Barge-in-able robot audition based on ICA and missing feature theory under semi-blind situation

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

研究成果: Conference contribution

12 引用 (Scopus)

抜粋

This paper describes a robot audition system that allows the user to barge-in; that is, the user can speak simultaneously when the robot is speaking. Our "barge-in-able" system consists of two stages: (1) cancellation of robot speech and (2) recognition of the separated user speech under the "semi-blind situation". The semi-blind situation is where a robot's speech signal is known but a user's speech signal is not. The first stage is achieved by using an adaptive filter based on time-frequency domain Independent Component Analysis, because that can separate robot speech more robustly against noise than conventional echo cancellers. To improve performance in online processing, we utilized known source normalization and the exponentially weighted stepsize method. The second stage is achieved by automatic speech recognition (ASR) based on the missing feature theory which provides robust recognition by exploiting the reliability of speech features distorted due to noise and/or separation. The semi-blind situation simplifies the estimation of such reliabilities. Experiments demonstrated that our system improved word correctness of ASR by 10.0 %.

元の言語English
ホスト出版物のタイトル2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
ページ1718-1723
ページ数6
DOI
出版物ステータスPublished - 2008 12 1
イベント2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS - Nice, France
継続期間: 2008 9 222008 9 26

出版物シリーズ

名前2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

Conference

Conference2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
France
Nice
期間08/9/2208/9/26

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

フィンガープリント Barge-in-able robot audition based on ICA and missing feature theory under semi-blind situation' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Takeda, R., Nakadai, K., Komatani, K., Ogata, T., & Okuno, H. G. (2008). Barge-in-able robot audition based on ICA and missing feature theory under semi-blind situation. : 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS (pp. 1718-1723). [4650799] (2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS). https://doi.org/10.1109/IROS.2008.4650799