Views
No views yet
1@inproceedings{de-la-rosa-etal-2023-boosting,
2 title = "Boosting {N}orwegian Automatic Speech Recognition",
3 author = "De La Rosa, Javier and
4 Braaten, Rolv-Arild and
5 Kummervold, Per and
6 Wetjen, Freddy",
7 booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
8 month = may,
9 year = "2023",
10 address = "T{\'o}rshavn, Faroe Islands",
11 publisher = "University of Tartu Library",
12 url = "https://aclanthology.org/2023.nodalida-1.55",
13 pages = "555--564",
14 abstract = "In this paper, we present several baselines for automatic speech recognition (ASR) models for the two official written languages in Norway: Bokm{\aa}l and Nynorsk. We compare the performance of models of varying sizes and pre-training approaches on multiple Norwegian speech datasets. Additionally, we measure the performance of these models against previous state-of-the-art ASR models, as well as on out-of-domain datasets. We improve the state of the art on the Norwegian Parliamentary Speech Corpus (NPSC) from a word error rate (WER) of 17.10{\%} to 7.60{\%}, with models achieving 5.81{\%} for Bokm{\aa}l and 11.54{\%} for Nynorsk. We also discuss the challenges and potential solutions for further improving ASR models for Norwegian.",
15}