Metraipolis › archive › dc_722298cd3ece

Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech — arXiv:2609.33060

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33060
License (as archived)
CC0-1.0
Archived
2026-10-07T22:37:08.068Z
SHA-256 of the archived text
7a40bb087b5ef10f9955c6d67ef40a0aa648ebcae1a87c00e739eb7080d1d55e
Stable URL of this page
https://metraipolis.com/documento/dc_722298cd3ece

How to cite

Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech — arXiv:2609.33060 — arXiv (en), https://arxiv.org/abs/2609.33060 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_722298cd3ece (Metraipolis archive dc_722298cd3ece, sha256 7a40bb087b5ef10f9955c6d67ef40a0aa648ebcae1a87c00e739eb7080d1d55e)
BibTeX
@misc{dc722298cd3ece,
  title = {Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech — arXiv:2609.33060},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33060},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_722298cd3ece; sha256 7a40bb087b5ef10f9955c6d67ef40a0aa648ebcae1a87c00e739eb7080d1d55e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33060. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Speech therapists often face difficulties diagnosing impairments due to the lack of efficient tools for transcribing speech into the International Phonetic Alphabet (IPA). This work addresses this challenge with Broca, a Conformer-based deep learning system pretrained on 8 days of adult speech and fine-tuned on a 165-minute dataset of Italian child speech collected through a range of standardized diagnostic tests for children aged 3.5-6.5. Broca was optimized to handle phonetic variability in children's speech, including tone, accent, and speech errors, and achieved a state-of-the-art weighted Phoneme Error Rate of 13.36% on Italian speech. Remarkably, this performance was obtained using less than three hours of child-specific data, underscoring the model's efficiency and robustness in low-resource clinical settings. This work demonstrates that accurate, vocabulary-independent speech-to-IPA transcription can be achieved with minimal data, paving the way for more accessible, data-efficient tools to support speech assessment and diagnosis.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.33060 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:27.853Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).