Tiny-Align aligns ASR audio features with an LLM's text-embedding space via a trained projector, claiming 50x faster convergence and improved ROUGE scores for edge ASR-LLM personalization.
Combating partial perception deficit in autonomous driving with multimodal llm commonsense
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
Tiny-Align aligns ASR audio features with an LLM's text-embedding space via a trained projector, claiming 50x faster convergence and improved ROUGE scores for edge ASR-LLM personalization.