Multi-band long-term signal variability features for robust voice activity detection
Publication
, Conference
Tsiartas, A; Chaspari, T; Katsamanis, N; Ghosh, P; Li, M; Van Segbroeck, M; Potamianos, A; Narayanan, SS
Published in: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
January 1, 2013
In this paper, we propose robust features for the problem of voice activity detection (VAD). In particular, we extend the long term signal variability (LTSV) feature to accommodate multiple spectral bands. The motivation of the multi-band approach stems from the non-uniform frequency scale of speech phonemes and noise characteristics. Our analysis shows that the multi-band approach offers advantages over the single band LTSV for voice activity detection. In terms of classification accuracy, we show 0.3%-61.2% relative improvement over the best accuracy of the baselines considered for 7 out 8 different noisy channels. Experimental results, and error analysis, are reported on the DARPA RATS corpora of noisy speech. Copyright © 2013 ISCA.
Duke Scholars
Published In
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
EISSN
1990-9772
ISSN
2308-457X
Publication Date
January 1, 2013
Start / End Page
718 / 722
Citation
APA
Chicago
ICMJE
MLA
NLM
Tsiartas, A., Chaspari, T., Katsamanis, N., Ghosh, P., Li, M., Van Segbroeck, M., … Narayanan, S. S. (2013). Multi-band long-term signal variability features for robust voice activity detection. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 718–722).
Tsiartas, A., T. Chaspari, N. Katsamanis, P. Ghosh, M. Li, M. Van Segbroeck, A. Potamianos, and S. S. Narayanan. “Multi-band long-term signal variability features for robust voice activity detection.” In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 718–22, 2013.
Tsiartas A, Chaspari T, Katsamanis N, Ghosh P, Li M, Van Segbroeck M, et al. Multi-band long-term signal variability features for robust voice activity detection. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2013. p. 718–22.
Tsiartas, A., et al. “Multi-band long-term signal variability features for robust voice activity detection.” Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2013, pp. 718–22.
Tsiartas A, Chaspari T, Katsamanis N, Ghosh P, Li M, Van Segbroeck M, Potamianos A, Narayanan SS. Multi-band long-term signal variability features for robust voice activity detection. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2013. p. 718–722.
Published In
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
EISSN
1990-9772
ISSN
2308-457X
Publication Date
January 1, 2013
Start / End Page
718 / 722