Efficient blind dereverberation and echo cancellation based on independent component analysis for actual acoustic signals

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

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

This letter presents a new algorithm for blind dereverberation and echo cancellation based on independent component analysis (ICA) for actual acoustic signals. We focus on frequency domain ICA (FD-ICA) because its computational cost and speed of learning convergence are sufficiently reasonable for practical applications such as hands-free speech recognition. In applying conventional FD-ICA as a preprocessing of automatic speech recognition in noisy environments, one of the most critical problems is how to copewith reverberations. To extract a clean signal from the reverberant observation, we model the separation process in the shorttime Fourier transform domain and apply the multiple input/output inverse-filtering theorem (MINT) to the FD-ICA separation model. A naive implementation of this method is computationally expensive, because its time complexity is the second order of reverberation time. Therefore, themain issue in dereverberation is to reduce the high computational cost of ICA. In this letter, wereduce the computational complexity to the linear order of the reverberation time by using two techniques: (1) a separation model based on the independence of delayed observed signals with MINT and (2) spatial sphering for preprocessing. Experiments show that the computational cost grows in proportion to the linear order of the reverberation time and that ourmethod improves the word correctness of automatic speech recognition by 10 to 20 points in a RT20 =670 ms reverberant environment.

Original languageEnglish
Pages (from-to)234-272
Number of pages39
JournalNeural Computation
Volume24
Issue number1
DOIs
Publication statusPublished - 2012
Externally publishedYes

Fingerprint

Acoustics
Costs and Cost Analysis
Fourier Analysis
Hand
Observation
Learning
Reverberation
Independent Component Analysis
Recognition (Psychology)
Costs
Computational
Linear Order
Automatic Speech Recognition

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Arts and Humanities (miscellaneous)

Cite this

Efficient blind dereverberation and echo cancellation based on independent component analysis for actual acoustic signals. / Takeda, Ryu; Nakadai, Kazuhiro; Takahashi, Toru; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

In: Neural Computation, Vol. 24, No. 1, 2012, p. 234-272.

Research output: Contribution to journalArticle

@article{de25fb022fd84a6b98d7edde105b216c,
title = "Efficient blind dereverberation and echo cancellation based on independent component analysis for actual acoustic signals",
abstract = "This letter presents a new algorithm for blind dereverberation and echo cancellation based on independent component analysis (ICA) for actual acoustic signals. We focus on frequency domain ICA (FD-ICA) because its computational cost and speed of learning convergence are sufficiently reasonable for practical applications such as hands-free speech recognition. In applying conventional FD-ICA as a preprocessing of automatic speech recognition in noisy environments, one of the most critical problems is how to copewith reverberations. To extract a clean signal from the reverberant observation, we model the separation process in the shorttime Fourier transform domain and apply the multiple input/output inverse-filtering theorem (MINT) to the FD-ICA separation model. A naive implementation of this method is computationally expensive, because its time complexity is the second order of reverberation time. Therefore, themain issue in dereverberation is to reduce the high computational cost of ICA. In this letter, wereduce the computational complexity to the linear order of the reverberation time by using two techniques: (1) a separation model based on the independence of delayed observed signals with MINT and (2) spatial sphering for preprocessing. Experiments show that the computational cost grows in proportion to the linear order of the reverberation time and that ourmethod improves the word correctness of automatic speech recognition by 10 to 20 points in a RT20 =670 ms reverberant environment.",
author = "Ryu Takeda and Kazuhiro Nakadai and Toru Takahashi and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2012",
doi = "10.1162/NECO_a_00219",
language = "English",
volume = "24",
pages = "234--272",
journal = "Neural Computation",
issn = "0899-7667",
publisher = "MIT Press Journals",
number = "1",

}

TY - JOUR

T1 - Efficient blind dereverberation and echo cancellation based on independent component analysis for actual acoustic signals

AU - Takeda, Ryu

AU - Nakadai, Kazuhiro

AU - Takahashi, Toru

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2012

Y1 - 2012

N2 - This letter presents a new algorithm for blind dereverberation and echo cancellation based on independent component analysis (ICA) for actual acoustic signals. We focus on frequency domain ICA (FD-ICA) because its computational cost and speed of learning convergence are sufficiently reasonable for practical applications such as hands-free speech recognition. In applying conventional FD-ICA as a preprocessing of automatic speech recognition in noisy environments, one of the most critical problems is how to copewith reverberations. To extract a clean signal from the reverberant observation, we model the separation process in the shorttime Fourier transform domain and apply the multiple input/output inverse-filtering theorem (MINT) to the FD-ICA separation model. A naive implementation of this method is computationally expensive, because its time complexity is the second order of reverberation time. Therefore, themain issue in dereverberation is to reduce the high computational cost of ICA. In this letter, wereduce the computational complexity to the linear order of the reverberation time by using two techniques: (1) a separation model based on the independence of delayed observed signals with MINT and (2) spatial sphering for preprocessing. Experiments show that the computational cost grows in proportion to the linear order of the reverberation time and that ourmethod improves the word correctness of automatic speech recognition by 10 to 20 points in a RT20 =670 ms reverberant environment.

AB - This letter presents a new algorithm for blind dereverberation and echo cancellation based on independent component analysis (ICA) for actual acoustic signals. We focus on frequency domain ICA (FD-ICA) because its computational cost and speed of learning convergence are sufficiently reasonable for practical applications such as hands-free speech recognition. In applying conventional FD-ICA as a preprocessing of automatic speech recognition in noisy environments, one of the most critical problems is how to copewith reverberations. To extract a clean signal from the reverberant observation, we model the separation process in the shorttime Fourier transform domain and apply the multiple input/output inverse-filtering theorem (MINT) to the FD-ICA separation model. A naive implementation of this method is computationally expensive, because its time complexity is the second order of reverberation time. Therefore, themain issue in dereverberation is to reduce the high computational cost of ICA. In this letter, wereduce the computational complexity to the linear order of the reverberation time by using two techniques: (1) a separation model based on the independence of delayed observed signals with MINT and (2) spatial sphering for preprocessing. Experiments show that the computational cost grows in proportion to the linear order of the reverberation time and that ourmethod improves the word correctness of automatic speech recognition by 10 to 20 points in a RT20 =670 ms reverberant environment.

UR - http://www.scopus.com/inward/record.url?scp=83455200229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83455200229&partnerID=8YFLogxK

U2 - 10.1162/NECO_a_00219

DO - 10.1162/NECO_a_00219

M3 - Article

C2 - 22023192

AN - SCOPUS:83455200229

VL - 24

SP - 234

EP - 272

JO - Neural Computation

JF - Neural Computation

SN - 0899-7667

IS - 1

ER -