Evaluation of Automatic Speech Recognition Using Generative Large Language Models

• URL: http://arxiv.org/abs/2604.21928v2
• Date: Wed, 29 Apr 2026 07:43:20 GMT
• Title: Evaluation of Automatic Speech Recognition Using Generative Large Language Models
• Abstract summary: This paper evaluates relevance of Large Language Models (LLMs) for automatic speech recognition evaluation.<n>The best LLMs achieve 92--94% agreement with human annotators for hypothesis selection.<n> Embeddings from decoder-based LLMs show performance comparable to encoder models.
• Score: 13.666045109234107
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study [13.666045109234107]
  We analyze BERTScore and SemDist across different Large Language Models (LLMs) for Automatic Speech Recognition (ASR) evaluation.<n>Our results show that encoder-based metrics remain highly competitive, while generative LLMs perform strongly in hypothesis comparison and improve the interpretability of ASR evaluation.
  arXiv  Detail & Related papers  (2026-08-26T09:36:48Z)
• A-VERT: Agnostic Verification with Embedding Ranking Targets [0.0]
  A structure-free evaluation method is presented.<n>The method makes use of semantic embedding distances to match target candidates with arbitrary LM-generated text.<n>The results show a regression score of 0.97 and an accuracy of 96% against human annotators.
  arXiv  Detail & Related papers  (2025-10-01T21:26:03Z)
• Criteria-Based LLM Relevance Judgments [5.478764356647438]
  Large Language Models (LLMs) provide a scalable solution by generating relevance labels directly through prompting.<n>We propose the Multi-Criteria framework for LLM-based relevance judgments, decomposing the notion of relevance into multiple criteria.<n>Our results demonstrate that Multi-Criteria judgments enhance the system ranking/leaderboard performance.
  arXiv  Detail & Related papers  (2025-07-13T04:21:21Z)
• AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models [86.83875864328984]
  We propose an automated method for synthesizing open-ended logic puzzles, and use it to develop a bilingual benchmark, AutoLogi.<n>Our approach features program-based verification and controllable difficulty levels, enabling more reliable evaluation that better distinguishes models' reasoning abilities.
  arXiv  Detail & Related papers  (2025-02-24T07:02:31Z)
• Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback [50.84142264245052]
  This work introduces the Align-SLM framework to enhance the semantic understanding of textless Spoken Language Models (SLMs)<n>Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO)<n>We evaluate the framework using ZeroSpeech 2021 benchmarks for lexical and syntactic modeling, the spoken version of the StoryCloze dataset for semantic coherence, and other speech generation metrics, including the GPT4-o score and human evaluation.
  arXiv  Detail & Related papers  (2024-11-04T06:07:53Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• ANLS* -- A Universal Document Processing Metric for Generative Large Language Models [40.94659575657584]
  This paper introduces a new metric for evaluating generative models called ANLS*.<n>The ANLS* metric extends existing ANLS metrics as a drop-in-replacement and is still compatible with previously reported ANLS scores.<n>We also benchmark a novel approach to generate prompts for documents, called SFT, against other prompting techniques such as LATIN.
  arXiv  Detail & Related papers  (2024-02-06T09:50:08Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• Towards Computationally Verifiable Semantic Grounding for Language Models [18.887697890538455]
  The paper conceptualizes the LM as a conditional model generating text given a desired semantic message formalized as a set of entity-relationship triples. It embeds the LM in an auto-encoder by feeding its output to a semantic fluency whose output is in the same representation domain as the input message. We show that our proposed approaches significantly improve on the greedy search baseline.
  arXiv  Detail & Related papers  (2022-11-16T17:35:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.