Robot Audition based on Multiple-Input Independent Component Analysis for Recognizing Barge-In Speech under Reverberation
-
- Takeda Ryu
- Graduate School of Informatics, Kyoto University
-
- Nakadai Kazuhiro
- Honda Research Institute Japan Co., Ltd.
-
- Takahashi Toru
- Graduate School of Informatics, Kyoto University
-
- Komatani Kazunori
- Graduate School of Informatics, Kyoto University
-
- Ogata Tetsuya
- Graduate School of Informatics, Kyoto University
-
- Okuno Hiroshi G.
- Graduate School of Informatics, Kyoto University
Bibliographic Information
- Other Title
-
- 残響下でのバージイン発話認識のための多入力独立成分分析を応用したロボット聴覚
- ザンキョウ カ デ ノ バージイン ハツワ ニンシキ ノ タメ ノ タニュウリョク ドクリツ セイブン ブンセキ オ オウヨウ シタ ロボット チョウカク
Search this article
Abstract
This paper presents a new method based on independent component analysis (ICA) for enhancing a target source and suppressing other interfering sound sources, supposed that the latter are known. The method can provides in a reverberant environment a barge-in-able robot audition system; that is, the user can talk to the robot at any time even when the robot speaks. Our method separates and dereverberates the user's speech and the robot's one by using Multiple Input ICA. The critical issue for real-time processing is to reduce the computational complexity of Multiple Input ICA to the linear order of the reverberation time, which has not been proposed so far. We attain it by exploit the property of the independence relationship between late observed signals and late speech signals. Experimental results show that 1) the computational complexity of our method is less than the naïve Multiple Input ICA method, and that 2) our method improves word correctness of automatic speech recognition under barge-in and reverberant situations; by at most 40 points for reverberation time of 240[ms] and 30 points for 670[ms].
Journal
-
- Journal of the Robotics Society of Japan
-
Journal of the Robotics Society of Japan 27 (7), 782-792, 2011
The Robotics Society of Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679704463744
-
- NII Article ID
- 10025114321
-
- NII Book ID
- AN00141189
-
- ISSN
- 18847145
- 02891824
- http://id.crossref.org/issn/02891824
-
- NDL BIB ID
- 10374037
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed