@inproceedings{de-la-rosa-etal-2023-boosting,
title = "Boosting {N}orwegian Automatic Speech Recognition",
author = "De La Rosa, Javier and
Braaten, Rolv-Arild and
Kummervold, Per and
Wetjen, Freddy",
editor = {Alum{\"a}e, Tanel and
Fishel, Mark},
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.55",
pages = "555--564",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-la-rosa-etal-2023-boosting">
<titleInfo>
<title>Boosting Norwegian Automatic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">De La Rosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolv-Arild</namePart>
<namePart type="family">Braaten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Per</namePart>
<namePart type="family">Kummervold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Freddy</namePart>
<namePart type="family">Wetjen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanel</namePart>
<namePart type="family">Alumäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tórshavn, Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">de-la-rosa-etal-2023-boosting</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.55</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>555</start>
<end>564</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Boosting Norwegian Automatic Speech Recognition
%A De La Rosa, Javier
%A Braaten, Rolv-Arild
%A Kummervold, Per
%A Wetjen, Freddy
%Y Alumäe, Tanel
%Y Fishel, Mark
%S Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2023
%8 May
%I University of Tartu Library
%C Tórshavn, Faroe Islands
%F de-la-rosa-etal-2023-boosting
%X 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.
%U https://aclanthology.org/2023.nodalida-1.55
%P 555-564
Markdown (Informal)
[Boosting Norwegian Automatic Speech Recognition](https://aclanthology.org/2023.nodalida-1.55) (De La Rosa et al., NoDaLiDa 2023)
ACL
- Javier De La Rosa, Rolv-Arild Braaten, Per Kummervold, and Freddy Wetjen. 2023. Boosting Norwegian Automatic Speech Recognition. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 555–564, Tórshavn, Faroe Islands. University of Tartu Library.