| 14.00-14.30 | Stochastic Conceptual Model for Spoken Language Understanding: Caroline Bousquet-Vernhettes, Nadine Vigouroux and Guy Pérennou |
| 14.30-15.00 | Combining Statistics with Semantic Networks in a Real-time Dialogue System: J.Fischer, E.Nöth, H.Niemann |
| 15.00-15.30 | Spoken Dialogue Systems: Toward a Complexity Measure for System’s Questions: Carine-Alexia Lavelle, Guy Pérennou |
| 15.30-16.00 | Coffee break |
| 16.00-16.30 | Acceleration of Lexical Access Caused by Word Familiarity and by Accent Nucleus Perception in Japanese: Nobuaki Minematsu, Seiichi Nakagawa |
| 16.30-17.00 | Speech Based, Multimodal Human computer Interaction: L.J.M.Rothkrantz, M.Andre, B.Sletterink |
| 18.15 | Visiting the Bolshoy Theater |
| 14.00-14.30 | Improvement of Multi-Band Speech Recognition: J.-P.Haton, C.Cerisara, D.Fohr |
| 14.25-14.55 | Integrating Speech Recognition and Natural Language LTAG Techniques with Weighted Synchonized Automata: Jean-Luc Husson (*) and Patrice Lopez (**) |
| 14.55-15.25 | An Adaptive Pruning Threshold Algorithm for Efficient Speech Recognition: Cheol-Jun Hwang, Se-Jun Oh, Ho-Youl Jung, Hyun-Yeol Chung |
| 15.30-16.00 | Coffee break |
| 16.00-16.15 | Development and Evaluation of Digital Map Retrieval System Using speech Recognition Interface: Tae-Soo Kim, Chelo-Jun Hwang, Ho-Youl Jung, Hyun-Yeol Chung |
| 16.15-16.30 | Acoustic Speech Recognition by Two and three Layered Neural Networks with Competition and Cooperation: Tetsuro Kitazoe, Sung-Ill Kim, Tomoyuki Ichiki, Makoto Junamori |
| 16.30-16.45 | Towards a Better Collaboration Between a n-class and a n-gram Language Model: K.Smażli, I.Zitouni, J.P.Haton |
| 16.45-17.00 | Phoneme-by-Phoneme Recognition for Continuous Speech: Taras K.Vintsiuk |
| 18.15 | Visiting the Bolshoy Theater |
| 14.00-14.25 | Hypertextual Multimedia Database of Russian Phonetics for distance Education: G.E.Kedrova, O.V.Dedova, V.V.Potapov |
| 14.25-14.50 | Acoustic Evidence of Tension in Voiceless German Plosives: Natalia Petlyuchenko |
| 14.50-15.15 | Usage of the Acoustic-Phonetic Classifier for Optimization of Codecs with a Linear Prediction: Gennady V.Bogachev, Alexander A.Rybolovlev |
| 15.15-15.30 | Recurrent multiband pitch estimation: Michael Braude-Zolotarev (*), Yuri Braude-Zolotarev (**) |
| 15.30-16.00 | Coffee break |
| 16.00-16.15 | A speech interface sysstem for information retrieval tasks on the WWW: Atsuhiko Kai (*), Takahiro Nakano, and Seiichi Nakagawa (**) |
| 16.15-16.30 | Automatic formant tracking by an active contour technique: Yves Laprie |
| 16.30-16.15 | Speech quality measurements: Vadim G.Mikhailov |
| 16.45-17.00 | Pattern Response Generation as a Part of the Model of the Dialogue with the Telephone Query System: Svetlana Toldova |
| 18.15 | Visiting the Bolshoy Theater |
| 9.00-9.50 | The beginning of machine translation in the USSR (retrospective review): Yu.N.Marchuk |
| 9.50-10.40 | The interactive expert system for forensic speaker identification used in Russia: N.F.Popov, A.N.Linkov (1), An.V.Fesenko, N.B.Kurachenkova, N.V.Baicharov (2), I.P.Karlin, I.N.Timofeev (3), R.K.Potapova (4), |
| 10.40-11.00 | Coffee break |
| 11.00-11.50 | The Knowledge Based Speech – Input expert System for Russian: R.K.Potapova |
| 11.50-12.40 | Realization of some reserves of language and extralinguistic knowledge for the speech dialogue systems improvement: Yu.Kosarev, J.Savage |
| 12.40-14.00 | Lunch break |
| 14.00 | Sightseeing tour in Moscow |
| 19.30 | Workshop Dinner |
| 9.00-9.25 | Testing of [Text-to-Speech] System Developed in MSU: Alexey Babkin, Leonid Zakharov |
| 9.25-9.50 | The Application of Text-to-Speech System in Slovak to Singing voice Synthesis: Sachia Darzagin, Varian Trnka, Milan Rusko |
| 9.50-10.20 | Main Principles and Overall Structure of TTS system for Russian Language: Olga Krivnova |
| 10.20-10.40 | Coffee break |
| 10.40-11.20 | Prosody Generation and Segment Concatenation in the Time Domain: J.Longster, R.Sahandi and D.S.G.Vine |
| 11.20-11.40 | Recording Concatenative Units for Speech Synthesis using a Reference Pitch Prompt: D.S.G.Vine, R.Sahandi, J.Longster |
| 11.40-12.20 | Design and Implementation of a Russian Telephone Speech Database: V.Kouznetsov (*), V.Chuchupal, K.Makovkin , A.Chichagov (**) |
| 12.20-12.50 | Fast and Robust Segment Searching Algorithms: Masahide Sugiyama |
| 12.50-13.10 | Closing of Workshop |
| 13.10-14.30 | Lunch |
| 14.30 | Visiting the world famous Kremlin |
| 9.00-9.25 | Sound Pressure Distributions and Propagation Paths in the vocal Tract with the Pyriform Fossa and the Supraglottis: Takayoshi Nakai, Kenji Satoh, Yasunori Suzuki and Keizo Ishida |
| 9.25-9.50 | Emotional Colouring of a Voice and the Phenomenon of Quasiharmony of Overtones: Vladimir P.Morozov (*), Youri M.Kouznetsov (**) |
| 9.50-10.20 | Phonetic Analysis of Brief Utterances: a Practical Method of a Sophisticated Forensic speaker Identification Technique: Elena I.Galyashina |
| 10.20-10.40 | Coffee break |
| 10.40-11.20 | Speaker Identification in the Case of Voice Disguising: Serguey N.Krinov |
| 11.20-11.40 | A Research of Person Emotional State Reflection in Spectral Characteristics of the Speech: V.A. Orlov |
| 11.40-12.20 | Some Aspects of Forensic Phonetics Experts Learning (on the Basis of Russian): R. K.Potapova |
| 12.20-12.50 | Speaker Identification Using Discriminative Feature Selection - A Growing Neural Gas Approach: Bogdan Dabac and Inge Gavat |
| 12.50-13.10 | Closing of Workshop |
| 13.10-14.30 | Lunch |
| 14.30 | Visiting the world famous Kremlin |
