Multidimensional scaling for fast speaker clustering

Chi Chun Hsia, Kuo Yuan Lee, Chih Chieh Chuang, Yu-Hsien Chiu

研究成果: Conference contribution

3 引文 斯高帕斯(Scopus)

摘要

This study presents a fast speaker clustering method based on multidimensional scaling. Speech segments are trained as initial acoustic models. MDS is utilized to transform acoustic models to a space with the coordinate best preserve the distances or dissimilarity between models. Speaker clusters are clustered using vector quantization on the MDS coordinates and the acoustic speaker models are trained on MFCCs features for each cluster. Experimental results show the proposed method outperforms the baseline speaker clustering method in lower execution time.

原文English
主出版物標題2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Proceedings
頁面296-299
頁數4
DOIs
出版狀態Published - 2010 十二月 1
事件2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Tainan, Taiwan
持續時間: 2010 十一月 292010 十二月 3

出版系列

名字2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Proceedings

Other

Other2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010
國家Taiwan
城市Tainan
期間10-11-2910-12-03

All Science Journal Classification (ASJC) codes

  • Linguistics and Language

指紋 深入研究「Multidimensional scaling for fast speaker clustering」主題。共同形成了獨特的指紋。

引用此