Multi-band long-term signal variability features for robust voice activity detection Conference Paper uri icon

abstract

  • 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.

name of conference

  • Interspeech 2013

published proceedings

  • 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5

author list (cited authors)

  • Tsiartas, A., Chaspari, T., Katsamanis, N., Ghosh, P., Li, M., Van Segbroeck, M., Potamianos, A., & Narayanan, S. S.

citation count

  • 6

complete list of authors

  • Tsiartas, Andreas||Chaspari, Theodora||Katsamanis, Nassos||Ghosh, Prasanta||Li, Ming||Van Segbroeck, Maarten||Potamianos, Alexandros||Narayanan, Shrikanth S

publication date

  • January 2013