TFD-MelGAN: personalized voiceprint feature speech synthesis based on multi-domain signal processing

Daigang Chen; Hua Jiang; Chengxi Pu; Shaowen Yao

doi:10.1117/12.2645688

23 August 2022 TFD-MelGAN: personalized voiceprint feature speech synthesis based on multi-domain signal processing

Daigang Chen, Hua Jiang, Chengxi Pu, Shaowen Yao

Proceedings Volume 12305, International Symposium on Artificial Intelligence Control and Application Technology (AICAT 2022); 1230509 (2022) https://doi.org/10.1117/12.2645688
Event: International Symposium on Artificial Intelligence Control and Application Technology (AICAT 2022), 2022, Hangzhou, China

Abstract

In recent years, with the popularity of deep learning, speech synthesis technology has developed rapidly and achieved many good achievements. Among them, the technology of speech synthesis for personalized voiceprint features has also become a research focus. In the existing work, the model for personalized voiceprint feature speech synthesis based on GANs has achieved certain results. The model successfully synthesized speech with personalized voiceprint features in a non-autoregressive way, but the audio quality of the synthesized speech and efficiency was low, and the model training time was long. In this paper, we improve the model through techniques such as multi-domain signal processing. Specifically, we reduce a lot of training time by optimizing several parameters of the model. In addition, the architecture of the model has been improved to a certain extent, which effectively improves the MOS score of synthesized speech.

Citation Download Citation

Daigang Chen, Hua Jiang, Chengxi Pu, and Shaowen Yao "TFD-MelGAN: personalized voiceprint feature speech synthesis based on multi-domain signal processing", Proc. SPIE 12305, International Symposium on Artificial Intelligence Control and Application Technology (AICAT 2022), 1230509 (23 August 2022); https://doi.org/10.1117/12.2645688

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available