HAPPY Team Entry to NIST OpenSAD Challenge: A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors
Self archived versionpublished version
MetadataShow full item record
CitationKinnunen, Tomi. Sholokhov, Alexey. Khoury, Elie. Thomsen, Dennis. Sahidullah, Md. Tan, Zheng-Hua. (2016). HAPPY Team Entry to NIST OpenSAD Challenge: A Fusion of Short-Term Unsupervised and Segment i-Vector Based Speech Activity Detectors. Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2992-2996. 10.21437/Interspeech.2016-1281.
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.