SyncAI.news, a Varaisys broadcasting
Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech
NB

Nicola Barbaro, Cristina Gena, Francesco Petriglia, Andrea Meirone, Alessandro Mazzei, Arianna Viotti

· 1 min read

ResearcharXiv cs.LG

Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech

arXiv:2609.33060v1 Announce Type: new Abstract: 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.

Original source

This story was published by arXiv cs.LG and written by Nicola Barbaro, Cristina Gena, Francesco Petriglia, Andrea Meirone, Alessandro Mazzei, Arianna Viotti. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News