Faetar Low-Resource ASR Challenge 2025: A New Initiative for Speech Recognition Research

Join the Faetar Low-Resource ASR Challenge 2025 to address common issues in archival collections of speech data and contribute to the development of speech recognition technology for endangered languages.

We are excited to announce the opening of the Faetar Low-Resource ASR Challenge 2025. This competition aims to address common issues in archival collections of speech data, such as noisy recordings, lack of standard orthography, and limited transcribed data. The challenge utilizes the Faetar ASR Benchmark Corpus, which represents the majority of all archived speech recordings of Faetar, a variety of the Franco-Provençal language with less than 1000 speakers worldwide.

The challenge proposes four tracks, including a constrained ASR track and three thematic tracks focusing on pre-trained models, unlabelled data, and dirty data. Participants can register and obtain data and the dev kit by visiting the challenge website.

Tags: Faetar Low-Resource ASR Challenge 2025, speech recognition, archival collections, Franco-Provençal language, ASR benchmark corpus, noisy recordings, transcriber inconsistencies, low-resource ASR