Crossmark

An audio generation model based on empirical mode decomposition and generative adversarial networks for enhancing voice quality and diversity

Published Online: 2025-11-28

Authors

Lai, Wen-Hsing https://orcid.org/0000-0003-2260-8810
Chen, Wei-Lun

Wang, Siou-Lin
Funding

Funding for this research was provided by:

NSTC (112-2221-E-992-070)
License Information

Text and Data Mining valid from 2025-11-28

Version of Record valid from 2025-11-28
More Information

Article History

Received: 13 February 2025

Accepted: 3 October 2025

First Online: 28 November 2025

Declarations

:

: The authors declare that they have no competing interests.

Document is current