Ali Zare
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1Audio and Speech Processing×1
Frequent co-authors
Research Timeline
2026
Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving
This paper proposes Joint Speech-Text Interleaved Pretraining (JSTIP) for speech recognition, which constructs interleaved speech-text sequences and achieves consistent entity accuracy improvement.
Highlighted terms show continued research focus across papers
Papers
cs.CLeess.ASEmpiricalRecentJul 2, 2026
Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving
Ruchao Fan, Yiming Wang, Rui Zhao, Liliang Ren +9 more
This paper proposes Joint Speech-Text Interleaved Pretraining (JSTIP) for speech recognition, which constructs interleaved speech-text sequences and achieves consistent entity accuracy improvement.
View →