Dynamic programming method for fine-tuning the boundary points in automatic segmentation of speech

• Autorzy: Szymański M. , Grocholewski S.
• Języki publikacji: EN

Abstrakty

EN

The important element of today's speech systems is the set of recorded wavefiles annotated by a sequence of phonemes and boundary time-points. As the manual segmentation of speech is a very laborious task, there is the need for automatic segmentation algorithms. However, it was observed that common HMM-based methods are prone to systematical errors. Thus, some boundary refinement approaches were introduced. In this paper we combine two sources of information: boundary error distribution and an acoustic observation distribution, in a single dynamic programming approach.

Słowa kluczowe

EN

speech segmentation; dynamic programming

• Wydawca: Instytut Podstawowych Problemów Techniki PAN ; Komitet Akustyki PAN ; Polskie Towarzystwo Akustyczne
• Czasopismo: Archives of Acoustics
• Rocznik: 2007
• Tom: Vol. 32, No. 1
• Strony: 127--134
• Opis fizyczny: Bibliogr. 8 poz., rys., tab.

Twórcy

autor

Szymański M.

autor

Grocholewski S.

• Poznań University of Technology, Institute of Computing Science, Piotrowo 3a, 60-965 Poznań, Poland,

Bibliografia

• [1] ADELL J., BONAFONTE A., Towards phone segmentation for concatenation speech synthesis, Proc. 5th Speech Synthesis Workshop, pp. 139.144, Pittsburgh 2004.
• [2] GROCHOLEWSKI S., CORPORA . Speech database for Polish diphones, Proc. Eurospeech'97, pp. 1735.1738, 1997.
• [3] KVALE K., Segmentation and labelling of speech, Ph.D. Thesis, Inst. for Teleteknikk, Trondheim 1993.
• [4] MATOUSEK J., TIHELKA D., PSUTKA J., Automatic segmentation for Czech concatenative speech synthesis using statistical approach with boundary-specific correction, Proc. Eurospeech 2003, pp. 301.304, Geneva 2003.
• [5] OSTENDORF M., DIGALAKIS V. V., KIMBALL O. A., From HMM's to segment models: a unified view of stochastic modeling for speech recognition, IEEE Trans. on Speech and Audio Proc., 4, 5, September 1996.
• [6] SZYMA´NSKI M., GROCHOLEWSKI S., Implementation of speech segmentation algorithm with statistical duration models [in Polish], Tuning the Model Parameters, RB.004/05, Poznań Univ. of Technology, Inst. of Computing Science 2005.
• [7] SZYMA´NSKI M., GROCHOLEWSKI S., Semi-automatic segmentation of speech: manual segmentation strategy, Problem Space Analysis, Proc. CORES'05, Wroc_aw 2005.
• [8] TAYLOR P. A., ISARD S. D., Automatic phone segmentation, Proc. Eurospeech, pp. 709.711, Genova 1991.