Haoning Xu
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
A novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means is proposed.
A novel confidence score guided incremental and speaker adaptive pseudo-labeling approach is proposed for semi-supervised elderly speech recognition.
A novel approach for zero-shot, real-time speaker adaptation for elderly speech recognition.
The paper presents OmniVChat-Studio, a multi-agent data engine for synthesizing audio-visual dialogues, and OmniVChat-RL, a reinforcement learning reward design for evaluating omni models.
Papers
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
Haolin He, Yunfei Chu, Qi Chen, Wen Huang +14 more
The paper presents OmniVChat-Studio, a multi-agent data engine for synthesizing audio-visual dialogues, and OmniVChat-RL, a reinforcement learning reward design for evaluating omni models.