CV - Professor Yuri Kosarev

CURRICULUM VITAE

Kosarev Yuri Alexandrovich, Doctor of Technical Sciences

Personal Data

born 16 March 1932 in Yaroslavl, Russia.
dead 8 August 2003 in Barcelona, Spain

Education

1957 - Graduated from Leningrad Institute for Electrical
Engineering;
1968 - Conferred on the Candidate in Technical Science Degree;
1994 - Conferred on the Doctor in Technical Science Degree.

Affiliation

1984 - 2003 Head of the Speech Informatics Group of St. Petersburg Institute for Informatics and Automation.

Research interests, achievements
The point is: a good recognition of words is not yet enough for real voice interaction with machine, but a robust semantic interpretation of spoken messages is required there. Unfortunately, usual approaches are based on mechanical combination of speech recognition and text understanding. Many attempts to do it have not got a real success because two main components of this combination (speech recognition and text understanding) are based on different histories, research paradigms, mathematical machinery. So they are not compatible.

So the global problem, crucial for all the perspective voice applications in automatic systems is : how to get a reliable sense of utterance in spite of relatively low level of word accuracy and diverse kind of acoustical- syntactical incorrectness.

To solve this problem we use some analogies from human speech communication, for example, associations, situative analysis for applied area, The Through Understanding (Insight) Phenomenon. Owing to above peculiarities our model allows: to refuse from strict syntax for inputting utterances, to provide required degree of working stability and accuracy under real conditions. About our work in this direction see a list of publications below.

Realization:

1. Project of speech operating system for the atomic power station equipment;
2. Project of speech operating system for perspective aircraft ;
3. Project for speech operated local computer net.
4. Dialog phrase book system.
5. System for robot voice operating etc.

Courses of Lectures
1. Methods of speech recognition/understanding - Gertzen State pedagogical university (SPU), St-Petersburg State University;
2. Natural Language and Computer Languages (SPU);
3. Computer speech technology in science and education (SPU).

Participation in Conferences

1. Intern. Conf. on Automation and Robotics ICARCV'94, Singapore
2. Regional Infomatics-94".St.Petersburg.
3. German Acoustics Conference DAGA-94. (Drezden)
4. German Acoustics Conference DAGA-95. (Saarbrucken)
5. 4th European Conference on Speech Communication and Technology,
6. EUROSPEECH'95 (Madrid, September )
7. Intern.Workshop "Integration of Language and Speech". Moscow-Domodedovo, 1995.
8. Intern. Conf. "Regional Informatics-95". St.Petersburg.
9. Intern. Workshop "Speech and Computer" - SPECOM'96,St-Petersburg.
10.ESCA 5th European Conference on Speech Communication and Technology,EUROSPEECH'97, Greece, 1997
11.2nd Intern.Workshop "Speech and Computer"-SPECOM'97,Romania
12.Intern. Workshop "Speech and Computer" - SPECOM'98,St-Petersburg
13. SPECOM'99, Moscow
14. International Workshop on Soft Computing in Industry, IWSCI'99, Muroran, Hokkaido, Japan, June 16-18.
15. Proc. International COST 254 Workshop on Intelligent ommunication Technologies and Applications. Neuchatel, Switzerland, May 5-7, 1999.
16. SPECOM'2000, St- Petersburg
17. SPECOM'2001, Moscow
18. SPECOM'2002, St- Petersburg
19. 15-th International Congress of Phonetic Sciences, Barcelona, Spain, August 2003

Membership in Scientific Committees of International Conferences:

"Speech and Computer" SPECOM'96, SPECOM'98, SPECOM'2000, SPECOM'2002.
SPECOM'97, EUROSPEECH'97, SPECOM'99, COST 254.

Membership in International Associations

ISCA-International Speech Communicational Association,
ISTN- International Speech Communicational Network

P u b l i c a t i o n s

1. Yu.A.Kosarev, F.M.Kulakov. The Model of Robot Speech Operation: Integration of Signal Processing and Application Area Modeling. Proc. Int. Conf. ICARCV'94, vol.2. SINGAPORE. 1994. pp. 1389-1391.
2. Yu.A.Kosarev. A Natural Form of Dialogue with Computer. Leningrad: Mashinostroenije, 1989. 143 p. (in Rus.).
3. Yu.A.Kosarev. Code Model of Speech Message. Leningrad:SPIIRAN, 1986. 23 p. (in Rus.).
4. Yu.A.Kosarev. The Through Understanding Model of Oral Speech. Leningrad: SPIIRAN, 1987. 20 p.(in Rus.).
5. Yu.A.Kosarev. Network Model of the Speech Recognition. Leningrad: SPIIRAN, 1988. 22 p. (in Rus.).
6. Yu.A.Kosarev. An Intelligent Speech Terminal. Proc. Intern. Symp. INFORMATICS-89. (Minsk, 1989), vol. 1, P. 413-418. ( in Rus.,sum. Engl.).
7. Yu.A.Kosarev. A Neuron like Model for Speech Recognition. Proc. Conf.of Speech Technology. Tallinn. 1989, pp. 12-13.
8. Yu.A.Kosarev, Yu.M.Kozlov. Theoretical Problems of Speech Informatics. Proc. Intern. Conf. "Regional Infomatics-94".
St.Petersburg. 1994. (in Rus.).
9. Yu.A.Kosarev. The Model of Oral Speech Semantic Interpretation : Quantitative Processing and Integration of Acoustic,
Syntactic, Semantic and Pragmatic Data. Proc. German Acoustics Conference DAGA-94. (Drezden, 1994), pp. 1281-1284.
10. Yu.A.Kosarev. Investigation and elaboration of the methods of the speech semantic interpretation. Abstr. of doct. diss.
Russ.Acad.of Sciences Inst. for Inf.& Aut. SPb. 1994.(in Rus.).
11. Yu.A.Kosarev, P.A.Jarov. Associations Help to Recognize Words. Proc. German Acoustics Conference DAGA-95. (Saarbrucken, 1995), vol 2. pp. 979-982.
12. Y.A. Kosarev, "Communicative Language Model: Structure and Functioning", in Proceedings of the ESCA 4th European Conference on Speech Communication and Technology, EUROSPEECH '95 (Madrid, sept. 1995), vol 2. Madrid: 1995, pp. 1211-1214.
13. Yu.Kosarev, Yu.Kozlov, R.Piotrowski. Speech and Computer: Signal Analysis, Syntax, Semantics, Pragmatics. Proc. Intern. Workshop "Integration of Language and Speech". Moscow-Domodedovo, 1995. pp. 69-78.
14. Yu.A.Kosarev, P.Jarov Speech Understanding in Situative Context: Reveal of Phrase Pragmatical Components.
Proc. Intern. Conf. "Regional Informatics-95". St.Petersburg. 1995. (in Rus.).
15. Yuri A.Kosarev. High-Level Processing of the Handwritten Text. Proc. Intern. Workshop "Speech and Computer" - SPECOM'96, St-Petersburg, 1996, pp. 113-116.
16.Yu.A.Kosarev. Problems Arisen by Spoken Language Modelling Proc. Intern. Workshop "Speech and Computer" - SPECOM'96, St-Petersburg, 1996, pp. 6-11.
17. Yu.Kosarev, R.Piotrowski. Spoken Language Translation Model Based on the Speech Understanding in Activity Context. Proc. Intern. Workshop "Speech and Computer" - SPECOM'96. St-Petersburg
18. Yu.Kosarev, R.Piotrowski. Synergetics and 'Insight' Strategy for Speech Processing. Literary and Linguistic Computing, Vol. 12, Oxford University Press 1997. pp.113-118.
19. Yu.Kosarev, P.Jarov, A.Osipov. "The Structural Weighted Sets Method for Continuous Speech and Text Recognition"- Proceedings of the ESCA 5th European Conference on Speech Communication and Technology, EUROSPEECH'97, Greece, 1997 pp. 2819-2822.
20. Yu.Kosarev. What Reserves We Still Don't Use for The Perfect Man-Machine Speech Dialogue. Proc. Intern. Workshop "Speech and Computer" - SPECOM'98. St-Petersburg, 1998, pp. 49-56.
21. S.Dikareva, Yu.Kosarev, et al. Speech Dialogue in Learning Systems for Foreign Language. Proc. Intern. Workshop "Speech and Computer" - SPECOM'98. St-Petersburg, 1998, pp. 101-104.
22. Yu. Kosarev, R.Piotrowski, et al. Language Perception Modeling Based on Analysis of Children's Speech.
Proc. Intern. Workshop "Speech and Computer" - SPECOM'98. St-Petersburg, 1998, pp. 161-168.
23. Yu. Kosarev, A.Osipov, et al. Network model for continuous speech understanding. Proc. Intern. Workshop "Speech and Computer" - SPECOM'98. St-Petersburg, 1998, pp.175-180.
24. Yuri Kosarev, Andrei Mikhailov. The SPIIRAS Approach to the Speech Understanding for Dialog Systems. Proc. International COST 254 Workshop on Intelligent Communication Technologies and Applications. Neuchatel, Switzerland, May 5-7, 1999.
25. Yuri Kosarev. The Role of Soft Computing in Speech Recognition/
Understanding Area. Proc. International Workshop on Soft Computing in Industry, IWSCI'99, Muroran, Hokkaido, Japan, June 16-18, 1999.
26. Yuri Kosarev, Jesus Savage. Realization of some reserves of language and extralinguistic knowledge for the speech dialogue systems improvement. Proc. SPECOM'99. Moscow.
27. Косарев Ю.А., Пиотровский Р.Г., Осипов А.Н. Проблемы, возникающие при моделировании устного естественного языка. В сборнике: Теоретические основы и прикладные задачи интеллектуальных информационных технологий. РАН, СПИИРАН, Санкт-Петербург, с 234-240.
28. Косарев Ю.А., Осипов А.Н. Система распознавания изолированных слов устной речи. В сб. Вычислительные процессы и структуры. Л. ЛИАП. 1982. с. 92-94.
29. Беляева Л.Н., Косарев Ю.А., Пиотровский Р.Г. Обработка речи и текста: Достижения, проблемы, пути. Вестник СПб отделения Российской академии естественных наук. 1999, 3,1. с. 72-82.
30. Yu.Kosarev. Achievements and Challenges in Speech Dialogue with Computer. Proc. Intern.Workshop "Speech and Computer" - SPECOM'2000. St-Petersburg, 2000, pp.1-7.
31. A.Ronjin, I. Lee, Yu. Kosarev. Qquasi-allophone method of acoustic and speech adaptation. Proc. Intern. Workshop "Speech and Computer" - SPECOM'2000. St-Petersburg, 2000, pp.91-93.
32. Yu. Kosarev. Crisis in speech technologies: some ways out from it. Abstract of report for the International Conference "Regional Informatics-2000". St-Petersburg, 2000.
33. Yuri Kosarev, Izolda Lee, Andrey Ronzhin, Jesus Savage. State of the Art in Speech Understanding. International Workshop SPECOM'2001, pp. 241-250. Moscow, 2001.
34. Yu.Kosarev, I.Lee, A.Ronzhin, A.Karpov. Continuous Speech Recognition Suitable for Robust Speech Understanding. International Workshop SPECOM'2002, St. Petersburg, 2002.
35. Yuri Kosarev, Izolda Lee, Andrey Ronzhin, Alexey Karpov, Jesus Savage, Fred Haritatos. Robust Speech Understanding for Voice control system. International Workshop SPECOM'2002, St. Petersburg, 2002.
36. Yuri Kosarev. Some aspects of Robust Speech Understanding. Invited lecture for the International Workshop SPECOM'2002, St.Petersburg, 2002.
37. A. Ronzhin, Yu. Kosarev, I. Lee, A. Karpov. The method of continuous speech recognition based on signal analysis in a sliding window and theory of the fuzzy sets. Scientific journal “Artificial Intelligence” of the Institute of Artificial Intelligence of the National Academy of Sciences of Ukraine, Volume 4, 2002, pp. 256-263.
38. Yuri Kosarev, Izolda Lee, Andrey Ronzhin, Alexey Karpov. Robust Speech Understanding Methods for New Intellectual Applications, AVIOS 2003 Conference, San Jose, California, USA, 2003
39. Yuri Kosarev, Andrey Ronzhin, Izolda Lee and Alexey Karpov. Continuous Speech Recognition without Use of High-Level Information, the 15-th International Congress of Phonetic Sciences, Barcelona, Spain, August 2003
40. Alexey Karpov, Yuri Kosarev, Andrey Ronzhin, Izolda Lee. Development of acoustical features of speech siganl robust to variations of signal scale and spectrum deformations", the 3-th All-Russian Conference "Theory and Practice of speech invertigations" ARSO-2003, Moscow, Russia, September 2003
41. Andrey Ronzhin, Yuri Kosarev, Alexey Karpov, Izolda Lee. Recognition and understanding of the continuous speech based on sliding analysis and integral structure of processing. In Proceedings of the Fourth International Scientific and Technical Conference "Intellectual and Multiprocessing Systems IMS ' 2003", Divnomorskoe, Russia, September 2003
42. Yuri Kosarev, Andrey Ronzhin, Alexey Karpov, Izolda Lee. Approaches to creation of situational databases for integral speech understanding models. International Workshop SPECOM'2003, Moscow, Russia, October 2003.
43. Andrey Ronzhin, Yuri Kosarev, Alexey Karpov, Izolda Lee. Elaboration of the intellectual speech interface provided accuracy, robustness and adaptability. International Workshop SPECOM'2003, Moscow, Russia, October 2003.