Show simple item record

dc.contributor.authorDavis, A.
dc.contributor.authorNordholm, Sven
dc.contributor.authorTogneri, R.
dc.identifier.citationDavis, Alan and Nordholm, Sven and Togneri, Roberto. 2006. Statistical voice activity detection using low-variance spectrum estimation and an adaptive threshold. IEEE Transactions on Audio, Speech, and Language Processing. 14 (2): pp. 412-423.

Traditionally voice activity detection algorithms are based on any combination of general speech properties such as temporal energy variations, periodicity, and spectrum. This paper describes a novel statistical method for voice activity detection using a signal to noise ratio measure. The method employs a low-variance spectrum estimate and determines an optimal threshold based on the estimated noise statistics. A possible implementation is presented and evaluated over a large test set and compared to current modern standardized algorithms. The evaluations indicate promising results with the proposed scheme being comparable or favorable over the whole test set.

dc.publisherIEEE Signal Processing Society
dc.subjectvoice activity detector
dc.subject- VAD
dc.subjectVoice activity detection
dc.subjectstatistical decision
dc.subjectadaptive voice activity detection
dc.titleStatistical voice activity detection using low-variance spectrum estimation and an adaptive threshold
dc.typeJournal Article
dcterms.source.titleIEEE Transactions on Audio, Speech, and Language Processing
curtin.departmentDepartment of Electrical and Computer Engineering
curtin.accessStatusFulltext not available

Files in this item


This item appears in the following Collection(s)

Show simple item record