IMPROVING MULTI-SPEAKER ASR WITH OVERLAP-AWARE ENCODING AND MONOTONIC ATTENTION

Date:2024-06-25 clicks:

Journal:ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Co-author:HQY

Indexed by:Conference article (CA)

Page Number:12416-12420

Translation or Not:no

Pre One:LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation Next One:MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis