TY - GEN
T1 - Speech Enhancement-assisted Voice Conversion in Noisy Environments
AU - Chan, Yun Ju
AU - Peng, Chiang Jen
AU - Wang, Syu Siang
AU - Wang, Hsin Min
AU - Tsao, Yu
AU - Chi, Tai Shih
N1 - Publisher Copyright:
© 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).
PY - 2022
Y1 - 2022
N2 - Numerous voice conversion (VC) techniques have been proposed for the conversion of voices among different speakers. Although good quality of the converted speech can be observed when VC is applied in a clean environment, the quality degrades drastically when the system is run in noisy conditions. In order to address this issue, we propose a novel speech enhancement (SE)-assisted VC system that utilizes the SE techniques for signal pre-processing, where the VC and SE components are optimized in an joint training strategy with the aim to provide high-quality converted speech signals. We adopt a popular model, StarGAN, as the VC component and thus call the combined system as EStarGAN. We test the proposed EStarGAN system using a Mandarin speech corpus. The experimental results first verified the effectiveness of joint training strategy used in EStarGAN. Moreover, EStarGAN demonstrated performance robustness in various unseen noisy environments. The subjective listening test results further showed that EStarGAN can improve the sound quality of speech signals converted from noise-corrupted source utterances.
AB - Numerous voice conversion (VC) techniques have been proposed for the conversion of voices among different speakers. Although good quality of the converted speech can be observed when VC is applied in a clean environment, the quality degrades drastically when the system is run in noisy conditions. In order to address this issue, we propose a novel speech enhancement (SE)-assisted VC system that utilizes the SE techniques for signal pre-processing, where the VC and SE components are optimized in an joint training strategy with the aim to provide high-quality converted speech signals. We adopt a popular model, StarGAN, as the VC component and thus call the combined system as EStarGAN. We test the proposed EStarGAN system using a Mandarin speech corpus. The experimental results first verified the effectiveness of joint training strategy used in EStarGAN. Moreover, EStarGAN demonstrated performance robustness in various unseen noisy environments. The subjective listening test results further showed that EStarGAN can improve the sound quality of speech signals converted from noise-corrupted source utterances.
UR - http://www.scopus.com/inward/record.url?scp=85146278016&partnerID=8YFLogxK
U2 - 10.23919/APSIPAASC55919.2022.9979851
DO - 10.23919/APSIPAASC55919.2022.9979851
M3 - Conference contribution
AN - SCOPUS:85146278016
T3 - Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
SP - 1533
EP - 1538
BT - Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
Y2 - 7 November 2022 through 10 November 2022
ER -