Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bañeras-Roux, Thibault, Kumar, Shashi, Khalil, Driss, Burdisso, Sergio, Motlicek, Petr, Liu, Shiran, Rouvier, Mickael, Wottawa, Jane, Dufour, Richard
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.21928
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916063443156992
author Bañeras-Roux, Thibault
Kumar, Shashi
Khalil, Driss
Burdisso, Sergio
Motlicek, Petr
Liu, Shiran
Rouvier, Mickael
Wottawa, Jane
Dufour, Richard
author_facet Bañeras-Roux, Thibault
Kumar, Shashi
Khalil, Driss
Burdisso, Sergio
Motlicek, Petr
Liu, Shiran
Rouvier, Mickael
Wottawa, Jane
Dufour, Richard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21928
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evaluation of Automatic Speech Recognition Using Generative Large Language Models
Bañeras-Roux, Thibault
Kumar, Shashi
Khalil, Driss
Burdisso, Sergio
Motlicek, Petr
Liu, Shiran
Rouvier, Mickael
Wottawa, Jane
Dufour, Richard
Computation and Language
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.
title Evaluation of Automatic Speech Recognition Using Generative Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2604.21928