TY - GEN
T1 - TEA-PSE
T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
AU - Ju, Yukai
AU - Rao, Wei
AU - Yan, Xiaopeng
AU - Fu, Yihui
AU - Lv, Shubo
AU - Cheng, Luyao
AU - Wang, Yannan
AU - Xie, Lei
AU - Shang, Shidong
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - ECAPA-TDNN
KW - Personalized speech enhancement
KW - real-time
KW - two-stage network
UR - http://www.scopus.com/inward/record.url?scp=85134054148&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9747765
DO - 10.1109/ICASSP43922.2022.9747765
M3 - 会议稿件
AN - SCOPUS:85134054148
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 6367
EP - 6371
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 22 May 2022 through 27 May 2022
ER -