Rule Based Speech Signal Segmentation

• Autorzy: Greibus M. , Telksnys L.
• Języki publikacji: EN

Abstrakty

EN

This paper presents the automated speech signal segmentation problem. Segmentation algorithms based on energetic threshold showed good results only in noise-free environments. With higher noise level automatic threshold calculation becomes complicated task. Rule based postprocessing of segments can give more stable results. Off-line, on-line and extrema types of rules are reviewed. An extrema-type segmentation algorithm is proposed. This algorithm is enhanced by a rule base to extract higher energy level segments from noise. This algorithm can work well with energy like features. The experiments were made to compare threshold and rule-based segmentation in different noise types. Also was tested if multifeature segmentation can improve segmentation results. The extrema rule-based segmentation showed smaller error ratio in different noise types and levels. Proposed algorithm does not require high calculation resources. Such algorithm can be processed by devices with limited computing power.

Słowa kluczowe

EN

rule base; speech analysis; speech endpoint detection; speech segmentation

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2010
• Tom: nr 4
• Strony: 37--43
• Opis fizyczny: Bibliogr. 12 poz., rys., tab.

Twórcy

autor

Greibus M.

autor

Telksnys L.

• Institute of Mathematics and Informatics, Recognition Processes Department, Gostauto 12, LT-01108 Vilnius, Lithuania,

Bibliografia

• [1] Y. Hioka and N. Hamada, “Voice activity detection with array signal processing in the wavelet domain”, IEICE Trans. Fund. Elec. Commun. Comput. Sci., vol. 86, no. 11, pp. 2802–2811, 2003.
• [2] F. Beritelli and S. Casale, “Robust voiced/unvoiced speech classification using fuzzy rules”, in IEEE Worksh. Speech Cod. Telecommun. Proc., Pocono Manor, USA, 1997, pp. 5–6.
• [3] Y. Qi and B. R. Hunt, “Voiced-unvoiced-silence classifications of speech using hybridfeatures and a network classifier”, IEEE Trans. Speech Audio Proces., vol. 1, no. 2, pp. 250–255, 1993.
• [4] S. Basu, “A linked-HMM model for robust voicing and speech detection”, in IEEE Int. Conf. ICASSP’03, Hong Kong, China, 2003, vol. 1, pp. 816–819.
• [5] J. Lipeika, A. Lipeikiene, and L. Telksnys, “Development of isolated word speech recognition system”, Informatica, vol. 13, no. 1, pp. 37–46, 2002.
• [6] L. Lu, H. Jiang and H. J. Zhang, “A robust audio classification and segmentation method”, in Proc. 9th ACM Int. Conf. Multimedia, Ottawa, Canada, 2001, p. 211.
• [7] K. Waheed, K. Weaver, and F. Salam, “A robust algorithm for detecting speech segments using an entropic contrast” in Proc. IEEE Midwest Symp. Circ. Sys. MWCAS 2002, Tulsa, USA, 2002, vol. 5.
• [8] M. Greibus and L. Telksnys, “Speech segmentation features selection”, Inf. Technol., vol. 15, no. 4, pp. 33–45, 2009.
• [9] P. Mermelstein, “Automatic segmentation of speech into syllabic units”, J. Acoust. Soc. Am, vol. 58, no. 4, pp. 880–883, 1975.
• [10] S. Van Gerven and F. Xie, “A comparative study of speech detec- tion methods”, in Proc. 5th Eur. Conf. EUROSPEECH’97, Rhodes, Greece, 1997, vol. 3, Rhodes, Greece pp. 1095–1098.
• [11] Y. Hu and P. C. Loizou, “Subjective comparison and evaluation of speech enhancement algorithms”, Speech Commun., vol. 49, no. 7–8, pp. 588–601, 2007.
• [12] TIA/EIA-136-250 Standard, “TDMA third generation wireless – minimum performance standards for acelp voice activity detection. Tech. Rep., TIA, 2001.