Publication View

Universal Background Models for Real-Time Speaker Change Detection (2008)

Abstract
This paper addresses the problem of real-time speaker change detection in TV news broadcast, in which no prior knowledge on speakers is assumed. To enhance the effect of the reliable frames in a speech stream, we propose a new approach to feature categorization based on Gaussian Mixture Model- Universal Background Model (GMM-UBM). The feature vectors are categorized into three sets, which include reliable speech, doubtful speech and unreliable speech. Then a novel distance measure is presented for real-time speaker change detection. Extensive experiments demonstrate the superior performance of the proposed approach. The intrinsic difficulties on real-time speaker change detection are discussed as well in this paper. 1

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.123.9679
Source http://research.microsoft.com/users/llu/publications/mmm03_ubmforspkseg.pdf
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English
Relation 10.1.1.27.8804, 10.1.1.133.1595, 10.1.1.16.1742, 10.1.1.57.1972, 10.1.1.5.3825, 10.1.1.128.6678