TY - GEN
T1 - PL-EESR
T2 - 2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021
AU - Ma, Yi
AU - Lee, Kong Aik
AU - Hautamaki, Ville
AU - Li, Haizhou
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/12
Y1 - 2021/12
N2 - Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance of speaker embedding extraction. To alleviate this problem, we propose an end-to-end deep learning framework, dubbed PL-EESR, for robust speaker representation extraction. This framework is optimized based on the feedback of the speaker identification task and the high-level perceptual deviation between the raw speech signal and its noisy version. We conducted speaker verification tasks in both noisy and clean environment respectively to evaluate our system. Compared to the baseline, our method shows better performance in both clean and noisy environments, which means our method can not only enhance the speaker relative information but also avoid adding distortions.
AB - Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance of speaker embedding extraction. To alleviate this problem, we propose an end-to-end deep learning framework, dubbed PL-EESR, for robust speaker representation extraction. This framework is optimized based on the feedback of the speaker identification task and the high-level perceptual deviation between the raw speech signal and its noisy version. We conducted speaker verification tasks in both noisy and clean environment respectively to evaluate our system. Compared to the baseline, our method shows better performance in both clean and noisy environments, which means our method can not only enhance the speaker relative information but also avoid adding distortions.
KW - End-to-end training
KW - Perceptual Loss
KW - Speaker representation
KW - Speech enhancement
UR - http://www.scopus.com/inward/record.url?scp=85124782729&partnerID=8YFLogxK
U2 - 10.1109/ASRU51503.2021.9688031
DO - 10.1109/ASRU51503.2021.9688031
M3 - Conference article published in proceeding or book
AN - SCOPUS:85124782729
T3 - 2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings
SP - 106
EP - 113
BT - 2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 13 December 2021 through 17 December 2021
ER -