Large vocabulary continuous speech recognition system for Polish

• Autorzy: Marasek K.
• Języki publikacji: EN

Abstrakty

EN

This paper describes the development of the LVCSR (Large Vocabulary Continuous Speech Recognition) system for Polish. All system components have been built from scratch: grapheme-to-phoneme converter, language models and acoustic models. Test results for twenty thousands word vocabulary continuous speech recognition (read sentences) are given. The system can be used as a basis for application oriented continuous speech recognition.

• Wydawca: Instytut Podstawowych Problemów Techniki PAN ; Komitet Akustyki PAN ; Polskie Towarzystwo Akustyczne
• Czasopismo: Archives of Acoustics
• Rocznik: 2003
• Tom: Vol. 28, no. 4
• Strony: 293--303
• Opis fizyczny: Bibliogr. 17 poz., rys., tab.

Twórcy

autor

Marasek K.

• Polish-Japanese Institute of Information Technology, Koszykowa 86, 02-008 Warszawa, Poland,

Bibliografia

• [1] BABEL, Copernicus # 1304 project, P. ROACH et al., BABEL: An Eastern European Multi-Language Database, ICSLP-96, pp. 1982-1986, Philadelphia.
• [2] R. DE MORI [Ed.], Spoken dialogues with computers, Academic Press, 1998.
• [3] S. GROCHOLEWSKI, The use of HMMs for modelling Polish triphones [in Polish], Speech and Language Technology, W. JASSEM [Ed.], 5, 59-76, 2001.
• [4] L. MADELSKA, M. WITASZEK-SAMBORSKA, Phonetic transcription. A set of exercises [in Polish], Wydawnictwa UAM, Poznań 1997.
• [5] S. MARTINČIĆ-IPŠIĆ, J. ŽIBERT, I. IPŠIĆ, F. MIHELIČ, Speech recognition of Slovenian and Croatian weather forecasts, Proceedings B of the 5-th International Multi-Conference Language Technologies, 14-15-th October 2002, Ljubljana, ISBN 961-6303-42-2.
• [6] MBRDICO project, http://tcts.fpms.ac.be/synthesis/mbrdico.
• [7] J. PSUTKA, et al., Automatic transcription of Czech language oral history in the MALACH project: resources and initial experiments, Text, Speech, and Dialog Workshop, TSD2002, Brno 2002.
• [8] J. R. QUINLAN, Introduction of decision trees, Machine Learning, 1, 81-106, (1986).
• [9] R. ROSENFELD, Adaptive statistical language modelling: a maximum entropy approach, PhD Dissertation, CMU 1994.
• [10] T. SCHULTZ, M. WESTPHAL, A. WAIBEL, The global phone project: Multilingual LVCSR with JANUS-3, Multilingual Information Retrieval Dialogs: 2-nd SQEL Workshop, pp. 20-27, Plzen, April 1997.
• [11] SpeeCon IST-1999-10003 EC project, http://www.speecon.com.
• [12] K. SZAFRAN, The morphological analyser SAM-95 [in Polish], ftp://mimuw.edu.pl.
• [13] A. WIŚNIEWSKI, Automatic speech recognition on the basis of hidden Markov models – problems and methods [in Polish], Biuletyn Instytutu Automatyki i Robotyki WAT, 12, 3-83, (2000).
• [14] J. WELLS, SAMPA – (Speech assessment methods phonetic alphabet), http://www.phon.ucl.ac.uk/home/sampa/home.htm.
• [15] E. WHITTAKER, P. WOODLAND, Comparison of language modelling techniques for russian and english, Proceedings of ICSLP’98, Sydney 1998.
• [16] A. WRZOSKOWICZ, Hidden Markov models for noisy speech recognition, Proc. Eurospeech’93, pp. 1591-1594.
• [17] S. YOUNG, et al., The HTK Book, http://htk.eng.cam.ac.uk.