Fine-Tuning South Tyrolean Dialect-to-Standard German ASR with AlpiLinK
By: Greta H. Franzini and Luca Ducceschi
References
- Adda-Decker, M., Lamel, L., Adda, G., & Lavergne, T. (2014).
A First LVCSR System for Luxembourgish, a Low-Resourced European Language . In Z. Vetulani & J. Mariani (Eds.), Human Language Technology Challenges for Computer Science and Linguistics (pp. 479–490). Springer International Publishing. 10.1007/978-3-319-08958-4_39 - Blaschke, V., Winkler, M., Förster, C., Wenger-Glemser, G., & Plank, B. (2025).
A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation . In Proceedings of Interspeech 2025 (pp. 913–917). ISCA. 10.21437/Interspeech.2025-318 - Colletti, N., & Lombardo, S. (2025). Südtiroler Sprachbarometer: Sprachgebrauch und Sprachidentität in Südtirol. (Tech. Rep.), Autonome Provinz Bozen-Südtirol, Landesinstitut für Statistik – ASTAT. Retrieved 2026-05-06, from
https://assets-eu-01.kc-usercontent.com/b5376750-8076-01cf-17d2-d343e29778a7/936599a9-e59d-4c7b-bb13-f84efd0718c8/Sprachbarometer - Dehak, N., Dumouchel, P., & Kenny, P. (2007). Modeling Prosodic Features With Joint Factor Analysis for Speaker Verification. In IEEE Transactions on Audio, Speech and Language Processing (pp. 2095–2103). 10.1109/TASL.2007.902758
- Dogan-Schönberger, P., Mäder, J., & Hofmann, T. (2021). SwissDial: Parallel Multidialectal Corpus of Spoken Swiss German. (Working Paper 2103.11401). Cornell University.
- Ducceschi, L., & Franzini, G. (2025).
Speech transcription from South Tyrolean Dialect to Standard German with Whisper . In Proceedings of Interspeech 2025 (pp. 1–5). ISCA. 10.21437/Interspeech.2025-1976 - Fant, G. (1960). Acoustic Theory of Speech Production. Mouton.
- FFmpeg Developers (2016). ffmpeg tool.
https://ffmpeg.org/ - Franzini, G., & Ducceschi, L. (to appear). South Tyrolean Dialect-to-Standard Speech Translation: A Resource. In Proceedings of the Workshop on Dialects in NLP — A Resource Perspective (DialRes-LREC26), co-located with the Language Resources and Evaluation Conference (LREC). Palma de Mallorca, Spain.
- Gilles, P., Hillah, L., & Hosseini-Kivanani, N. (2023).
ASRLUX: Automatic Speech Recognition for the low-resource language Luxembourgish . In R. Skarnitzl & J. Volín (Eds.), Proceedings of the 20th International Congress of Phonetic Sciences (pp. 3091–3095).https://hdl.handle.net/10993/55819 - Hollenstein, N., & Aepli, N. (2014).
Compilation of a Swiss German Dialect Corpus and its Application to PoS Tagging . In M. Zampieri, L. Tan, N. Ljubešić, & J. Tiedemann (Eds.), Proceedings of the First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects (pp. 85–94). Association for Computational Linguistics and Dublin City University. 10.3115/v1/W14-5310 - Hosseini-Kivanani, N., Schommer, C., & Gilles, P. (2025).
Voices of Luxembourg: Tackling Dialect Diversity in a Low-Resource Setting . In Š. A. Holdt, N. Ilinykh, B. Scalvini, M. Bruton, I. N. Debess, & C. M. Tudor (Eds.), Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025) (pp. 143–152). University of Tartu Library, Estonia.https://aclanthology.org/2025.resourceful-1.29/ - Kent, R., & Read, C. (2002). The Acoustic Analysis of Speech. Singular Publishing Group.
- Kerle, L. K., Pucher, M., & Schuppler, B. (2023).
Speaker interpolation based data augmentation for automatic speech recognition . In Proceedings of the 20th International Congress of Phonetic Sciences (pp. 3126–3130). International Phonetic Association.https://phaidra.kug.ac.at/o:127503 - Kruijt, A., & Rabanus, S. (2025). From VinKo to AlpiLinK: web-based long-term storage and accessibility of information. Korpus im Text, 17.
https://www.kit.gwi.uni-muenchen.de/?p=106395&v=1 - Linke, J., Winkler, J., & Schuppler, B. (2025). Context is all you need? Low-resource conversational ASR profits from context, coming from the same or from the other speaker. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 3199–3203).
ISCA, International Speech Communication Association . 10.21437/Interspeech.2025-1824 - Plüss, M., Deriu, J., Schraner, Y., Paonessa, C., Hartmann, J., Schmidt, L., …, Cieliebak, M. (2023).
STT4SG-350: A Speech Corpus for All Swiss German Dialect Regions . In A. Rogers, J. Boyd-Graber, & N. Okazaki (Eds.), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (pp. 1763–1772). Association for Computational Linguistics. 10.18653/v1/2023.acl-short.150 - Plüss, M., Hürlimann, M., Cuny, M., Stöckli, A., Kapotis, N., Hartmann, J., …, Vogel, M. (2022). SDS-200: A Swiss German Speech to Standard German Text Corpus. In N. Calzolari, et al. (Eds.), Proceedings of the Thirteenth Language Resources and Evaluation Conference (pp. 3250–3256).
European Language Resources Association . Retrieved 2026-05-06, fromhttps://aclanthology.org/2022.lrec-1.347/ - Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2023). Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning (pp. 28492–28518).
PMLR .https://arxiv.org/abs/2212.04356 - Samardžić, T., Scherrer, Y., & Glaser, E. (2015).
Normalising orthographic and dialectal variants for the automatic processing of Swiss German . In Proceedings of the 4th Biennial Workshop on Less-resourced Languages (pp. 294–298). ELRA. Retrieved 2026-05-06, fromhttps://ltc.amu.edu.pl/a2015/book/papers/LRL-2.pdf - Sicard, C., Gillioz, V., & Pyszkowski, K. (2023). Spaiche: Extending State-of-the-Art ASR Models to Swiss German Dialects. In H. Ghorbel, M. Sokhn, M. Cieliebak, M. Hürlimann, E. de Salis, & J. Guerne (Eds.), Proceedings of the 8th Edition of the Swiss Text Analytics Conference (pp. 76–83).
Association for Computational Linguistics . Retrieved 2026-05-06, fromhttps://aclanthology.org/2023.swisstext-1.8/ - Solberg, E., Ortiz, P., Parsons, P., Svendsen, T., & Salvi, G. (2023). Improving Generalization of Norwegian ASR with Limited Linguistic Resources. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa) (pp. 508–517).
University of Tartu Library . Retrieved 2026-05-06, fromhttps://aclanthology.org/2023.nodalida-1.51/ - Stöckle, P., & Vergeiner, P. (2025). Geographical patterns in the Bavarian dialects of Austria and South Tyrol. A real-time comparison using dialectometric methods. Zeitschrift für Sprachvariation und Soziolinguistik - Journal of Language Variation and Sociolinguistics (pp. 20–41). 10.5282/jlvs/7
- Titze, I. (1994). Principles of Voice Production. Prentice Hall.
- Volgger, J., Röggla, M., Ganthaler, D., Iacopino, T., Mühlberger, M., & Mariz, C. (2024). Autonomy Dashboard South Tyrol. Eurac Research. Retrieved from
https://www.eurac.edu/doi/10-57749-m70n-ms30 - Vásquez-Correa, J. C., Orozco-Arroyave, J. R., Bocklet, T., & Nöth, E. (2018). Towards an automatic evaluation of the dysarthria level of patients with Parkinson’s disease. Journal of Communication Disorders, 21–26. 10.1016/j.jcomdis.2018.08.002
- Wiesinger, P. (1983).
Die Einteilung der deutschen Dialekte . In W. Besch, U. Knoop, W. Putschke, & H. Wiegand (Eds.), Dialektologie (pp. 807–900). de Gruyter. 10.1515/9783110203332.807 - Zhang, Y., Han, W., Qin, J., Wang, Y., Bapna, A., Chen, Z., …, others. (2023). Google USM: Scaling automatic speech recognition beyond 100 languages. 10.48550/arXiv.2303.01037
DOI: https://doi.org/10.5334/johd.533 | Journal eISSN: 2059-481X
Language: English
Page range: 74 - 74
Submitted on: Mar 1, 2026
Accepted on: May 5, 2026
Published on: Jun 8, 2026
Published by: Ubiquity Press
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year
Keywords:
© 2026 Greta H. Franzini, Luca Ducceschi, published by Ubiquity Press
This work is licensed under the Creative Commons Attribution 4.0 License.