Layer selection plus RIR augmentation on synthetic speech matches full real-data ASR performance using 25% real speech in SLAM-ASR.
Distilling conversations: Abstract compression of conversational audio context for llm-based asr,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
Layer selection plus RIR augmentation on synthetic speech matches full real-data ASR performance using 25% real speech in SLAM-ASR.