@inproceedings{GlockerGeorges2022, author = {Glocker, Kevin and Georges, Munir}, title = {Hierarchical Multi-Task Transformers for Crosslingual Low Resource Phoneme Recognition}, booktitle = {Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022)}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg}, isbn = {978-1-959429-36-4}, url = {https://aclanthology.org/2022.icnlsp-1.21}, pages = {187 -- 192}, year = {2022}, abstract = {This paper proposes a method for multilingual phoneme recognition in unseen, low resource languages. We propose a novel hierarchical multi-task classifier built on a hybrid convolution-transformer acoustic architecture where articulatory attribute and phoneme classifiers are optimized jointly. The model was evaluated on a subset of 24 languages from the Mozilla Common Voice corpus. We found that when using regular multi-task learning, negative transfer effects occurred between attribute and phoneme classifiers. They were reduced by the hierarchical architecture. When evaluating zero-shot crosslingual transfer on a data set with 95 languages, our hierarchical multi-task classifier achieves an absolute PER improvement of 2.78\% compared to a phoneme-only baseline.}, language = {en} }