Abstract
We investigate the effectiveness of multilingual automatic speech recognition models for Scandinavian languages by further fine-tuning a Swedish model on Swedish, Danish, and Norwegian. We first explore zero-shot models, which perform poorly across the three languages. However, we show that a multilingual model based on a strong Swedish model, further fine-tuned on all three languages, performs well for Norwegian and Danish, with a relatively low decrease in the performance for Swedish. With a language classification module, we improve the performance of the multilingual model even further.- Anthology ID:
- 2023.nodalida-1.46
- Volume:
- Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
- Month:
- May
- Year:
- 2023
- Address:
- Tórshavn, Faroe Islands
- Editors:
- Tanel Alumäe, Mark Fishel
- Venue:
- NoDaLiDa
- SIG:
- Publisher:
- University of Tartu Library
- Note:
- Pages:
- 460–466
- Language:
- URL:
- https://aclanthology.org/2023.nodalida-1.46
- DOI:
- Cite (ACL):
- Rafal Cerniavski and Sara Stymne. 2023. Multilingual Automatic Speech Recognition for Scandinavian Languages. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 460–466, Tórshavn, Faroe Islands. University of Tartu Library.
- Cite (Informal):
- Multilingual Automatic Speech Recognition for Scandinavian Languages (Cerniavski & Stymne, NoDaLiDa 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.nodalida-1.46.pdf