ICA-based efficient blind dereverberation and echo cancellation method for barge-in-able robot audition

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

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

11 Citations (Scopus)

Abstract

This paper describes a new method that allows "Barge-In" in various environments for robot audition. "Barge-in" means that a user begins to speak simultaneously while a robot is speaking. To achieve the function, we must deal with problems on blind dereverberation and echo cancellation at the same time. We adopt Independent Component Analysis (ICA) because it essentially provides a natural framework for these two problems. To deal with reverberation, we apply a Multiple Input/Output INverse-filtering Theorem-based model of observation to the frequency domain ICA. The main problem is its high-computational cost of ICA. We reduce the computational complexity to the linear order of reverberation time by using two techniques: 1) a separation model based on observed signal independence, and 2) enforced spatial sphering for preprocessing. The experimental results revealed that our method improved word correctness of reverberant speech by 10-20 points.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages3677-3680
Number of pages4
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei
Duration: 2009 Apr 192009 Apr 24

Other

Other2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
CityTaipei
Period09/4/1909/4/24

Fingerprint

Echo suppression
Barges
Independent component analysis
Audition
Reverberation
Robots
Computational complexity
Costs

Keywords

  • Barge-In
  • Blind dereverberation
  • Echo cancellation
  • ICA
  • MINT

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Takeda, R., Nakadai, K., Takahashi, T., Komatani, K., Ogata, T., & Okuno, H. G. (2009). ICA-based efficient blind dereverberation and echo cancellation method for barge-in-able robot audition. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 3677-3680). [4960424] https://doi.org/10.1109/ICASSP.2009.4960424

ICA-based efficient blind dereverberation and echo cancellation method for barge-in-able robot audition. / Takeda, Ryu; Nakadai, Kazuhiro; Takahashi, Toru; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. p. 3677-3680 4960424.

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

Takeda, R, Nakadai, K, Takahashi, T, Komatani, K, Ogata, T & Okuno, HG 2009, ICA-based efficient blind dereverberation and echo cancellation method for barge-in-able robot audition. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 4960424, pp. 3677-3680, 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei, 09/4/19. https://doi.org/10.1109/ICASSP.2009.4960424
Takeda R, Nakadai K, Takahashi T, Komatani K, Ogata T, Okuno HG. ICA-based efficient blind dereverberation and echo cancellation method for barge-in-able robot audition. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. p. 3677-3680. 4960424 https://doi.org/10.1109/ICASSP.2009.4960424
Takeda, Ryu ; Nakadai, Kazuhiro ; Takahashi, Toru ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / ICA-based efficient blind dereverberation and echo cancellation method for barge-in-able robot audition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. pp. 3677-3680
@inproceedings{1e97cc3e0a66419c935c4d8269bc4cf8,
title = "ICA-based efficient blind dereverberation and echo cancellation method for barge-in-able robot audition",
abstract = "This paper describes a new method that allows {"}Barge-In{"} in various environments for robot audition. {"}Barge-in{"} means that a user begins to speak simultaneously while a robot is speaking. To achieve the function, we must deal with problems on blind dereverberation and echo cancellation at the same time. We adopt Independent Component Analysis (ICA) because it essentially provides a natural framework for these two problems. To deal with reverberation, we apply a Multiple Input/Output INverse-filtering Theorem-based model of observation to the frequency domain ICA. The main problem is its high-computational cost of ICA. We reduce the computational complexity to the linear order of reverberation time by using two techniques: 1) a separation model based on observed signal independence, and 2) enforced spatial sphering for preprocessing. The experimental results revealed that our method improved word correctness of reverberant speech by 10-20 points.",
keywords = "Barge-In, Blind dereverberation, Echo cancellation, ICA, MINT",
author = "Ryu Takeda and Kazuhiro Nakadai and Toru Takahashi and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2009",
doi = "10.1109/ICASSP.2009.4960424",
language = "English",
isbn = "9781424423545",
pages = "3677--3680",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - ICA-based efficient blind dereverberation and echo cancellation method for barge-in-able robot audition

AU - Takeda, Ryu

AU - Nakadai, Kazuhiro

AU - Takahashi, Toru

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2009

Y1 - 2009

N2 - This paper describes a new method that allows "Barge-In" in various environments for robot audition. "Barge-in" means that a user begins to speak simultaneously while a robot is speaking. To achieve the function, we must deal with problems on blind dereverberation and echo cancellation at the same time. We adopt Independent Component Analysis (ICA) because it essentially provides a natural framework for these two problems. To deal with reverberation, we apply a Multiple Input/Output INverse-filtering Theorem-based model of observation to the frequency domain ICA. The main problem is its high-computational cost of ICA. We reduce the computational complexity to the linear order of reverberation time by using two techniques: 1) a separation model based on observed signal independence, and 2) enforced spatial sphering for preprocessing. The experimental results revealed that our method improved word correctness of reverberant speech by 10-20 points.

AB - This paper describes a new method that allows "Barge-In" in various environments for robot audition. "Barge-in" means that a user begins to speak simultaneously while a robot is speaking. To achieve the function, we must deal with problems on blind dereverberation and echo cancellation at the same time. We adopt Independent Component Analysis (ICA) because it essentially provides a natural framework for these two problems. To deal with reverberation, we apply a Multiple Input/Output INverse-filtering Theorem-based model of observation to the frequency domain ICA. The main problem is its high-computational cost of ICA. We reduce the computational complexity to the linear order of reverberation time by using two techniques: 1) a separation model based on observed signal independence, and 2) enforced spatial sphering for preprocessing. The experimental results revealed that our method improved word correctness of reverberant speech by 10-20 points.

KW - Barge-In

KW - Blind dereverberation

KW - Echo cancellation

KW - ICA

KW - MINT

UR - http://www.scopus.com/inward/record.url?scp=70349208674&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349208674&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2009.4960424

DO - 10.1109/ICASSP.2009.4960424

M3 - Conference contribution

SN - 9781424423545

SP - 3677

EP - 3680

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -