TY - CHAP A1 - Glocker, Kevin A1 - Herygers, Aaricia A1 - Georges, Munir T1 - Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes T2 - INTERSPEECH 2023 UR - https://doi.org/10.21437/Interspeech.2023-772 KW - speech recognition KW - cross-lingual KW - zero-shot KW - phoneme recognition Y1 - 2023 UR - https://doi.org/10.21437/Interspeech.2023-772 N1 - „Der Nachweis einer Preprint-Version dieser Veröffentlichung ist ebenfalls in diesem Repositorium verzeichnet, s. https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/3730" SP - 2258 EP - 2262 PB - ISCA CY - Baixas ER - TY - INPR A1 - Glocker, Kevin A1 - Herygers, Aaricia A1 - Georges, Munir T1 - Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes N2 - 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. UR - https://doi.org/10.48550/arXiv.2306.04306 KW - speech recognition KW - cross-lingual KW - zero-shot KW - phoneme recognition Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2306.04306 N1 - „Die veröffentlichte Version dieses Preprints ist ebenfalls in diesem Repositorium verzeichnet, s.https://opus4.kobv.de/opus4-haw/admin/document/edit/id/3923" PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Glocker, Kevin A1 - Georges, Munir T1 - Hierarchical Multi-Task Transformers for Crosslingual Low Resource Phoneme Recognition T2 - Proceedings of the 5th International Conference on Natural Language and Speech Processing (ICNLSP 2022) N2 - 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. KW - speech recognition KW - multilingual KW - zero-shot KW - multi-task learning Y1 - 2022 UR - https://aclanthology.org/2022.icnlsp-1.21 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-30544 SN - 978-1-959429-36-4 SP - 187 EP - 192 PB - Association for Computational Linguistics CY - Stroudsburg ER - TY - CHAP A1 - Glocker, Kevin A1 - Georges, Munir ED - Abbas, Mourad T1 - Hierarchical Multi-task Learning with Articulatory Attributes for Cross-Lingual Phoneme Recognition T2 - Practical Solutions for Diverse Real-World NLP Applications UR - https://doi.org/10.1007/978-3-031-44260-5_4 Y1 - 2023 UR - https://doi.org/10.1007/978-3-031-44260-5_4 SN - 978-3-031-44259-9 SN - 978-3-031-44260-5 SP - 59 EP - 75 PB - Springer CY - Cham ER - TY - CHAP A1 - Ranzenberger, Thomas A1 - Bocklet, Tobias A1 - Freisinger, Steffen A1 - Georges, Munir A1 - Glocker, Kevin A1 - Herygers, Aaricia A1 - Riedhammer, Korbinian A1 - Schneider, Fabian A1 - Simic, Christopher A1 - Zakaria, Khabbab ED - Baumann, Timo T1 - Extending HAnS: Large Language Models for Question Answering, Summarization, and Topic Segmentation in an ML-based Learning Experience Platform T2 - Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024 UR - https://doi.org/10.35096/othr/pub-7103 KW - hans KW - learning experience platform KW - speech processing KW - natural language processing KW - large language models Y1 - 2024 UR - https://doi.org/10.35096/othr/pub-7103 SN - 978-3-95908-325-6 SP - 219 EP - 224 PB - TUDPress CY - Dresden ER - TY - CHAP A1 - Ranzenberger, Thomas A1 - Bocklet, Tobias A1 - Freisinger, Steffen A1 - Frischholz, Lia A1 - Georges, Munir A1 - Glocker, Kevin A1 - Herygers, Aaricia A1 - Peinl, René A1 - Riedhammer, Korbinian A1 - Schneider, Fabian A1 - Simic, Christopher A1 - Zakaria, Khabbab ED - Draxler, Christoph T1 - The Hochschul-Assistenz-System HAnS: An ML-Based Learning Experience Platform T2 - Elektronische Sprachsignalverarbeitung 2023: Tagungsband der 34. Konferenz München, 1.-3. März 2023 Y1 - 2023 UR - https://www.essv.de/paper.php?id=1188 SN - 978-3-95908-303-4 SP - 168 EP - 169 PB - TUDpress CY - Dresden ER -