Deep bi-directional long short-term memory based speech enhancement for wind noise reduction

Jinkyu Lee; Keulbit Kim; Turaj Shabestary; Hong Goo Kang

doi:10.1109/HSCMA.2017.7895558

Deep bi-directional long short-term memory based speech enhancement for wind noise reduction

Jinkyu Lee, Keulbit Kim, Turaj Shabestary, Hong Goo Kang

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

17 Citations (Scopus)

Abstract

In this paper, we propose a new recurrent neural network (RNN)-based single-channel speech enhancement framework for off-line wind noise reduction. To adequately represent highly non-stationary characteristics of wind noise, we first adopt a deep bi-directional long short-term memory (DBLSTM) structure. However, its enhanced output becomes muffled due to the spectral over-smoothing effect. To overcome this problem, we propose a new structure of DBLSTM-based speech enhancement system that internally incorporates the speech and noise power estimation processes in the spectral filtering framework. Furthermore, we propose a structure with an additional internal constraint of minimizing log a priori SNR, which provides efficient learning mechanism. Experimental results show that the proposed method improves source-to-distortion ratio (SDR) by 6.9 dB and perceptual evaluation of speech quality (PESQ) by 0.24 in comparison to the conventional DBLSTM-based system.

Original language	English
Title of host publication	2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	41-45
Number of pages	5
ISBN (Electronic)	9781509059256
DOIs	https://doi.org/10.1109/HSCMA.2017.7895558
Publication status	Published - 2017 Apr 10
Event	2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - San Francisco, United States Duration: 2017 Mar 1 → 2017 Mar 3

Publication series

Name	2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings

Other

Other	2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017
Country/Territory	United States
City	San Francisco
Period	17/3/1 → 17/3/3

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Acoustics and Ultrasonics
Instrumentation
Communication

Access to Document

10.1109/HSCMA.2017.7895558

Cite this

Lee, J., Kim, K., Shabestary, T., & Kang, H. G. (2017). Deep bi-directional long short-term memory based speech enhancement for wind noise reduction. In 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings (pp. 41-45). Article 7895558 (2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HSCMA.2017.7895558

Lee, Jinkyu ; Kim, Keulbit ; Shabestary, Turaj et al. / Deep bi-directional long short-term memory based speech enhancement for wind noise reduction. 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 41-45 (2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings).

@inproceedings{84645b21c83842339c4666bec3664760,

title = "Deep bi-directional long short-term memory based speech enhancement for wind noise reduction",

abstract = "In this paper, we propose a new recurrent neural network (RNN)-based single-channel speech enhancement framework for off-line wind noise reduction. To adequately represent highly non-stationary characteristics of wind noise, we first adopt a deep bi-directional long short-term memory (DBLSTM) structure. However, its enhanced output becomes muffled due to the spectral over-smoothing effect. To overcome this problem, we propose a new structure of DBLSTM-based speech enhancement system that internally incorporates the speech and noise power estimation processes in the spectral filtering framework. Furthermore, we propose a structure with an additional internal constraint of minimizing log a priori SNR, which provides efficient learning mechanism. Experimental results show that the proposed method improves source-to-distortion ratio (SDR) by 6.9 dB and perceptual evaluation of speech quality (PESQ) by 0.24 in comparison to the conventional DBLSTM-based system.",

author = "Jinkyu Lee and Keulbit Kim and Turaj Shabestary and Kang, {Hong Goo}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 ; Conference date: 01-03-2017 Through 03-03-2017",

year = "2017",

month = apr,

day = "10",

doi = "10.1109/HSCMA.2017.7895558",

language = "English",

series = "2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "41--45",

booktitle = "2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings",

address = "United States",

}

Lee, J, Kim, K, Shabestary, T & Kang, HG 2017, Deep bi-directional long short-term memory based speech enhancement for wind noise reduction. in 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings., 7895558, 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 41-45, 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017, San Francisco, United States, 17/3/1. https://doi.org/10.1109/HSCMA.2017.7895558

Deep bi-directional long short-term memory based speech enhancement for wind noise reduction. / Lee, Jinkyu; Kim, Keulbit; Shabestary, Turaj et al.
2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 41-45 7895558 (2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deep bi-directional long short-term memory based speech enhancement for wind noise reduction

AU - Lee, Jinkyu

AU - Kim, Keulbit

AU - Shabestary, Turaj

AU - Kang, Hong Goo

PY - 2017/4/10

Y1 - 2017/4/10

N2 - In this paper, we propose a new recurrent neural network (RNN)-based single-channel speech enhancement framework for off-line wind noise reduction. To adequately represent highly non-stationary characteristics of wind noise, we first adopt a deep bi-directional long short-term memory (DBLSTM) structure. However, its enhanced output becomes muffled due to the spectral over-smoothing effect. To overcome this problem, we propose a new structure of DBLSTM-based speech enhancement system that internally incorporates the speech and noise power estimation processes in the spectral filtering framework. Furthermore, we propose a structure with an additional internal constraint of minimizing log a priori SNR, which provides efficient learning mechanism. Experimental results show that the proposed method improves source-to-distortion ratio (SDR) by 6.9 dB and perceptual evaluation of speech quality (PESQ) by 0.24 in comparison to the conventional DBLSTM-based system.

AB - In this paper, we propose a new recurrent neural network (RNN)-based single-channel speech enhancement framework for off-line wind noise reduction. To adequately represent highly non-stationary characteristics of wind noise, we first adopt a deep bi-directional long short-term memory (DBLSTM) structure. However, its enhanced output becomes muffled due to the spectral over-smoothing effect. To overcome this problem, we propose a new structure of DBLSTM-based speech enhancement system that internally incorporates the speech and noise power estimation processes in the spectral filtering framework. Furthermore, we propose a structure with an additional internal constraint of minimizing log a priori SNR, which provides efficient learning mechanism. Experimental results show that the proposed method improves source-to-distortion ratio (SDR) by 6.9 dB and perceptual evaluation of speech quality (PESQ) by 0.24 in comparison to the conventional DBLSTM-based system.

UR - http://www.scopus.com/inward/record.url?scp=85018737966&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018737966&partnerID=8YFLogxK

U2 - 10.1109/HSCMA.2017.7895558

DO - 10.1109/HSCMA.2017.7895558

M3 - Conference contribution

AN - SCOPUS:85018737966

T3 - 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings

SP - 41

EP - 45

BT - 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017

Y2 - 1 March 2017 through 3 March 2017

ER -

Lee J, Kim K, Shabestary T, Kang HG. Deep bi-directional long short-term memory based speech enhancement for wind noise reduction. In 2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 41-45. 7895558. (2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings). doi: 10.1109/HSCMA.2017.7895558

Deep bi-directional long short-term memory based speech enhancement for wind noise reduction

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this