ACOUSTIC AND PHONETIC ASPECTS OF MODELING HUMAN-COMPUTER COMMUNICATION
Keywords:
speech, automatic speech synthesis, speech recognition, communication, phonetics, dialogueAbstract
The article summarizes the main approaches to modeling human-computer speech communication by integrating speech synthesis and recognition technologies into the graphical user interfaces. Modern automatic dialogue systems are in the focus of attention. They combine automatic speech synthesis and recognition with conceptual models of knowledge required for modeling relevant human-computer dialogue. The reasons causing additional complications in speech synthesis and recognition are carefully analyzed. The article offers a principal scheme for the acoustic-phonetic analysis of human speech. The components of a typical automatic dialogue system are singled out and examined using the instruments of modern experimental phonetics. The paper suggests a guide of how to implement the mechanisms of modern signal phonetics in order to improve the performance of automatic dialogue systems.
References
Біскуб І. П. Англомовний дискурс програмного забезпечення як модель мовленнєвої взаємодії людини й комп’ютера : монографія / І. П. Біскуб. – Луцьк : Волин. нац. ун-т ім. Лесі Українки, 2009. – 388 с.
Вейценбаум Дж. Возможности вычислительных машин и человеческий разум: от суждений к вычислениям / Дж. Вейценбаум. – М. : Радио и связь, 1982. – 368 с.
Потапова Р. К. Введение в лингвокибернетику / Р. К. Потапова. – М. : Изд-во Моск. гос. лингв. ун-та, 1990. – 140 с.
Beale R. NeuralNetworks and Pattern Recognition in Human-computer Interaction / R. Beale, J. Finlay. – N. Y. : Ellis Horwood, 1992. – 386 p.
Bennacef S. An Oral Dialogue Model Based on Speech Acts Categorization, Workshop on Spoken Dialogue Systems / S. Bennacef, F. Nйel, H. Bonneau-Maynard // ESCA Workshop on Spoken Dialogue Systems. – 1995. – P. 237–240.
Carpenter B. Human versus machine: psycholinguistics meets ASR / B. Carpenter // Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding. – Keystone, CO., 1999. – P. 225–228.
Cutler A. Response time as a metric for comparison of speech recognition by humans and machines / A. Cutler, T. Robinson // Proceedings of ICSLP. – Banff, Canada, 1992. – P. 189–192.
Dusan S. On integrating insights from human speech recognition into automatic speech recognition / S. Dusan, L. R. Rabiner // Proceedings of Interspeech. – Lisabon, Portugal, 2005. – P. 1233–1236.
Fink J. Personalised hypermedia information through adaptive and adaptable system features: User modeling, privacy and security issues / J. Fink, A. Kobsa, J. Schreck // Intelligence in Services and Networks: Technology for Cooperative Competition / A. Mullery, M. Besson R. Campolargo, R. Reed (Eds.). – Berlin ; Heidelberg : Springer, 1997. – P. 459–467.
Holmes J. Speech synthesis and recognition / J. Holmes, W. Holmes. – London ; N. Y. : Taylor and Fransis, 2002. – 298 p.
Lippmann R. Speech recognition by machines and humans / R. Lippmann // Speech Communication. – 1997. – No 22 (1). – P. 1–15.
Maier V. Aninvestigation into a simulation of episodic memory for automatic speechrecognition / V. Maier, R. K. Moore // Proceedings ofInterspeech. – Lisbon, Portugal, 2005. – P. 1245–1248.
McGuire T. W. Groupand computer-mediated discussion effects in risk decision making / T. W. McGuire, S. Kiesler, J. Siegel // Journal of Personality and Social Psychology. – 1987. – No 52. – P. 917–930.
Minker W. Speech and Human-Machine Dialog / W. Minker, S. Bennasef. – N. Y. ; Boston ; Dordrecht ; London ; Moscow : Kluwer Academic Publishers, 2004. – 89 p.
Moore R. K. Constraints on theories of human vs. machine recognition of speech / R. K. Moore, A. Cutler // Proceedings of the Workshop on Speech Recognition as Pattern Classification / eds. by R. Smits, J. Kingston, T. M. Nearey, R. Zondervan. – Nijmegen : MPI for Psycholinguistics, 2001. – P. 145–150.
Nass C. Speech interfaces from an evolutionary perspective / C. Nass, L. Gong // Communications of the ACM. – 2000. – No 43 (9). – P. 36–43.
Shi R. Function words in early speech perception / R. Shi, J. Werker, A. Cutler // The proceedings of the 15th International Congress of Phonetic Sciences Casual Products. – Adelaide. – 2003. – [CD-ROM. – 3009–3012].
Weintraub M. Linguistic constraints in hidden Markov model based speech recognition / [M. Weintraub, H. Murveit, M. Cohen, P. Price, J. Bernstein, G. Baldwin, D. Bell ] // Proc. ICASSP_89. – Glasgow, Scotland, May 1989. – P. 699–702.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
