@inproceedings{GlockerHerygersGeorges2023, author = {Glocker, Kevin and Herygers, Aaricia and Georges, Munir}, title = {Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes}, booktitle = {INTERSPEECH 2023}, publisher = {ISCA}, address = {Baixas}, doi = {https://doi.org/10.21437/Interspeech.2023-772}, pages = {2258 -- 2262}, year = {2023}, language = {en} } @unpublished{GlockerHerygersGeorges2023, author = {Glocker, Kevin and Herygers, Aaricia and Georges, Munir}, title = {Allophant: Cross-lingual Phoneme Recognition with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} } @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} } @inbook{GlockerGeorges2023, author = {Glocker, Kevin and Georges, Munir}, title = {Hierarchical Multi-task Learning with Articulatory Attributes for Cross-Lingual Phoneme Recognition}, booktitle = {Practical Solutions for Diverse Real-World NLP Applications}, editor = {Abbas, Mourad}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-44259-9}, doi = {https://doi.org/10.1007/978-3-031-44260-5_4}, pages = {59 -- 75}, year = {2023}, language = {en} } @inproceedings{RanzenbergerBockletFreisingeretal.2024, author = {Ranzenberger, Thomas and Bocklet, Tobias and Freisinger, Steffen and Georges, Munir and Glocker, Kevin and Herygers, Aaricia and Riedhammer, Korbinian and Schneider, Fabian and Simic, Christopher and Zakaria, Khabbab}, title = {Extending HAnS: Large Language Models for Question Answering, Summarization, and Topic Segmentation in an ML-based Learning Experience Platform}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDPress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {https://doi.org/10.35096/othr/pub-7103}, pages = {219 -- 224}, year = {2024}, language = {en} } @inproceedings{RanzenbergerBockletFreisingeretal.2023, author = {Ranzenberger, Thomas and Bocklet, Tobias and Freisinger, Steffen and Frischholz, Lia and Georges, Munir and Glocker, Kevin and Herygers, Aaricia and Peinl, Ren{\´e} and Riedhammer, Korbinian and Schneider, Fabian and Simic, Christopher and Zakaria, Khabbab}, title = {The Hochschul-Assistenz-System HAnS: An ML-Based Learning Experience Platform}, booktitle = {Elektronische Sprachsignalverarbeitung 2023: Tagungsband der 34. Konferenz M{\"u}nchen, 1.-3. M{\"a}rz 2023}, editor = {Draxler, Christoph}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-303-4}, url = {https://www.essv.de/paper.php?id=1188}, pages = {168 -- 169}, year = {2023}, language = {en} }