Adding language-specific prompts and bi-directional conversational context to a speech LLM cuts validation error by 18% relative and edges out a model trained on four times more data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR
Adding language-specific prompts and bi-directional conversational context to a speech LLM cuts validation error by 18% relative and edges out a model trained on four times more data.