Language identification greatly impacts the success of downstream tasks such as automatic speech recognition. Recently, self-supervised speech representations learned by wav2vec 2.0 have been shown to be very effective for a range of speech tasks. We extend previous self-supervised work on language identification by experimenting with pre-trained models which were learned on real-world unconstrained speech in multiple languages and not just on English. We show that models pre-trained on many languages perform better and enable language identification systems that require very little labeled data to perform well. Results on a 26 languages setup show that with only 10 minutes of labeled data per language, a cross-lingually pre-trained model can achieve over 89.2% accuracy.
@article{arxiv.2107.04082,
title = {Improved Language Identification Through Cross-Lingual Self-Supervised Learning},
author = {Andros Tjandra and Diptanu Gon Choudhury and Frank Zhang and Kritika Singh and Alexis Conneau and Alexei Baevski and Assaf Sela and Yatharth Saraf and Michael Auli},
journal= {arXiv preprint arXiv:2107.04082},
year = {2021}
}