Boosting Norwegian Automatic Speech Recognition
This work addresses speech recognition for Norwegian speakers, providing incremental improvements over existing models.
The paper tackled automatic speech recognition for Norwegian languages (Bokmål and Nynorsk), improving the state-of-the-art word error rate on the Norwegian Parliamentary Speech Corpus from 17.10% to 7.60%, with specific rates of 5.81% for Bokmål and 11.54% for Nynorsk.
In this paper, we present several baselines for automatic speech recognition (ASR) models for the two official written languages in Norway: Bokmål 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 Bokmål and 11.54\% for Nynorsk. We also discuss the challenges and potential solutions for further improving ASR models for Norwegian.