論文

査読有り
2010年

ACCELERATION OF SEQUENCE KERNEL COMPUTATION FOR REAL-TIME SPEAKER IDENTIFICATION

2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
  • Makoto Yamada
  • ,
  • Masashi Sugiyama
  • ,
  • Gordon Wichern
  • ,
  • Tomoko Matsui

開始ページ
1626
終了ページ
1629
記述言語
英語
掲載種別
研究論文(国際会議プロシーディングス)
DOI
10.1109/ICASSP.2010.5495542
出版者・発行元
IEEE

The sequence kernel has been shown to be a promising kernel function for learning from sequential data such as speech and DNA. However, it is not scalable to massive datasets due to its high computational cost. In this paper, we propose a method of approximating the sequence kernel that is shown to be computationally very efficient. More specifically, we formulate the problem of approximating the sequence kernel as the problem of obtaining a pre-image in a reproducing kernel Hilbert space. The effectiveness of the proposed approximation is demonstrated in text-independent speaker identification experiments with 10 male speakers-our approach provides significant reduction in computation time with limited performance degradation. Based on the proposed method, we develop a real-time kernel-based speaker identification system using Virtual Studio Technology (VST).

リンク情報
DOI
https://doi.org/10.1109/ICASSP.2010.5495542
DBLP
https://dblp.uni-trier.de/rec/conf/icassp/YamadaSWM10
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000287096001153&DestApp=WOS_CPL
URL
http://dblp.uni-trier.de/db/conf/icassp/icassp2010.html#conf/icassp/YamadaSWM10
ID情報
  • DOI : 10.1109/ICASSP.2010.5495542
  • ISSN : 1520-6149
  • DBLP ID : conf/icassp/YamadaSWM10
  • Web of Science ID : WOS:000287096001153

エクスポート
BibTeX RIS