AVFSNet combines a Branchformer audio encoder, parallel audio-visual separation branches, and a mask-based counter to separate flexible numbers of speakers from audio-visual mixtures.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AVFSNet: Audio-Visual Speech Separation for Flexible Number of Speakers with Multi-Scale and Multi-Task Learning
AVFSNet combines a Branchformer audio encoder, parallel audio-visual separation branches, and a mask-based counter to separate flexible numbers of speakers from audio-visual mixtures.