Xinyu Liang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Sound×1
Frequent co-authors
Research Timeline
2026
SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision
This paper introduces a training recipe for sentence-level and long-form streaming speech-to-speech translation using only 2k hours of paired cross-lingual data and auxiliary supervision.
Highlighted terms show continued research focus across papers
Papers
cs.SDEmpiricalRecentJul 22, 2026
SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision
Rongshen He, Xinyu Liang, Dekun Chen, Jiaqi Li +2 more
This paper introduces a training recipe for sentence-level and long-form streaming speech-to-speech translation using only 2k hours of paired cross-lingual data and auxiliary supervision.
View →