Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915184486907904 |
|---|---|
| author | Medin, Lucas Block Pellegrini, Thomas Gelin, Lucile |
| author_facet | Medin, Lucas Block Pellegrini, Thomas Gelin, Lucile |
| contents | Child speech recognition is still an underdeveloped area of research due to the lack of data (especially on non-English languages) and the specific difficulties of this task. Having explored various architectures for child speech recognition in previous work, in this article we tackle recent self-supervised models. We first compare wav2vec 2.0, HuBERT and WavLM models adapted to phoneme recognition in French child speech, and continue our experiments with the best of them, WavLM base+. We then further adapt it by unfreezing its transformer blocks during fine-tuning on child speech, which greatly improves its performance and makes it significantly outperform our base model, a Transformer+CTC. Finally, we study in detail the behaviour of these two models under the real conditions of our application, and show that WavLM base+ is more robust to various reading tasks and noise levels. Index Terms: speech recognition, child speech, self-supervised learning |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04710 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning Medin, Lucas Block Pellegrini, Thomas Gelin, Lucile Sound Artificial Intelligence Audio and Speech Processing Child speech recognition is still an underdeveloped area of research due to the lack of data (especially on non-English languages) and the specific difficulties of this task. Having explored various architectures for child speech recognition in previous work, in this article we tackle recent self-supervised models. We first compare wav2vec 2.0, HuBERT and WavLM models adapted to phoneme recognition in French child speech, and continue our experiments with the best of them, WavLM base+. We then further adapt it by unfreezing its transformer blocks during fine-tuning on child speech, which greatly improves its performance and makes it significantly outperform our base model, a Transformer+CTC. Finally, we study in detail the behaviour of these two models under the real conditions of our application, and show that WavLM base+ is more robust to various reading tasks and noise levels. Index Terms: speech recognition, child speech, self-supervised learning |
| title | Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2503.04710 |