Phoné: An Initiative to Develop a Dataset for the Automatic Recognition of Spoken Italian
Oral Archives Journal · 2025
DOI: 10.36253/oar-3340 ↗Kurz gefasst
Fachartikel in der Zeitschrift Oral Archives Journal, 2025. Verfasst von Gianpaolo Coro und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large Language Models (LLM) have revolutionised natural language processing and its applications. However, high-performance LLMs require copious data and computing resources for their development and are rarely public. This also concerns Large Acoustic Models (LAM) for processing spoken language. The Phoné initiative seeks to build an open Italian speech dataset to advance Automatic Speech Recognition (ASR) systems and support public research. Spearheaded by institutions in Naples, Pisa, and Bolzano, the project gathers diverse Italian audio sources and applies advanced ASR architectures, including supervised and self-supervised models. This paper details Phoné’s dataset creation, ASR model evaluation, and ethical considerations, aiming to democratise access to Italian-language resources and foster innovation in ASR technologies.
Zitieren
APA
Coro, G., Cutugno, F., Schettino, L., Tanda, E., Vietti, A., & Vitale, V. N. (2025). Phoné: An Initiative to Develop a Dataset for the Automatic Recognition of Spoken Italian. Oral Archives Journal. https://doi.org/10.36253/oar-3340
Vancouver
Coro G, Cutugno F, Schettino L, Tanda E, Vietti A, Vitale VN. Phoné: An Initiative to Develop a Dataset for the Automatic Recognition of Spoken Italian. Oral Archives Journal. 2025. doi:10.36253/oar-3340
BibTeX
@article{Coro2025,
author = {Coro, Gianpaolo and Cutugno, Francesco and Schettino, Loredana and Tanda, Emilia and Vietti, Alessandro and Vitale, Vincenzo Norman},
title = {Phoné: An Initiative to Develop a Dataset for the Automatic Recognition of Spoken Italian},
journal = {Oral Archives Journal},
year = {2025},
doi = {10.36253/oar-3340}
}
EUVIMED