New generalized sidelobe canceller with denoising auto-encoder for improved speech enhancement

Minkyu Shin, Seongkyu Mun, David K. Han, Hanseok Ko

Research output: Contribution to journalArticle

Abstract

In this paper, a multichannel speech enhancement system which adopts a denoising auto-encoder as part of the beamformer is proposed. The proposed structure of the generalized sidelobe canceller generates enhanced multi-channel signals, instead of merely one channel, to which the following denoising auto-encoder can be applied. Because the beamformer exploits spatial information and compensates for differences in the transfer functions of each channel, the proposed system is expected to resolve the difficulty of modelling relative transfer functions consisting of complex numbers which are hard to model with a denoising auto-encoder. As a result, the modelling capability of the denoising auto-encoder can concentrate on removing the artefacts caused by the beamformer. Unlike conventional beamformers, which combine these artefacts into one channel, they remain separated for each channel in the proposed method. As a result, the denoising auto-encoder can remove the artefacts by referring to other channels. Experimental results prove that the proposed structure is effective for the six-channel data in CHiME, as indicated by improvements in terms of speech enhancement and word error rate in automatic speech recognition.

Original languageEnglish
Pages (from-to)3038-3040
Number of pages3
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE100A
Issue number12
DOIs
Publication statusPublished - 2017 Dec 1

Fingerprint

Speech Enhancement
Speech enhancement
Denoising
Encoder
Transfer functions
Speech recognition
Transfer Function
Automatic Speech Recognition
Spatial Information
Complex number
Modeling
Error Rate
Resolve
Experimental Results

Keywords

  • Acoustic beamforming
  • Denoising auto-encoder
  • Generalized sidelobe canceller
  • Speech enhancement

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

New generalized sidelobe canceller with denoising auto-encoder for improved speech enhancement. / Shin, Minkyu; Mun, Seongkyu; Han, David K.; Ko, Hanseok.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E100A, No. 12, 01.12.2017, p. 3038-3040.

Research output: Contribution to journalArticle

@article{6eb5dbb0ade245c49bc75b3d4c0fe346,
title = "New generalized sidelobe canceller with denoising auto-encoder for improved speech enhancement",
abstract = "In this paper, a multichannel speech enhancement system which adopts a denoising auto-encoder as part of the beamformer is proposed. The proposed structure of the generalized sidelobe canceller generates enhanced multi-channel signals, instead of merely one channel, to which the following denoising auto-encoder can be applied. Because the beamformer exploits spatial information and compensates for differences in the transfer functions of each channel, the proposed system is expected to resolve the difficulty of modelling relative transfer functions consisting of complex numbers which are hard to model with a denoising auto-encoder. As a result, the modelling capability of the denoising auto-encoder can concentrate on removing the artefacts caused by the beamformer. Unlike conventional beamformers, which combine these artefacts into one channel, they remain separated for each channel in the proposed method. As a result, the denoising auto-encoder can remove the artefacts by referring to other channels. Experimental results prove that the proposed structure is effective for the six-channel data in CHiME, as indicated by improvements in terms of speech enhancement and word error rate in automatic speech recognition.",
keywords = "Acoustic beamforming, Denoising auto-encoder, Generalized sidelobe canceller, Speech enhancement",
author = "Minkyu Shin and Seongkyu Mun and Han, {David K.} and Hanseok Ko",
year = "2017",
month = "12",
day = "1",
doi = "10.1587/transfun.E100.A.3038",
language = "English",
volume = "E100A",
pages = "3038--3040",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "12",

}

TY - JOUR

T1 - New generalized sidelobe canceller with denoising auto-encoder for improved speech enhancement

AU - Shin, Minkyu

AU - Mun, Seongkyu

AU - Han, David K.

AU - Ko, Hanseok

PY - 2017/12/1

Y1 - 2017/12/1

N2 - In this paper, a multichannel speech enhancement system which adopts a denoising auto-encoder as part of the beamformer is proposed. The proposed structure of the generalized sidelobe canceller generates enhanced multi-channel signals, instead of merely one channel, to which the following denoising auto-encoder can be applied. Because the beamformer exploits spatial information and compensates for differences in the transfer functions of each channel, the proposed system is expected to resolve the difficulty of modelling relative transfer functions consisting of complex numbers which are hard to model with a denoising auto-encoder. As a result, the modelling capability of the denoising auto-encoder can concentrate on removing the artefacts caused by the beamformer. Unlike conventional beamformers, which combine these artefacts into one channel, they remain separated for each channel in the proposed method. As a result, the denoising auto-encoder can remove the artefacts by referring to other channels. Experimental results prove that the proposed structure is effective for the six-channel data in CHiME, as indicated by improvements in terms of speech enhancement and word error rate in automatic speech recognition.

AB - In this paper, a multichannel speech enhancement system which adopts a denoising auto-encoder as part of the beamformer is proposed. The proposed structure of the generalized sidelobe canceller generates enhanced multi-channel signals, instead of merely one channel, to which the following denoising auto-encoder can be applied. Because the beamformer exploits spatial information and compensates for differences in the transfer functions of each channel, the proposed system is expected to resolve the difficulty of modelling relative transfer functions consisting of complex numbers which are hard to model with a denoising auto-encoder. As a result, the modelling capability of the denoising auto-encoder can concentrate on removing the artefacts caused by the beamformer. Unlike conventional beamformers, which combine these artefacts into one channel, they remain separated for each channel in the proposed method. As a result, the denoising auto-encoder can remove the artefacts by referring to other channels. Experimental results prove that the proposed structure is effective for the six-channel data in CHiME, as indicated by improvements in terms of speech enhancement and word error rate in automatic speech recognition.

KW - Acoustic beamforming

KW - Denoising auto-encoder

KW - Generalized sidelobe canceller

KW - Speech enhancement

UR - http://www.scopus.com/inward/record.url?scp=85038211226&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038211226&partnerID=8YFLogxK

U2 - 10.1587/transfun.E100.A.3038

DO - 10.1587/transfun.E100.A.3038

M3 - Article

VL - E100A

SP - 3038

EP - 3040

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 12

ER -