CASA-Net: Cross-attention and Self-attention for End-to-End Audio-visual Speaker Diarization

Date:2024-06-16 clicks:

Journal:2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Co-author:HQY

Indexed by:Conference article (CA)

Page Number:102-106

Translation or Not:no

Pre One:Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge Next One:Towards A Unified Conformer Structure: from ASR to ASV Task