LipsFlow converts RGB videos to event streams, segments multi-speaker scenes with ByteTrack and TalkNet, and uses OT-CFM plus dual semantic supervision to report 22.3% WER at 240 ms latency on VSR benchmarks.
In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2024) A First Exploration of Neuromorphic OT-CFM for Multi-Speaker VSR 17
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A First Exploration of Neuromorphic OT-CFM for Multi-Speaker VSR
LipsFlow converts RGB videos to event streams, segments multi-speaker scenes with ByteTrack and TalkNet, and uses OT-CFM plus dual semantic supervision to report 22.3% WER at 240 ms latency on VSR benchmarks.