Upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions

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

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

2 Citations (Scopus)

Abstract

This paper presents the upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. The goal is that the robot can automatically distinguish a target speech from its own speech and other sound sources in a reverberant environment. We focus on the multi-channel semi-blind ICA (MCSB-ICA), which is one of the sound source separation methods with a microphone array, to achieve such an audition system because it can separate sound source signals including reverberations with few assumptions on environments. The evaluation of MCSB-ICA has been limited to robot's speech separation and reverberation separation. In this paper, we evaluate MCSB-ICA extensively by applying it to multi-source separation problems under common reverberant environments. Experimental results prove that MCSB-ICA outperforms conventional ICA by 30 points in automatic speech recognition performance.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages4366-4371
Number of pages6
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 IEEE International Conference on Robotics and Automation, ICRA 2010 - Anchorage, AK
Duration: 2010 May 32010 May 7

Other

Other2010 IEEE International Conference on Robotics and Automation, ICRA 2010
CityAnchorage, AK
Period10/5/310/5/7

Fingerprint

Blind source separation
Barges
Independent component analysis
Audition
Robots
Source separation
Reverberation
Acoustic waves
Microphones
Speech recognition

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Takeda, R., Nakadai, K., Takahashi, T., Komatani, K., Ogata, T., & Okuno, H. G. (2010). Upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 4366-4371). [5509891] https://doi.org/10.1109/ROBOT.2010.5509891

Upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. / Takeda, Ryu; Nakadai, Kazuhiro; Takahashi, Toru; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

Proceedings - IEEE International Conference on Robotics and Automation. 2010. p. 4366-4371 5509891.

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

Takeda, R, Nakadai, K, Takahashi, T, Komatani, K, Ogata, T & Okuno, HG 2010, Upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. in Proceedings - IEEE International Conference on Robotics and Automation., 5509891, pp. 4366-4371, 2010 IEEE International Conference on Robotics and Automation, ICRA 2010, Anchorage, AK, 10/5/3. https://doi.org/10.1109/ROBOT.2010.5509891
Takeda R, Nakadai K, Takahashi T, Komatani K, Ogata T, Okuno HG. Upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. In Proceedings - IEEE International Conference on Robotics and Automation. 2010. p. 4366-4371. 5509891 https://doi.org/10.1109/ROBOT.2010.5509891
Takeda, Ryu ; Nakadai, Kazuhiro ; Takahashi, Toru ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. Proceedings - IEEE International Conference on Robotics and Automation. 2010. pp. 4366-4371
@inproceedings{086c0d43ab86475dba0c6bf378dafc01,
title = "Upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions",
abstract = "This paper presents the upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. The goal is that the robot can automatically distinguish a target speech from its own speech and other sound sources in a reverberant environment. We focus on the multi-channel semi-blind ICA (MCSB-ICA), which is one of the sound source separation methods with a microphone array, to achieve such an audition system because it can separate sound source signals including reverberations with few assumptions on environments. The evaluation of MCSB-ICA has been limited to robot's speech separation and reverberation separation. In this paper, we evaluate MCSB-ICA extensively by applying it to multi-source separation problems under common reverberant environments. Experimental results prove that MCSB-ICA outperforms conventional ICA by 30 points in automatic speech recognition performance.",
author = "Ryu Takeda and Kazuhiro Nakadai and Toru Takahashi and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2010",
doi = "10.1109/ROBOT.2010.5509891",
language = "English",
isbn = "9781424450381",
pages = "4366--4371",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - Upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions

AU - Takeda, Ryu

AU - Nakadai, Kazuhiro

AU - Takahashi, Toru

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2010

Y1 - 2010

N2 - This paper presents the upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. The goal is that the robot can automatically distinguish a target speech from its own speech and other sound sources in a reverberant environment. We focus on the multi-channel semi-blind ICA (MCSB-ICA), which is one of the sound source separation methods with a microphone array, to achieve such an audition system because it can separate sound source signals including reverberations with few assumptions on environments. The evaluation of MCSB-ICA has been limited to robot's speech separation and reverberation separation. In this paper, we evaluate MCSB-ICA extensively by applying it to multi-source separation problems under common reverberant environments. Experimental results prove that MCSB-ICA outperforms conventional ICA by 30 points in automatic speech recognition performance.

AB - This paper presents the upper-limit evaluation of robot audition based on ICA-BSS in multi-source, barge-in and highly reverberant conditions. The goal is that the robot can automatically distinguish a target speech from its own speech and other sound sources in a reverberant environment. We focus on the multi-channel semi-blind ICA (MCSB-ICA), which is one of the sound source separation methods with a microphone array, to achieve such an audition system because it can separate sound source signals including reverberations with few assumptions on environments. The evaluation of MCSB-ICA has been limited to robot's speech separation and reverberation separation. In this paper, we evaluate MCSB-ICA extensively by applying it to multi-source separation problems under common reverberant environments. Experimental results prove that MCSB-ICA outperforms conventional ICA by 30 points in automatic speech recognition performance.

UR - http://www.scopus.com/inward/record.url?scp=77955784920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955784920&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2010.5509891

DO - 10.1109/ROBOT.2010.5509891

M3 - Conference contribution

SN - 9781424450381

SP - 4366

EP - 4371

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -