MFCCA:Multi-Frame Cross-Channel Attention for Multi-Speaker ASR in Multi-Party Meeting Scenario.
Fan YuShiliang ZhangPengcheng GuoYuhao LiangZhihao DuYuxiao LinLei XiePublished in: SLT (2022)
Keyphrases
- multi party
- multi frame
- cross channel
- automatic speech recognition
- speech recognition
- motion estimation
- privacy preserving
- point correspondences
- image sequences
- super resolution
- free riding
- optical flow
- motion analysis
- computationally efficient
- optic flow
- filtering algorithm
- description language
- speech signal
- mental states
- hidden markov models
- service delivery
- motion model
- audio visual
- multiresolution
- multi agent
- focus of attention
- multiscale
- face recognition