Room D
`
`Session 33: Noise Reduction and Channel Adaptation 1
`Time and Place:
`14.00 - 15.40 hrs
`Chairperson: K. Shikano, NTT Human Interface Laboratories, Japan
`33.1 Noise-Adaptive Hidden Markov Models Based on Wiener Filters
`- S. V. Vaseghi, B.P. Milner, University of East Anglia, UK
`
`RoomE
`
`XXVI
`
`969
`
`973
`
`977
`
`981
`
`987
`
`991
`
`995
`
`999
`
`1003
`
`1009
`
`1013
`
`1017
`
`1023
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxvi
`
`

`

`3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`AN~ 'Jl:CHNOLOGY- Berlin, Germany, 21-23 September 1993
`
`EUROSPEECH 93
`
`33.2 Noisy Speech Recognition Using Singular Value Decomposition and Two-Sided
`Linear Prediction
`-K.F. Wong, S.H. Leung, H.C. Ng, City Polytechnic of Hong Kong, Hong Kong
`33.3 Recognition of Noisy Speech by Composition of Hidden Markov Models
`-F. Martin(*), K. Shikano(**), Y. Minami(**),(*) Ecole Polytechnique, France,
`(**)NIT Human Interface Laboratories, Japan
`33.4 Noise Reduction and Speech Recognition in Noise Conditions Tested on LPNN-Based
`Continuous Speech Recognition System
`- Y. Gao, J.-P. Haton, CRIN!CNRS, France
`33.5 Combination of Distortion-Robust Feature Extraction and Neural Noise Reduction
`forASR
`-M. Trompf, R. Richter, H. Eckhardt, H.Hackbarth, Alcatel SEL, Germany
`
`RoomF
`
`Session 34: Word Spotting I
`Time and Place:
`14.00-15.40 hrs
`Chairperson: J. Mariani, LIMSI-CNRS, France
`34.1 Robust Word Spotting in Adverse Car Environments
`- S. Nakamura, T. Akabane, S. Hamaguchi, Sharp Corporation, Japan
`34.2 Definition of Subword Acoustic Units for Wordspotting
`- R.C. Rose, AT&T Bell Laboratories, USA
`Spontaneous Speech Recognition by Sentence Spotting
`-J. Kiyama, Y. /toh, R. Oka, Tsukuba Research Center, Japan
`34.4 Phonetic-Based Word Spotter: Various Configurations and Application to Event
`Spotting
`- P. Jeanrenaud, K. Ng, M. Siu, J.R. Rohlicek, H. Gish, Bolt Beranek &
`Newman Inc, USA
`34.5 An Application of Word-Spotting in a Voice Activated Service Entry System
`-A. Imamura, M. Kitai, NIT Human Interface Laboratories, Japan
`
`34.3
`
`Session 35: Speech Processing and Coding
`Poster Session 5
`14.00-15.40 hrs
`Time and Place:
`Chairperson: K. Vicsi, University of Budapest, Hungary
`35.1 Generalised Frequency Domain Adaptive Filter for Acoustic Echo Canceller
`-F. Dohnal, Military Academy BRNO, Czech Republic
`35.2 Estimation of Speech Signal Classification Features in a Simulated Hyperbaric
`Environment
`-J. Crestel, M. Guitton, Universite de Rennes, ENSSAT!LASTI, France
`35.3 Noise Suppression System for a Car
`- P. Polltik, P. Sovka, J. Uhl(r, Czech Technical University Prague, Czech Republic
`35.4 Adaptive Gain Control and Echo Cancellation for Hands-Free Telephone Systems
`- P. Heitkiimper(* ), M. Walker(**),(*) TH Darmstadt, (**) ALCATEL-SEL, Germany
`
`RoomG
`
`1027
`
`1031
`
`1035
`
`1039
`
`1045
`
`1049
`
`1053
`
`1057
`
`1061
`
`1067
`
`1069
`
`1073
`
`1077.
`
`XXVII
`Petitioner Apple Inc.
`Ex. 1008, p. xxvii
`
`

`

`· ·/ : ;~·,~~f:~r
`·· · ·· · ·
`· 3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`'
`AND TECHNOLOGY- Berlin, Germany, 21-23 Septe~~~~.1~J .
`
`35.5
`
`Predicting Segmental Durations for Accommodation within a Syllable-Level Timing
`Framework
`- W.N. Campbell, ATR Interpreting Telecommunications Research Laboratories,
`Japan
`35.6 A Filterbank Based on Physiologically Measured Characteristics in an Auditory Model
`for Speech Signal Processing
`- T. Fjiillbrant, F. Mekuria, S. Amirijoo, University of Linkoping, Sweden
`Spectral Sensitivity Weighted Transform Coding for LSP Parameters
`-F.-R. Jean, C.-C. Kuo, H.-C. Wang, National Tsing Hua University, R.O.C.
`35.8 An Efficient Algorithm to Estimate the Instantaneous SNR of Speech Signals
`-R. Martin, Aachen University ofTechnology, Germany
`Speech/Non-Speech Detection for Voice Response Systems
`-L. Mauuary(*,**),J. Monne(**), (*) ACSYS, (**)France Telecom, France
`35.10 Time-Spectral Approach to Compiling Speech Reconstruction
`- A.Osipov, V. Zentsov, St. Petersburg Air and Spacecraft Equipment Academy, Russia
`A Voice Activity Detector Based on Cepstral Analysis
`-J A. Haigh, J.S. Mason, University College Wales, UK
`High Quality Coding of Wideband Speech at 24Kbit/s
`-J. Paulus, C. Antweiler, C. Gerlach, Aachen University ofTechnology, Germany
`A 32 Kbits/s Wideband Speech Coder Based on Transform Coding
`-H. Dia(*), G. Feng(*), Y. Mahieux(**), (*) Universite Stendhal, Grenoble,
`(**) CNET, Lannion, France
`Real-Time Implementation of High Quality 32 Kbps Wideband LD-CELP Coder
`- 0. Gottesman, Y. Shoham, AT&T Bell Laboratories, USA
`A Fixed-Point Implementation of the 16kb/s LD-CELP Speech Coding Algorithm
`-A. Popescu(*), D. Vicard(** ), F. Druilhe(** ), (*)Telecom Paris, (**) SGS-Thomson
`Microelectronics, France
`Optimality of Sequential Quantization in Analysis-By-Synthesis Speech Codecs
`- C.G. Gerlach, RWTH Aachen, Germany
`A Sub-Band MPLPC Coder for High Quality Speech Coding at 16 Kbit/s
`-R. Kastantin, G. Feng, INPG!Universite Stendhal, France
`Optimal Multipulse Excitation Determination by Simulated Annealing
`-E. Mumolo, A. Rebelli, Universita' di Trieste, Italy
`Split Vector Quantization of the LPC Parameters Using Weighted Lattice Structure
`-K.W. Law, C.F. Chan, City Polytechnic of Hong Kong, Hong Kong
`A New Approach to Noiseless Interframe Coding ofLPC Parameters in Vector
`Quantizer Applications
`- S. Bruhn, Technical University of Berlin, Germany
`Efficient Quantization of Speech Spectral Information
`- T. Svendsen, The Norwegian Institute of Technology, Norway
`Enhancing Robustness of Coded LPC-Spectra to Channel Errors by Use of Residual
`Redundancy
`-S. Feldes, DBP Telekom, Germany
`Multi-Rate Source and Channel Coding for Mobile Communication Systems
`- S.A. Atungsiri, A.M. Kondoz, B.G. Evans, University of Surrey, UK
`
`35.7
`
`35.9
`
`35.11
`
`35.12
`
`35.13
`
`35.14
`
`35.15
`
`35.16
`
`35.17
`
`35.18
`
`35.19
`
`35.20
`
`35.21
`
`35.22
`
`35.23
`
`1081
`
`1085
`
`1089
`
`1093
`
`1097
`
`1101
`
`1103
`
`1107
`
`1111
`
`1115
`
`1119
`
`1123
`
`1127
`
`1131
`
`1135
`
`1139
`
`1143
`
`1147
`
`1151
`
`XXVIII
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxviii
`
`

`

`3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`AND TECHNOLOGY- Berlin, Germany, 21-23 September 1993
`
`EUROSPEECH 93
`
`35.24 Training Method of the Excitation Codebook for CELP
`- T. Moriya, S. Miki, K. Mano, H.Ohmuro, NIT Human Interface Laboratories,
`Tokyo, Japan
`
`Coffee Break:
`
`15.40 ~ 16.00 hrs
`
`Room A
`
`Session 36: Dialogue Structure IT
`16.00 ~ 17.40 hrs
`Time and Place:
`Chairperson: J. Hirschberg, AT&T Bell Laboratories, USA
`36.1 Next Utterance Prediction Based on Two Kinds of Dialog Models
`- Y. Yamashita, R. Mizoguchi, Osaka University, Japan
`36.2 The Design of a Real World Wizard-of-Oz Experiment for a Speech Driven Telephone
`Directory Information System
`- T. Andernach (*),G. Deville(**), L. Mortier(***), (*) University ofTwente,
`The Netherlands(**) University of Namur, (***) Lernout & Hauspie Speech
`Products, Belgium
`36.3 Dialog Structure and Plan Recognition in Spontaneous Spoken Dialog
`- S.R. Young, Carnegie Mellon University, USA
`36.4 A Speech-First Model for Repair Identification in Spoken Language Systems
`-J. Hirschberg(*), C. Nakatani(**),(*) AT&T Bell Laboratories,
`(**)Harvard University, USA
`36.5 Recognition Confidence Measures for Spontaneous Spoken Dialog
`-S.R. Young, W. Ward, Carnegie Mellon University, USA
`
`Room B
`
`Session 37: Language Modelling IT
`16.00 - 17.40 hrs
`Time and Place:
`Chairperson: R. Pieraccini, AT&T Bell Laboratories, USA
`37.1 The Effects of Parameter Smoothing on Robust Learning in Syntactic Ambiguity
`Resolution
`- T.-H. Chiang, K.-Y. Su, National Tsing Hua University, R.O.C
`37.2 Learning Associations between Grammars: A New Approach to Natural Language
`Understanding
`-E. Vidal, R. Pieraccini, E. Levin, AT&T Bell Laboratories, USA
`37.3 Language Modelling for CSR of Large Corpus Using Automatic Oassification of Words
`- M. Jardino, G. Adda, LIMS!-CNRS, France
`Inference of Stochastic Context-Free Grammar Rules from Example Data Using the
`Theory of Bayesian Belief Propagation
`-H. Lucke, ATR Interpreting Telecommunication Research Laboratories, Japan
`37.5 Constructing Linguistic Oriented Language Models for Large Vocabulary Speech
`Recognition
`- P. Witschel, Siemens AG, Germany
`
`37.4
`
`1155
`
`1161
`
`1165
`
`1169
`
`1173
`
`1177
`
`1183
`
`1187
`
`1191
`
`1195
`
`1199
`
`XXIX
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxix
`
`

`

`:UROSPEECH 93
`
`Room C
`
`iession 38: Prosody IV: Phrasing
`16.00 - 17.40 hrs
`rime and Place:
`Chairperson: L.F. Lamel, UMSI-CNRS, France
`38.1
`Phrasing Strategies in Prosodic Parsing and Speech Synthesis
`-G. Bruce(*), B. Granstrom(**),K. Gustafson(**), D. House(*),(*) Lund University,
`(**) KTH Stockholm , Sweden
`38.2 Prosody in the Perception of Syntactic Boundaries
`-E. Strangert, B. Strangert, University of Umed, Sweden
`Prosodic Cues to the Perception of Constituent Boundaries
`-J.R. de Pijper, A. Sanderman, /PO, The Netherlands
`38.4 Acoustic Cues to Syntactic Structure- Evidence from Prosodic and Segmental Effects
`-E. Grabe, T. Holst, F. Nolan, P. Warren, University of Cambridge, UK
`38.5 Automatic Generation of French Intonation Based on a Perceptual Study and Morpho-
`Syntactic Information
`-F. Beaugendre(* ), A. Lacheret-Dujor(*, ** ), (*) LIMSI-CNRS, (**) ELSAP, France
`
`38.3
`
`Session 39: MLPs and TDNNs for Speech Recognition I
`Room D
`Time and Place:
`16.00-17.40 hrs
`Chairperson: A. Waibel, Universitiit Karlsruhe, Germany, Carnegie Mellon College, USA
`39.1 A Partitioned Neural Network Approach for Vowel Classification Using Smoothed
`Time/Frequency Features
`-SA. Zahorian, Z.B. Nossair, CA. Norton, Old Dominion University, USA
`39.2 Speaker-Independent 100 Word Recognition Using Dynamic Spectral Features of
`Speech and a Neural Network
`- T. Kitamura, Nagoya Institute of Technology, Japan
`Speaker Independent Isolated Word Recognition Using Vector Quantization and
`Neural Networks
`-M. Zhu, K. Fellbaum, Technical University of Berlin, Germany
`39.4 Multi-Layer Perceptrons and Probabilistic Neural Networks for Phoneme Recognition
`-K.O.E. Elenius, H.G.C. Trdven, KTH, Sweden
`39.5 Automatic Accent Classification Using Artificial Neural Networks
`- C.S. Blackburn, J.P. Vonwiller, R. W. King, University of Sydney, Australia
`
`39.3
`
`Session 40: Noise Reduction and Channel Adaptation IT
`Time and Place:
`16.00 - 17.20 hrs
`Chairperson: P. Lockwood, MATRA Communication, France
`40.1 On-Line Adaptation of a Speech Recognizer to Variations in Telephone Line Conditions
`-C. Mokbel, J. Monne, D. Jouvet, France Telecom, France
`40.2 Online Channel Compensation for Robust Speech Recognition
`-M. Wittmann, 0. Schmidbauer, A. Aktas, Siemens AG, Germany
`40.3 Evaluation of Car Noise Reduction/Compensation Techniques for Digit Recognition in
`a Speaker-Independent Context
`- P. Alexandre, J. Boudy, P. Lockwood, MATRA Communication, France
`
`RoomE
`
`XXX
`
`1205
`
`1209
`
`1211
`
`1215
`
`1219
`
`1225
`
`1229
`
`1233
`
`1237
`
`1241
`
`1247
`
`1251
`
`1255
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxx
`
`

`

`ird EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`ANDJECHN~LOGY-:- Berlin. Germany, 21-:-23 September 1993
`:o L~o~cocoYo>~"o-.-::-c:c fo~~'~': ,::oc ;n<-' c>. cM>~owoo <
`~_:;,~~<-.;;,,_0~~~ d,:l~ ~~~;~~;;~ c,~';?,~;c;:~:o~~~k'.,~HO;;~;; ,; ' ~,~
`~c'~ CY ~~~C::o~i '" >
`:Coo>
`
`EUROSPEECH 93
`
`40.4 Experiments on Noise Reduction Techniques with Robust Voice Detectors in Car
`Environment
`-A. Brancaccio, C. Pelaez, Alcatel Italia, FACE Division, Italy
`
`Room F
`
`Session 41: Word Spotting II
`16.00-17.40 hrs
`Time and Place:
`Chairperson: J.P. Haton, CRIN-CNRS!INRIA Lorraine, France
`41.1 Out-of-Vocabulary Word Modelling and Rejection for Keyword Spotting
`-E. Lleida, J.B. Marino, J. Salavedra, A. Bonajonte, E. Monte, A. Martfnez
`Polytechnical University of Catalonia, Spain
`41.2 Word and Phrase Spotting with Limited Training
`-MJ. 0' Kane, P.E. Kenne, University of Canberra, Australia
`41.3 A New Approach Towards Keyword Spotting
`-J.-M. Boite, H. Bourlard, B. D'Hoore, M. Haesen, Lernout & Hauspie Speech
`Products, Belgium
`41.4 Grammar Learning and Word Spotting Using Recurrent Neural Networks
`-J. Alvarez-Cercadillo, L.A. Hernandez-Gomez, UPM, Spain
`41.5 Word Spotting in Conversational Speech Based on Phonemic Unit Likelihood by
`Mutual Infonnation Criterion
`- S. Okawa, T. Kobayashi, K. Shirai, Waseda University, Japan
`
`RoomG
`
`Session 42: Speech Translation, Language Identification, Parsers
`Poster Session 6
`Time and Place:
`16.00 - 17.40 hrs
`Chairperson: H.G. Tillmann, University of Munich, Germany
`42.1 ATREUS: A Speech Recognition Front-End for a Speech Translation System
`- S. Sagayama, J. Takami, A. Nagai, H. Singer, K. Yamaguchi, K. Ohkura, K. Kita,
`A. Kurematsu, ATR Interpreting Telephony Research Labs., Japan
`42.2 ATR's Speech Translation System: ASURA
`- T. Morimoto, T. Takezawa, F. Yato, S. Sagayama, T. Tashiro, M. Nagata,
`A. Kurematsu, ATR Interpreting Telephony Research Laboratories, Japan
`42.3 Recent Advances in JANUS: A Speech Translation System
`- M. Woszczyna, N. Coccaro, A. Eisele, A. Lavie, A. McNair, T. Polzin, I. Rogina,
`C.P. Rose, T. Sloboda, M. Tomita, J. Tsutsumi, N. Aoki-Waibel, A. Waibel, W. Ward,
`Universitiit Karlsruhe, Germany, Carnegie Mellon University, USA
`Spoken Language Translation with Mid-90's Technology: A Case Study
`-M. Rayner(*), I. Bretan(***), D. Carter(*),M. Collins(*), V. Digalakis(**),
`B. Gambiick(*** ), J. Kaja(**** ), J. Karlgren(*** ), B. Lyberg(**** ), S. Pulman(* ),
`P. Price(**), C. Samuelson(***),(*) SRI International, Cambridge, UK,
`(**)SRI International, Ca, USA,(***) Swedish Institute for Computer Science,
`Stockholm, Sweden,(****) Telia Research AB, Sweden
`42.5 Automatic Language Identification Using a Segment-Based Approach
`- T J. Hazen, V.W. Zue, MIT, USA
`
`42.4
`
`1259
`
`1265
`
`1269
`
`1273
`
`1277
`
`1281
`
`1287
`
`1291
`
`1295
`
`1299
`
`1303
`
`XXXI
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxxi
`
`

`

`42.7
`
`42.8
`
`42.6 A Comparison of Approaches to Automatic Language Identification Using Telephone
`Speech
`_ Y. Muthusamy, K. Berkling, T. Arai, R. Cole, E. Barnard, Oregon Institute of Science
`and Technology, USA
`Integration of Neural Networks and Robust Parsers in Natural Language Understanding
`_ Y. Cheng(*,**), Y. Normandin(*), P. Fortier(**),(*) CRIM, (**)Laval University,
`Canada
`Joint Speech and Gesture Analysis; Some Experimental Results on Multimodal Interface
`-P. Dauchy(*), C. Mignot(**), C. Valot(*), (*) CERMA, (**) CRIN,France
`42.9 Generation of Speech Reply in the Speech Response System
`- K. Hirose, Y. Asano, University of Tokyo, Japan
`42.10 A Fast Multilingual Probabilistic Tagger
`-E. Dermatas, G. Kokkinakis, University ofPatras, Greece
`42.11 The Possibility for Aquisition of Statistical Network Grammar Using Ergodic HMM
`- J. Murakami(*), H. Yamamoto(*), S. Sagayama(** ), (*) ATR Interpreting Telecomm.
`Research Labs., (**)NIT Human Interface Research Labs., Japan
`42.12 A Robust Analyzer for Spoken Language Understanding
`-E. Millien, R. Kuhn, CRIM, Canada
`42.13 Identifying Usability Attributes of Automated Telephone Services
`-R.T. Dutton(*), J. Foster(*), MA. Jack(*), F.W Stentiford(**), (*) CSTR, Edinburgh,
`(**) BT Laboratories, Ipswich, UK
`42.14 Utilising Prosody to Perform Syntactic Disambiguation
`-A. Hunt, University of Sydney, Australia
`42.15 SPELL: An Automated System for Computer-Aided Pronunciation Teaching
`-S. Hiller(*), E. Rooney(*),J.-P. Lejevre(**),MA. Jack(*),(*) CSTR, Edinburgh, UK,
`(**) Agora Conseil, France
`42.16 Training Vowel Pronunciation Using a Computer-Aided Teaching System
`-E. Rooney, R. Vaughan, S. Hiller, F. Carraro, J. Laver, CSTR, Edinburgh, UK
`42.17 Methods forTraversing a Pre-Recorded Speech Message Network to Optimise
`Dialogue in Telephone Answering Systems
`- M. Zajicek, K. Brownsey, Oxford Brookes University, UK
`42.18 Service Creation Tools for Creating Speech Interactive Services
`- R. Hanes, J. Salter, P. Popay, F. Hedley, BT Laboratories, UK
`42.19 Deaccentuation and Persistence of Grammatical Function and Surface Position
`-J. Hirschberg(*),]. Terken(**), (*)AT&T Bell Laboratories, USA,(**) Institute for
`Perception Research, The Netherlands
`Design and Implementation of a Speech Server for Unix Based Multimedia Applications
`- S. Euler, K. Riedel, TELENORMA GmbH, Bosch Telecom, Germany
`Romaine: A Lattice-Based Approach to Lexical Access
`-D. Goodine, V.W Zue,M.l.T., USA
`42.22 A System for Oustering Spoken Documents
`- T A. Albina, E.G. Bernstein, DM. Goblirsch, DE. Lake, The MITRE
`Corporation, USA
`
`3rd EURO~EAN CONFERENCE ON SPEECH COMM~~~~AT.i:;~~r~
`
`·. AND TECHNOLOGY- Berlin, Germany, 21-23 September 1993
`'~"o:~,~t,';:v:2,_«'
`
`1307
`
`1311
`
`1315
`
`1319
`
`1323
`
`1327
`
`1331
`
`1335
`
`1339
`
`1343
`
`1347
`
`1351
`
`1355
`
`1359
`
`1363
`
`1367
`
`1371
`
`42.20
`
`42.21
`
`XXXII
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxxii
`
`

`

`~ ,__,, ;~~ "<f~';o''~~ ~~
`
`,;,':'·'~_-o}''";'-',:,
`
`';~ '
`
`3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATION
`AND ~CHNOLOGV-: Berlin •. Germany, 21-23 September 1993
`J,;~;;,.;)';,u\L..;;5_,,,;,_:;t-&; -"-"-;-~~:..,,-,;;.~'""' ~ <,- o ~ ,;;,~_.>;;.} ;;_~ ~:,~, ;.,/,,-.;,, %> ·- <-~_;,~~ ,~,~-_ _::;, ~ ~,
`:.-:::t> .!.-/~~9.:,>; :...,-~,, :: ~-~' ~"' -;, -:,:
`
`Thursday, 23 September
`
`EUROSPEECH 93
`
`Keynote 10
`Time and Place:
`08.40 - 09.10 hrs
`The Conversational Computer: An Apple Perspective
`- K. F. Lee, Apple Computer Inc., USA
`Keynote 11
`08.40- 09.10 hrs
`Time and Place:
`Speech Quality Assessment and Evaluation
`- U. Jekosch, Ruhr-Universitiit Bochum, Germany
`Keynote 12
`08.40-09.10 hrs
`Time and Place:
`Timing in Text-to-Speech Systems
`-J. P.H. v. Santen,AT&T Bell Labs., USA
`Keynote 13
`Time and Place:
`08.40 - 09.10 hrs
`Learning how to Understand Language
`- R. Pieraccini(*), E. Levin(*), E. Vidal(**)(* )AT&T Bell Labs, USA,
`(**) Universidad Politecnica de Valencia, Spain
`
`Room A
`
`RoomB
`
`Roome
`
`RoomD
`
`Room A
`
`Session 43: Dialogue Evaluation
`09.20 - 11.00 hrs
`Time and Place:
`Chairperson: N. Fraser, Logica Cambridge Ltd., UK
`43.1
`Spoken Dialogues for Human-Computer Interaction over the Telephone:
`Complexity Measures
`-NA. Vergeynst, K. Edwards,J.C. Foster,MA. Jack, CSTR, Edinburgh, UK
`4 3.2 The Cost of Errors in a Spoken Language System
`-L. Hirschman, C. Pao, MIT, USA
`43.3 Black Box and Glass Box Evaluation of the SUNDIAL System
`-A. Simpson(*), N M. Fraser(**), (*) University of Surrey, (** )Vocalis Ltd.,
`Cambridge, UK
`43.4 A Methodology for Evaluating Human-Machine Spoken Language Interaction
`-C. Delogu, A. DiCarlo, C. Sementina, S. Stecconi, Fondazione Ugo Bordoni, Italy
`43.5 Error Correction and Ambiguity Resolution in Multimodal Man-Machine Dialogue
`-P. Morin(*,**),J.-C. Junqua(*), (*)Speech Technology Laboratory, Panasonic
`Technologies, Inc., USA,(**) CRIN-CNRS, France
`
`Session 44: Data Bases
`09.20- 10.40 hrs
`Time and Place:
`Chairperson: M. Eskenazi, UMSI Paris, France
`44.1 Constraints in the Recording of Speech Data Bases; Analysis of the Speaker and
`Operator Behaviours
`-M.-F. Castaing, D. True-Martini, LIMSI-CNRS, France
`
`RoomB
`
`1377
`
`1387
`
`1397
`
`1407
`
`1415
`
`1419
`
`1423
`
`1427
`
`1431
`
`1437
`
`XXXIII
`
`Petitioner Apple Inc.
`Ex. 1008, p. xxxiii
`
`

`

`.
`
`3rd EUROPEAN CONFERENCE ON SPEECH COMMUNICATIIlN
`• . AND TECHNOLOGY- Berlin, Germany, 21-23 Septeltl~er 1993
`
`44.2 Multi-Level Transcription of Speech Corpora from Orthographic Forms
`-A. de Ginestel-Mailland, M. d