Author

Yusuke Fujita

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Mar 2026

Streaming Translation and Transcription Through Speech-to-Text Causal Alignment

This work proposes Hikari, a policy-free, end-to-end model for simultaneous speech-to-text translation and streaming transcription, and presents a supervised fine-tuning strategy that trains the model to recover from delays, significantly improving the quality-latency trade-off.

Roman Koshkin, Haesung Jeon, Lian-Bo Liu et al. · arXiv.org · 2 citations