HAPPY Team Entry to NIST OpenSAD Challenge: A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors

Tomi Kinnunen, Alexey Sholokhov, Elie Khoury, Dennis Alexander Lehmann Thomsen, Md. Sahidullah, Zheng-Hua Tan


Speech activity detection (SAD), the task of locating speech segments from a given recording, remains challenging under acoustically degraded conditions. In 2015, National Institute of Standards and Technology (NIST) coordinated OpenSAD bench-mark. We summarize “HAPPY” team effort to OpenSAD. SADs come in both unsupervised and supervised flavors, the latter requiring a labeled training set. Our solution fuses six base SADs (2 supervised and 4 unsupervised). The individually best SAD, in terms of detection cost function (DCF), is supervised and uses adaptive segmentation with i-vectors to represent the segments. Fusion of the six base SADs yields a relative decrease of 9.3% in DCF over this SAD. Further, relative decrease of 17.4% is obtained by incorporating channel detection side information.


DOI: 10.21437/Interspeech.2016-1281

Cite as

Kinnunen, T., Sholokhov, A., Khoury, E., Thomsen, D.A.L., Sahidullah, M., Tan, Z. (2016) HAPPY Team Entry to NIST OpenSAD Challenge: A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors. Proc. Interspeech 2016, 2992-2996.

Bibtex
@inproceedings{Kinnunen+2016,
author={Tomi Kinnunen and Alexey Sholokhov and Elie Khoury and Dennis Alexander Lehmann Thomsen and Md. Sahidullah and Zheng-Hua Tan},
title={HAPPY Team Entry to NIST OpenSAD Challenge: A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors},
year=2016,
booktitle={Interspeech 2016},
doi={10.21437/Interspeech.2016-1281},
url={http://dx.doi.org/10.21437/Interspeech.2016-1281},
pages={2992--2996}
}