Abstract
The aim of this work is to present a set of novel language resources in Faroese suitable for the field of Automatic Speech Recognition including: an ASR corpus comprised of 109 hours of transcribed speech data, acoustic models in systems such as WAV2VEC2, NVIDIA-NeMo, Kaldi and PocketSphinx; a set of n-gram language models and a set of pronunciation dictionaries with two different variants of Faroese. We also show comparison results between the distinct acoustic models presented here. All the resources exposed in this document are publicly available under creative commons licences.- Anthology ID:
- 2023.nodalida-1.4
- 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:
- 32–41
- Language:
- URL:
- https://aclanthology.org/2023.nodalida-1.4
- DOI:
- Cite (ACL):
- Carlos Hernández Mena, Annika Simonsen, and Jon Gudnason. 2023. ASR Language Resources for Faroese. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 32–41, Tórshavn, Faroe Islands. University of Tartu Library.
- Cite (Informal):
- ASR Language Resources for Faroese (Hernández Mena et al., NoDaLiDa 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.nodalida-1.4.pdf