Jie Jin1,★, Ziyin Ma2, Min Yin3, Jinyu Chen4, Haigang Song1, Zhikun Pang1, Xiaowen Zhang1

≤ 0.25 s≤ 0.5 s≤ 2 s
12.5 + 860016.9311
017.320.433.5335
1.5k12.5 + 87008.4251
1.5k09.712.018.4227
 

@inproceedings{jin2027duplexjev,
  title     = {Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen {LLM} Hear Beyond the Transcript},
  author    = {Jin, Jie and Ma, Ziyin and Yin, Min and Chen, Jinyu and Song, Haigang and Pang, Zhikun and Zhang, Xiaowen},
  booktitle = {Submitted to IEEE ICASSP},
  year      = {2027}
}