Work hard
Work hard
Home
Talks
Publications
Contact
Light
Dark
Automatic
Audio-Visual Active Speaker Extraction for Sparsely Overlapped Multi-talker Speech
Junjie Li
,
Ruijie Tao
,
Zexu Pan
,
Meng Ge
,
Shuai Wang
,
Haizhou Li
May 2024
tse
Type
Conference paper
Publication
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Korea, 2024
Related
Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition
AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data
DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion
Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit
On the Importance of Different Frequency Bins for Speaker Verification
Cite
×