TEA-PSE: TENCENT-ETHEREAL-AUDIO-LAB PERSONALIZED SPEECH ENHANCEMENT SYSTEM FOR ICASSP 2022 DNS CHALLENGE

Yukai Ju, Wei Rao, Xiaopeng Yan, Yihui Fu, Shubo Lv, Luyao Cheng, Yannan Wang, Lei Xie, Shidong Shang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

38 Scopus citations

Abstract

This paper describes Tencent Ethereal Audio Lab - Northwestern Polytechnical University personalized speech enhancement (TEA-PSE) system submitted to track 2 of the ICASSP 2022 Deep Noise Suppression (DNS) challenge. Our system specifically combines the dual-stage network which is a superior real-time speech enhancement framework with the ECAPA-TDNN speaker embedding network which achieves state-of-the-art performance in speaker verification. The dual-stage network aims to decouple the primal speech enhancement problem into multiple easier sub-problems. Specifically, in stage 1, only the magnitude of the target speech is estimated, which is incorporated with the noisy phase to obtain a coarse complex spectrum estimation. To facilitate the formal estimation, in stage 2, an auxiliary network serves as a post-processing module, where residual noise and interfering speech are further suppressed and the phase information is effectively modified. With the asymmetric loss function to penalize over-suppression, more target speech is preserved, which is helpful for both speech recognition performance and subjective sense of hearing. Our system reaches 3.97 in overall audio quality (OVRL) MOS and 0.69 in word accuracy (WAcc) on the blind test set of the challenge, which outperforms the DNS baseline by 0.57 OVRL and ranks 1st in track 2.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6367-6371
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 - Hybrid, Singapore
Duration: 22 May 202227 May 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityHybrid
Period22/05/2227/05/22

Keywords

  • ECAPA-TDNN
  • Personalized speech enhancement
  • real-time
  • two-stage network

Fingerprint

Dive into the research topics of 'TEA-PSE: TENCENT-ETHEREAL-AUDIO-LAB PERSONALIZED SPEECH ENHANCEMENT SYSTEM FOR ICASSP 2022 DNS CHALLENGE'. Together they form a unique fingerprint.

Cite this