Ruchao Fan
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Audio and Speech Processing×2Sound×1NLP×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.
Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs
The paper proposes SpeechKV, a method to compress speech sequences inside large language models using a learned pooling, maintaining performance and delivering decoding speedup.
Highlighted terms show continued research focus across papers
Papers
eess.AScs.SDEmpiricalRecentJul 7, 2026
Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs
Ke-Han Lu, Keqi Deng, Ruchao Fan, Rui Zhao +1 more
The paper proposes SpeechKV, a method to compress speech sequences inside large language models using a learned pooling, maintaining performance and delivering decoding speedup.
View →
cs.CLeess.ASEmpirical