A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language

• URL: http://arxiv.org/abs/2605.03696v1
• Date: Tue, 05 May 2026 12:39:40 GMT
• Title: A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language
• Abstract summary: This paper investigates the impact of subword tokenization algorithms and self-supervised learning models from different linguistic and acoustic perspectives.<n>It shows that these algorithms fail to adequately describe the downstream application of automatic transcripts.
• Score: 12.151730134044696
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The performance of end-to-end automatic speech recognition (ASR) systems enables their increasing integration into numerous applications. While there are various benefits to such speech-to-text systems, the choice of hyperparameters and models plays a crucial role in their performance. Typically, these choices are determined by considering only the character (CER) and/or word error rate (WER) metrics. However, it has been shown in several studies that these metrics are largely incomplete and fail to adequately describe the downstream application of automatic transcripts. In this paper, we conduct a qualitative study on the French language that investigates the impact of subword tokenization algorithms and self-supervised learning models from different linguistic and acoustic perspectives, using a comprehensive set of evaluation metrics.

Related papers

• Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning [57.22705949022221]
  RoleJudge is an evaluation framework that leverages audio large language models to assess the alignment between speech and character.<n>We introduce RoleChat, the first voice role-playing evaluation dataset enriched with chain-of-thought reasoning annotations.
  arXiv  Detail & Related papers  (2026-04-15T12:39:03Z)
• I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations [9.275967682881944]
  This paper introduces a comprehensive benchmark for evaluating how Large Language Models respond to linguistic shibboleths.<n>We demonstrate how LLMs systematically penalize certain linguistic patterns, particularly hedging language, despite equivalent content quality.<n>We validate our approach along multiple linguistic dimensions, showing that hedged responses receive 25.6% lower ratings on average.
  arXiv  Detail & Related papers  (2025-08-06T23:51:03Z)
• SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models [60.72029578488467]
  SpeechR is a unified benchmark for evaluating reasoning over speech in large audio-language models.<n>It evaluates models along three key dimensions: factual retrieval, procedural inference, and normative judgment.<n> Evaluations on eleven state-of-the-art LALMs reveal that high transcription accuracy does not translate into strong reasoning capabilities.
  arXiv  Detail & Related papers  (2025-08-04T03:28:04Z)
• Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling [50.62091603179394]
  Whisper, one of the most advanced ASR models, handles 99 languages effectively.<n>However, Whisper struggles with unseen languages, those not included in its pre-training.<n>We propose methods that exploit these relationships to enhance ASR performance on unseen languages.
  arXiv  Detail & Related papers  (2024-12-21T04:05:43Z)
• Spoken Grammar Assessment Using LLM [10.761744330206065]
  Spoken language assessment (SLA) systems analyse the pronunciation and oral fluency of a speaker by analysing the read and spontaneous spoken utterances respectively. Most WLA systems present a set of sentences from a curated finite-size database of sentences thereby making it possible to anticipate the test questions and train oneself. We propose a novel end-to-end SLA system to assess language grammar from spoken utterances thus making WLA systems redundant.
  arXiv  Detail & Related papers  (2024-10-02T14:15:13Z)
• STAB: Speech Tokenizer Assessment Benchmark [57.45234921100835]
  Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text. We present STAB (Speech Tokenizer Assessment Benchmark), a systematic evaluation framework designed to assess speech tokenizers comprehensively. We evaluate the STAB metrics and correlate this with downstream task performance across a range of speech tasks and tokenizer choices.
  arXiv  Detail & Related papers  (2024-09-04T02:20:59Z)
• Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation [23.757896930482342]
  This work explores the selection process through a study of downstream tasks. Units that perform well in resynthesis performance do not necessarily correlate with those that enhance translation efficacy.
  arXiv  Detail & Related papers  (2024-07-08T08:53:26Z)
• Investigating model performance in language identification: beyond simple error statistics [28.128924654154087]
  Language development experts need tools that can automatically identify languages from fluent, conversational speech. We investigate how well a number of language identification systems perform on individual recordings and speech units with different linguistic properties.
  arXiv  Detail & Related papers  (2023-05-30T10:32:53Z)
• Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching [41.88097793717185]
  Code-Switching (CS) is a common linguistic phenomenon in multilingual communities. This paper presents our investigations on end-to-end speech recognition for Mandarin-English CS speech.
  arXiv  Detail & Related papers  (2021-12-19T17:31:15Z)
• Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring [60.55025339250815]
  We propose a novel deep learning technique for non-native ASS, called speaker-conditioned hierarchical modeling. We take advantage of the fact that oral proficiency tests rate multiple responses for a candidate. In our technique, we take advantage of the fact that oral proficiency tests rate multiple responses for a candidate. We extract context from these responses and feed them as additional speaker-specific context to our network to score a particular response.
  arXiv  Detail & Related papers  (2021-08-30T07:00:28Z)
• Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale [52.663117551150954]
  A few popular metrics remain as the de facto metrics to evaluate tasks such as image captioning and machine translation. This is partly due to ease of use, and partly because researchers expect to see them and know how to interpret them. In this paper, we urge the community for more careful consideration of how they automatically evaluate their models.
  arXiv  Detail & Related papers  (2020-10-26T13:57:20Z)

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.