An LLM-based ASR system that jointly performs overlapping-speech recognition and rare-word biasing, with a CTC-stage filter that trims large biasing lists, beats the tested baselines on LibriMix and AMI.
Existing methods include permutation invariant training [1], heuristic error assignment [2], and serialized output training (SOT) [3]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models
An LLM-based ASR system that jointly performs overlapping-speech recognition and rare-word biasing, with a CTC-stage filter that trims large biasing lists, beats the tested baselines on LibriMix and AMI.