Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge

Mingshuai Liu; Shubo Lv; Zihan Zhang; Runduo Han; Xiang Hao; Xianjun Xia; Li Chen; Yijian Xiao; Lei Xie

doi:10.1109/ICASSP49357.2023.10094827

Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge

Mingshuai Liu, Shubo Lv, Zihan Zhang, Runduo Han, Xiang Hao, Xianjun Xia, Li Chen, Yijian Xiao, Lei Xie

School of Computer Science

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

7 Scopus citations

Abstract

In ICASSP 2023 speech signal improvement challenge, we developed a dual-stage neural model which improves speech signal quality induced by different distortions in a stage-wise divide-and-conquer fashion. Specifically, in the first stage, the speech improvement network focuses on recovering the missing components of the spectrum, while in the second stage, our model aims to further suppress noise, reverberation, and artifacts introduced by the first-stage model. Achieving 0.446 in the final score and 0.517 in the P.835 score, our system ranks 4th in the non-real-time track.

Original language	English
Title of host publication	ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728163277
DOIs	https://doi.org/10.1109/ICASSP49357.2023.10094827
State	Published - 2023
Event	48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece Duration: 4 Jun 2023 → 10 Jun 2023

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2023-June
ISSN (Print)	1520-6149

Conference

Conference	48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Country/Territory	Greece
City	Rhodes Island
Period	4/06/23 → 10/06/23

Keywords

speech distortion
speech enhancement

Access to Document

10.1109/ICASSP49357.2023.10094827

Cite this

Liu, M., Lv, S., Zhang, Z., Han, R., Hao, X., Xia, X., Chen, L., Xiao, Y., & Xie, L. (2023). Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2023-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP49357.2023.10094827

Liu, Mingshuai ; Lv, Shubo ; Zhang, Zihan et al. / Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{4a79ce9e6c9a4428b2b79ed3973d2a53,

title = "Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge",

abstract = "In ICASSP 2023 speech signal improvement challenge, we developed a dual-stage neural model which improves speech signal quality induced by different distortions in a stage-wise divide-and-conquer fashion. Specifically, in the first stage, the speech improvement network focuses on recovering the missing components of the spectrum, while in the second stage, our model aims to further suppress noise, reverberation, and artifacts introduced by the first-stage model. Achieving 0.446 in the final score and 0.517 in the P.835 score, our system ranks 4th in the non-real-time track.",

keywords = "speech distortion, speech enhancement",

author = "Mingshuai Liu and Shubo Lv and Zihan Zhang and Runduo Han and Xiang Hao and Xianjun Xia and Li Chen and Yijian Xiao and Lei Xie",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",

year = "2023",

doi = "10.1109/ICASSP49357.2023.10094827",

language = "英语",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

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

booktitle = "ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings",

}

Liu, M, Lv, S, Zhang, Z, Han, R, Hao, X, Xia, X, Chen, L, Xiao, Y & Xie, L 2023, Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2023-June, Institute of Electrical and Electronics Engineers Inc., 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10094827

Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge. / Liu, Mingshuai; Lv, Shubo; Zhang, Zihan et al.
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2023-June).

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

TY - GEN

T1 - Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge

AU - Liu, Mingshuai

AU - Lv, Shubo

AU - Zhang, Zihan

AU - Han, Runduo

AU - Hao, Xiang

AU - Xia, Xianjun

AU - Chen, Li

AU - Xiao, Yijian

AU - Xie, Lei

PY - 2023

Y1 - 2023

N2 - In ICASSP 2023 speech signal improvement challenge, we developed a dual-stage neural model which improves speech signal quality induced by different distortions in a stage-wise divide-and-conquer fashion. Specifically, in the first stage, the speech improvement network focuses on recovering the missing components of the spectrum, while in the second stage, our model aims to further suppress noise, reverberation, and artifacts introduced by the first-stage model. Achieving 0.446 in the final score and 0.517 in the P.835 score, our system ranks 4th in the non-real-time track.

AB - In ICASSP 2023 speech signal improvement challenge, we developed a dual-stage neural model which improves speech signal quality induced by different distortions in a stage-wise divide-and-conquer fashion. Specifically, in the first stage, the speech improvement network focuses on recovering the missing components of the spectrum, while in the second stage, our model aims to further suppress noise, reverberation, and artifacts introduced by the first-stage model. Achieving 0.446 in the final score and 0.517 in the P.835 score, our system ranks 4th in the non-real-time track.

KW - speech distortion

KW - speech enhancement

UR - http://www.scopus.com/inward/record.url?scp=85177435317&partnerID=8YFLogxK

U2 - 10.1109/ICASSP49357.2023.10094827

DO - 10.1109/ICASSP49357.2023.10094827

M3 - 会议稿件

AN - SCOPUS:85177435317

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

BT - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

Y2 - 4 June 2023 through 10 June 2023

ER -

Liu M, Lv S, Zhang Z, Han R, Hao X, Xia X et al. Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP49357.2023.10094827

Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this