Speedup and performance improvement of ica-based robot audition by parallel and resampling-based block-wise processing

Ryu Takeda*, Kazuhiro Nakadai, Toru Takahashi, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

*この研究の対応する著者

研究成果

2 被引用数 (Scopus)

抄録

This paper describes a speedup and performance improvement of multi-channel semi-blind ICA (MCSB-ICA) with parallel and resampling-based block-wise processing. MCSB-ICA is an integrated method of sound source separation that accomplishes blind source separation, blind dereverberation, and echo cancellation. This method enables robots to separate user's speech signals from observed signals including the robot's own speech, other speech and their reverberations without a priori information. The main problem when MCSB-ICA is applied to robot audition is its high computational cost. We tackle this by multi-threading programming, and the two main issues are 1) the design of parallel processing and 2) incremental implementation. These are solved by a) multiple-stack-based parallel implementation, and b) resampling-based overlaps and block-wise separation. The experimental results proved that our method reduced the real-time factor to less than 0.5 with an eight-core CPU, and it improves the performance of automatic speech recognition by 2.10 points compared with the single-stack-based parallel implementation without the resampling technique.

本文言語English
ホスト出版物のタイトルIEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings
ページ1949-1956
ページ数8
DOI
出版ステータスPublished - 2010 12 1
外部発表はい
イベント23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Taipei, Taiwan, Province of China
継続期間: 2010 10 182010 10 22

出版物シリーズ

名前IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings

Conference

Conference23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010
国/地域Taiwan, Province of China
CityTaipei
Period10/10/1810/10/22

ASJC Scopus subject areas

  • 人工知能
  • 人間とコンピュータの相互作用
  • 制御およびシステム工学

フィンガープリント

「Speedup and performance improvement of ica-based robot audition by parallel and resampling-based block-wise processing」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル