@article{GlockerHerygersGeorges2023, author = {Glocker, Kevin and Herygers, Aaricia and Georges, Munir}, title = {Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2306.04306}, year = {2023}, abstract = {This paper proposes Allophant, a multilingual phoneme recognizer. It requires only a phoneme inventory for crosslingual transfer to a target language, allowing for low-resource recognition. The architecture combines a compositional phone embedding approach with individually supervised phonetic attribute classifiers in a multi-task architecture. We also introduce Allophoible, an extension of the PHOIBLE database. When combined with a distance based mapping approach for grapheme-to-phoneme outputs, it allows us to train on PHOIBLE inventories directly. By training and evaluating on 34 languages, we found that the addition of multi-task learning improves the model's capability of being applied to unseen phonemes and phoneme inventories. On supervised languages we achieve phoneme error rate improvements of 11 percentage points (pp.) compared to a baseline without multi-task learning. Evaluation of zero-shot transfer on 84 languages yielded a decrease in PER of 2.63 pp. over the baseline.}, language = {en} }