MRMI-TTS: Multi-Reference Audios and Mutual Information Driven Zero-Shot Voice Cloning

Open Webpage

Yi Ting Chen, Wanting Li, Buzhou Tang

Published: 31 May 2024, Last Modified: 05 Jan 2026ACM Transactions on Asian and Low-Resource Language Information ProcessingEveryoneRevisionsCC BY-SA 4.0
External IDs:doi:10.1145/3649501