Development of Large Vocabulary Continuous Speech Recognition for Polish

• Authors: G. Demenko , M. Szymański , R. Cecko , E. Kuśmierek , M. Lange , K. Wegner , K. Klessa , M. Owsianny
• Languages of publication: EN

Abstracts

EN

In this study, the results of acoustic modeling used in a large vocabulary continuous speech recognition system are presented. The acoustic models have been developed with the use of a phonetically controlled large corpus of contemporary spoken Polish. Evaluation experiments showed that relatively good speech recognition results may be obtained with adequate training material, taking into account: (a) the presence of lexical stress; (b) speech styles (a variety of segmental and prosodic structures, various degrees of spontaneity of speech (spontaneous vs. read speech), pronunciation variants and dialects); (c) the influence of the sound level and background noises. The present large vocabulary continuous speech recognition evaluation results were obtained with Sclite assessment software. Moreover, the article delivers information about the speech corpus structure and contents and also a brief outline of the design and architecture of the automatic speech recognition system.

Keywords

EN

43.72.-p; 43.72.+q

Discipline

• 43.72.+q: Speech processing and communication systems

• Publisher: Institute of Physics, Polish Academy of Sciences
• Journal: Acta Physica Polonica A
• Year: 2012
• Volume: 121
• Issue: 1A
• Pages: A-86-A-91

Dates

published

2012-01

Contributors

author

G. Demenko

• Laboratory of Integrated Speech and Language Processing Systems, Poznań Supercomputing and Networking Center The Institute of Bioorganic Chemistry of the Polish Academy of Sciences, Poznań, Poland

author

M. Szymański

• Laboratory of Integrated Speech and Language Processing Systems, Poznań Supercomputing and Networking Center The Institute of Bioorganic Chemistry of the Polish Academy of Sciences, Poznań, Poland

author

R. Cecko

• Laboratory of Integrated Speech and Language Processing Systems, Poznań Supercomputing and Networking Center The Institute of Bioorganic Chemistry of the Polish Academy of Sciences, Poznań, Poland

author

E. Kuśmierek

• Laboratory of Integrated Speech and Language Processing Systems, Poznań Supercomputing and Networking Center The Institute of Bioorganic Chemistry of the Polish Academy of Sciences, Poznań, Poland

author

M. Lange

• Laboratory of Integrated Speech and Language Processing Systems, Poznań Supercomputing and Networking Center The Institute of Bioorganic Chemistry of the Polish Academy of Sciences, Poznań, Poland

author

K. Wegner

• Faculty of Electronics and Telecommunications, Poznań University of Technology, Poznań, Poland

author

K. Klessa

• The Institute of Linguistics, Department of Phonetics, Adam Mickiewicz University, Poznań, Poland

author

M. Owsianny

• Laboratory of Integrated Speech and Language Processing Systems, Poznań Supercomputing and Networking Center The Institute of Bioorganic Chemistry of the Polish Academy of Sciences, Poznań, Poland

References

• [1] G. Demenko, S. Grocholewski, K. Klessa, J. Ogórkiewicz, A. Wagner, M. Lange, D. Śledziński, N. Cylwik, in: Proc. 6th Int. Language Resources and Evaluation Conf., Marrakech 2008
• [2] R.K. Moore, in: Proc. Eurospeech, Geneva 2003, p. 2582
• [3] S. Ananthakrishnan, S. Narayanan, in: Proc. Int. Conf. on Acoustics, Speech and Signal Processing, Los Angeles 2007
• [4] M. Szymański, K. Klessa, M. Lange, B. Rapp, S. Grocholewski, G. Demenko, Best Practices - Nauka w obliczu społeczeństwa cyfrowego, Poznań 2010, p. 280
• [5] Handbook of Standards and Resources for Spoken Language Systems, Eds. D. Gibbon, R. Moore, R. Winski, Mouton de Gruyter, Berlin 1997
• [6] V. Fischer, F. Diehl, A. Kiessling, K. Marasek, Specification of Databases - Specification of Annotation, SPEECON Deliverale D214,2000
• [7] M. Szymański, S. Grocholewski, in: Proc. 2nd Language and Technology Conf., Poznań, 2005
• [8] K. Klessa, M. Karpiński, O. Bałdys, G. Demenko, Speech and Language Technology, Vol. 12/13 Polish Phonetic Association, Poznań, 2009
• [9] K. Klessa, G. Demenko, in: Proc. Interspeech, Brighton (UK) 2009, p. 1815
• [10] S. Young, G. Evermann, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, P. Woodland, The HTK Book (Version 3.2), Cambridge University Engineering Department, Cambridge 2002
• [11] A. Stolcke, in: Proc. Int. Conf. Spoken Language Processing, Denver, 2001
• [12] Sclite tool kit on-line documentation: http://www.itl.nist.gov/iad/mig/tools/
• [13] M. Maucec, T. Rotovnik, M. Zemljak, IJST 6, 245 (2003)
• [14] L.R Rabiner, in: Proc. IEEE 77, 257 (1989)
• [15] M. Steffen-Batogowa, T. Batóg, The Families of Polish Homophones. Dictionary of Homophones, Vol. 1, 2, Wydawnictwo UAM, Poznań, 2009, (in Polish)

Identifiers

DOI

10.12693/APhysPolA.121.A-86