Automatic estimation of reverberation time with robot speech to improve ICA-based robot audition

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents an ICA-based robot audition system which estimates the reverberation time of the environment automatically by using the robot's own speech. The system is based on multi-channel semi-blind independent component analysis (MCSB-ICA), a source separation method using a microphone array that can separate user and robot speech under reverberant environments. Perception of the reverberation time (RT) is critical, because an inappropriate RT degrades separation performance and increases processing time. Unlike most previous methods that assume the RT is given in advance, our method estimates an RT by using the echo's intensity of the robot's own speech. It has three steps: speaks a sentence in a new environment, calculates the relative powers of the echoes, and estimates the RT using linear regression of them. Experimental results show that this method sets an appropriate RT for MCSB-ICA for real-world environments and that word correctness is improved by up to 6 points and processing time is reduced by up to 60%.

Original languageEnglish
Title of host publication9th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS09
Pages250-255
Number of pages6
DOIs
Publication statusPublished - 2009 Dec 1
Externally publishedYes
Event9th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS09 - Paris, France
Duration: 2009 Dec 72009 Dec 10

Publication series

Name9th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS09

Conference

Conference9th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS09
CountryFrance
CityParis
Period09/12/709/12/10

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Automatic estimation of reverberation time with robot speech to improve ICA-based robot audition'. Together they form a unique fingerprint.

  • Cite this

    Takeda, R., Nakadai, K., Takahashi, T., Komatani, K., Ogata, T., & Okuno, H. G. (2009). Automatic estimation of reverberation time with robot speech to improve ICA-based robot audition. In 9th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS09 (pp. 250-255). [5379572] (9th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS09). https://doi.org/10.1109/ICHR.2009.5379572