Scholarlink

In contrast to written texts and prepared speeches, conversational/spontaneous speech has a very high degree of freedom and includes a huge number of disfluencies. Detecting disfluencies using transformer-based models has advanced state-of-the-art performance. In this work, we aim to process disfluencies in the spontaneous tunisian dialect speech by generating fluent utterances from disfluent transcripts. We propose a transformer-based model by fine-tuning the pre-trained T5 language model. Using this model, we achieved an F-Measure score of 74,71% based on the evaluation data set part of DisCoTAT.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Disfluent-to-Fluent Tunisian Dialect Speech Translation with Fine-Tuning Pre-trained Language Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Emna Boughariou,
  • Younés Bahou,
  • Lamia Hadrich Belguith

摘要

In contrast to written texts and prepared speeches, conversational/spontaneous speech has a very high degree of freedom and includes a huge number of disfluencies. Detecting disfluencies using transformer-based models has advanced state-of-the-art performance. In this work, we aim to process disfluencies in the spontaneous tunisian dialect speech by generating fluent utterances from disfluent transcripts. We propose a transformer-based model by fine-tuning the pre-trained T5 language model. Using this model, we achieved an F-Measure score of 74,71% based on the evaluation data set part of DisCoTAT.