Decoder-based LLMs reach 92-94% agreement with humans when choosing correct ASR hypotheses, beating WER at 63% and outperforming encoder-based semantic metrics.
Interspeech , year=
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
-
Evaluation of Automatic Speech Recognition Using Generative Large Language Models
Decoder-based LLMs reach 92-94% agreement with humans when choosing correct ASR hypotheses, beating WER at 63% and outperforming encoder-based semantic metrics.