Common-word acoustic cues and bias-word position prediction in speech LLMs cut rare-word transcription errors by 16.3% versus baselines, including out-of-domain cases.
BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Contextual Biasing for ASR in Speech LLM with Common Word Cues and Bias Word Position Prediction
Common-word acoustic cues and bias-word position prediction in speech LLMs cut rare-word transcription errors by 16.3% versus baselines, including out-of-domain cases.