|
|
|
GENERAL CHAIRMAN'S MESSAGE
Distinguished quests, ladies and gentlemen, dear colleagues! It is great pleasure for me as General Chairman to welcome you to the 5-th International Workshop on Speech and Compute.
The SPECOM - series established by St.-Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, was intended to discuss the most important fundamental aspects of man-computer speech interaction and more perspective application of this research.
During the first event in 1996 it was established to hold SPECOMs every second year in St-Petersburg, because it is very important topic for our region and our country. Also it was established to hold this event in another years in other cities. So, the first SPECOM was held in October 1996 in St.- Petersburg, SPECOM'97 - in Romania, the SPECOM'98 was held in St.-Petersburg, the SPECOM’99 was held in Moscow and this 5-th event goes again in St. Petersburg.
We would like to convey our best wishes to all the participants and guests.
I wish you success.
Rafael Yusupov
Chairman, SPECOM'2000
ORGANIZING COMMITTEE CHAIR'S MESSAGE
Distinguished guests, ladies and gentlemen, dear colleagues! It is a great pleasure for me as Chairman of the Organizing Committee to welcome you to the 5-th SPECOM Workshop.
This Workshop is last one in XX Century, it is jubilee. So we asked members to show in reports achievements and prognoses in their concrete research area. The student section is included in the Program to encourage young researches for initiative-creative activity.
We are pleased that so many outstanding researchers from Russia and from some other countries have come to attend this Workshop. We would like to convey our best wishes to all the participants and guests.
Our research are developed impetuously. But there are some challenges and obstacles preventing successful application of speech systems. So let us solve this problem together!
I wish you success here and in your research. Thank you.
Yuri Kosarev
SPECOM’2000
Organizing Committee Chair
SCIENTIFIC COMMITTEE
|
Chair: |
|
|
R. Yusupov |
SPIIRAS, St.-Petersburg, Russia |
|
Members: |
|
|
G.Kokkinakis |
WCL, University of Patras, Greece |
|
B.Millar |
Australian National University, Australia |
|
H.Niemann |
University of Erlangen-Nuremberg, Germany |
|
G.Rigoll |
Gerhard-Mercator-University Duisburg, Germany |
|
J. Savage |
Departamento de Computacion University of Mexico, Mexico |
|
R.Piotrowski |
State Pedagogical University of St-Petersburg, Russia |
|
Y.Kosarev |
SPIIRAS, St-Petersburg, Russia |
ORGANIZING COMMITTEE
|
Chair: |
|
|
Yuri Kosarev |
SPIIRAS, Russia |
|
Members: |
|
|
Izolda Lee |
SPIIRAS, Russia |
|
Andrey Ronjin |
SPIIRAS, Russia |
|
Anatoli Tkatsh |
SPIIRAS, Russia |
|
Aleksandr Shalin |
SPIIRAS, Russia |
REGISTRATION
Registration fees are arranged as following:
|
Western and Japan participants |
$ 300 |
|
Western students |
$ 150 |
|
Central Europe participants |
$ 180 |
|
Central Europe students |
$ 80 |
|
Russian and former SU states participants |
$ 50 |
|
Russian students |
free of charge |
Payments can only be made in US dollars cash.
The fees include the Reception, a copy of the workshop Proceedings, all workshop material, admission to all sessions and to the exhibition, banquet, and coffee break refreshments.
Additional copies of the Proceedings cost $ 20.
CONTACT ADDRESS
All correspondence regarding the workshop should be addressed to:
Dr. Yu. Kosarev
St.-Petersburg Institute for Informatics and Automation,
39, 14th line, St.-Petersburg, 199178, RUSSIA
Tel.: 812 328 7081
Fax : 812 328 4450
E-mail: specom@mail.iias.spb.su
http://www.spiiras.nw.ru/speech
TECHNICAL PROGRAM
The program at a glance
|
Date |
Time |
Sessions |
|
25.09 |
1000-1300 |
Opening ceremony (Session O). |
|
1400-1800 |
Session 1: Dialogue systems. Multi-lingual and Multi-modal systems. Speech Translation. |
|
|
26.09 |
900-1300 |
Session 2: Speech Recognition - 1. |
|
1400-1800 |
Session 3: Speech Recognition - 2. |
|
|
27.09 |
900-1300 |
Session 4: Student Session. |
Time schedule
Survey lectures: report - 30 min., answers to questions - 10 min.
Regular reports: report - 15 min., answers to questions - 5 min.
MONDAY MORNING, Sept. 25
Opening ceremony
|
8:00 |
Registration, Coffee |
|
10:00 |
City Government, Russian Academy of Science |
|
10:15 |
Prof. Rafael M. Yusupov General Chair, SPIIRAS Director, Russia |
|
10:30 |
Prof. R. Piotrowski General Scientific Chair of Speech and Language Research Center, Herzen State Pedagogical University of Russia, Russia |
|
10:45 |
Dr. Yuri Kosarev Organizing Committee Chair, SPIIRAS, Russia
Survey lectures (Session O) |
|
11:00 |
Achievements and Challenges in Speech Dialogue with Computer Yuri Kosarev Chair, St. Petersburg Institute for Informatics and Automation, Russia |
|
11:40 |
Naturalness of Synthesized Speech: Choice of Basic Sound Units Pavel Skrelin St. Petersburg State University, Department of Phonetics |
|
12:20 |
Language and Speech Synergetics Rajmund Piotrowski, Yuri Romanov Herzen State Pedagogical University of Russia, Russia |
|
13:00 |
Lunch |
MONDAY AFTERNOON, Sept. 25
Session 1: Dialogue Systems. Speech Understanding.
Multi-lingual and Multi-modal Systems.
Speech Translation.
|
14:00 |
Russian Phonetics in Distance Education V.V. Potapov, G.E. Kedrova, O.V. Dedova Department of Philology, Moscow State Lomonosov University, Russia |
|
14:30 |
Oral SILOD - an Experimental System of Oral Machine Translation L. Beliaeva, N. Zaitseva, S. Makarska, N. Nymm, K. Piotrowska, Y. Romanov Herzen State Pedagogical University of Russia, Russia |
|
15:00 |
Multimodal Dialogue Management L.J.M. Rothkrantz & R.J. van Vark Delft University of Technology Department of Knowledge Based System, The Netherlands |
|
15:30 |
Coffee break |
|
16:00 |
Discussion |
|
18:00 |
Banquet |
TUESDAY MORNING, Sept. 26
Session 2: Speech Recognition - 1.
|
9:00 |
The Experience of Using of the Visual Information with Acoustic-Speech Recognition Purposes R.K. Potapova, A.N. Sobakin Department of Applied and Experimental Linguistics, Moscow State Linguistic University, Russia |
|
9:30 |
TT Continuous Speaker-Independent Speech Recognizer Oleg Maleev Titan Technology, St.-Petersburg, Russia |
|
10:00 |
Optimization of clusters distances matrix G.V. Galunov and A. F. Kononov AudiTech Ltd., Saint-Petersburg |
|
10:30 |
Automatic speech signal segmentation using neural networks G.V.Galunov, A.F.Kononov and B.A.Smirnov AudiTech ltd., Saint-Petersburg, Russia |
|
11:00 |
Coffee break |
|
11:30 |
On a Cepstrum-Based Speech Detector Robust to White Noise Sergei Skorik and Frederic Berthommier Institute de la Communication Palree (ICP/INPG), France |
|
12:00 |
Preprocessing and Classification of Emotional Features in Speech Sentences ...................Apolloni Bruno1, Aversano Guido2, Esposito Anna2 1Departimento di Scienze dell’informazione , Universita di Milano, Italy 2 International Institute for Advanced Scientific Studies, Italy |
|
12:30 |
A Neuro-Fuzzy Inference System for Noise Source Identification .....................................A.Esposito1,2, E.C.Ezin1,3, C.A. Reyes-Garcia4 1International Institute for Advances Scientific Studies, Italy 2 INFM Salerno University, Italy3 Institut de Mathematigues et de Sciences Physigues, Italy4 Instituto Tecnologico de Apizaco-DGIT, Italy |
|
13:00 |
Lunch |
TUESDAY AFTERNOON, Sept. 26 Session 3: Speech Recognition - 2.
|
14:00 |
The ALERT System: Advanced Broadcast Speech Recognition Technology for Selective Dissemination if Multimedia Information G.Rigoll, A. Kosmala Gerhard-Mercator-University Duisburg Faculty of Electrical Engineering, Dept. of Computer Science, Germany |
|
14:30 |
. Detection of Prosodic Events Using Acoustic-Prosodic Features and Part-of-Speech Tags Jan Buckow, Anton Batliner, Richard Huber, Heinrich Niemann, Elmar Noth, Volker Warnke University of Erlangen-Nuremberg, Chair for Pattern Recognition (Computer Science 5), Germany |
|
15:00 |
Acoustic modeling for Polish Stefan Grocholewski Institute of Computing Science, Poznan University of Technology, Poland |
|
15:30 |
Accurate acoustic modeling for Russian Vladimir Chuchupal, Konstantin Makovkin, Alexander Chichagov Computer Center, Russian Academy of Science, Russia |
|
16:00 |
Coffee break |
|
16:30 |
Multy-Stream Words Recognition Based On a Large Set of Decision Rules and Acoustic Features Boris Lobanov, Tatiana Levkovskaya Institute of Engineering Cybernetics, Minsk, BELARUS |
WEDNESDAY MORNING, Sept. 27
Session 4: Student Session.
|
9:00 |
Physiological Processes Lungs Model At Speech Formation Prof. Dr. Vladimir P. Bondarenko, Poman V. Metcherjakov, Vladislav P. Kotsubinsky Tomsk State University for Control System and RAdioelectronics, Russia |
|
9:30 |
Semantic Representation In Dialogue Systems Roman Moucek, Karel Tauser Department of Computer Science and Engineering University of West Bohemia |
|
10:00 |
Response Generation in Information Dialogue System Karel Tauser, Roman Moucek Department of Computer Science and Engineering University of West Bohemia in Pilsen, Czech Republic |
|
10:30 |
Quasi-allophone method for acoustic + voice adaptation A. Ronjin, I. Lee, Yu. A.Kosarev St. Petersburg Institute for Informatics and Automation, Russia |
|
11:00 |
Statistical interpretation Veber’s rule on sensitiveness threshold of ear human system. V.I. Anciperov, Yu.V. Guliaev, S.A. Nikitov Radiotechnical and Electronical Institute Russian Academy of Science, Russia |
|
11:30 |
Duscussion |
|
13:00 |
Lunch |
THURSDAY AFTERNOON, Sept. 27
14:00 Discussions. Closing ceremony.