Paper Detail

Evaluation of Automatic Speech Recognition Using Generative Large Language Models

Thibault Bañeras-Roux, Shashi Kumar, Driss Khalil, Sergio Burdisso, Petr Motlicek, Shiran Liu, Mickael Rouvier, Jane Wottawa, Richard Dufour

arxiv Score 7.3

Published 2026-04-23 · First seen 2026-04-24

General AI

Abstract

Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large Language Models (LLMs) remain underexplored for this task. This paper evaluates their relevance through three approaches: (1) selecting the best hypothesis between two candidates, (2) computing semantic distance using generative embeddings, and (3) qualitative classification of errors. On the HATS dataset, the best LLMs achieve 92--94\% agreement with human annotators for hypothesis selection, compared to 63\% for WER, also outperforming semantic metrics. Embeddings from decoder-based LLMs show performance comparable to encoder models. Finally, LLMs offer a promising direction for interpretable and semantic ASR evaluation.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{baerasroux2026evaluation,
  title = {Evaluation of Automatic Speech Recognition Using Generative Large Language Models},
  author = {Thibault Bañeras-Roux and Shashi Kumar and Driss Khalil and Sergio Burdisso and Petr Motlicek and Shiran Liu and Mickael Rouvier and Jane Wottawa and Richard Dufour},
  year = {2026},
  abstract = {Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large Language Models (LLMs) remain underexplored for this task. This paper evaluates their relevance through three approaches: (1) selecting the best hypothesis between two candidates, (2) computing semantic distance using generative embeddings, and (3) qualitative class},
  url = {https://arxiv.org/abs/2604.21928},
  keywords = {cs.CL},
  eprint = {2604.21928},
  archiveprefix = {arXiv},
}

Metadata

{}