UNSUPERVISED SPEAKER SEGMENTATION OF BROADCAST NEWS USING MDL-BASED GAUSSIAN MODEL

Jia Hsin Hsieh, Chung Hsien Wu

研究成果: Conference article同行評審

摘要

This paper proposes an approach for unsupervised speaker segmentation and gender discrimination of broadcast news. In this paradigm, a speaker segmentation mechanism using MDL-based Gaussian model is firstly adopted to determine the speaker changes using mean and covariance of the Gaussian model. These speaker segments partitioned by speaker changes are smoothed and discriminated into male or female. Experimental results show the proposed method achieved a better performance with 9.2% missed detection rate and 7.5% false alarm rate compared to the Delta-BIC method for speaker segmentation on broadcast news. In addition, the segment-based gender discrimination improves 9% accuracy compared to the clip-based discriminator.

All Science Journal Classification (ASJC) codes

  • 語言與語言學
  • 人機介面
  • 訊號處理
  • 軟體
  • 建模與模擬

指紋

深入研究「UNSUPERVISED SPEAKER SEGMENTATION OF BROADCAST NEWS USING MDL-BASED GAUSSIAN MODEL」主題。共同形成了獨特的指紋。

引用此