@inproceedings{luhtaru-etal-2023-automatic,
title = "Automatic Transcription for {E}stonian Children`s Speech",
author = {Luhtaru, Agnes and
Jaaska, Rauno and
Kruusam{\"a}e, Karl and
Fishel, Mark},
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-1.70/",
pages = "705--709",
abstract = "We evaluate the impact of recent improvements in Automatic Speech Recognition (ASR) on transcribing Estonian children`s speech. Our research focuses on fine-tuning large ASR models with a 10-hour Estonian children`s speech dataset to create accurate transcriptions. Our results show that large pre-trained models hold great potential when fine-tuned first with a more substantial Estonian adult speech corpus and then further trained with children`s speech."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luhtaru-etal-2023-automatic">
<titleInfo>
<title>Automatic Transcription for Estonian Children‘s Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnes</namePart>
<namePart type="family">Luhtaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rauno</namePart>
<namePart type="family">Jaaska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="family">Kruusamäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</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>We evaluate the impact of recent improvements in Automatic Speech Recognition (ASR) on transcribing Estonian children‘s speech. Our research focuses on fine-tuning large ASR models with a 10-hour Estonian children‘s speech dataset to create accurate transcriptions. Our results show that large pre-trained models hold great potential when fine-tuned first with a more substantial Estonian adult speech corpus and then further trained with children‘s speech.</abstract>
<identifier type="citekey">luhtaru-etal-2023-automatic</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.70/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>705</start>
<end>709</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Transcription for Estonian Children‘s Speech
%A Luhtaru, Agnes
%A Jaaska, Rauno
%A Kruusamäe, Karl
%A Fishel, Mark
%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 luhtaru-etal-2023-automatic
%X We evaluate the impact of recent improvements in Automatic Speech Recognition (ASR) on transcribing Estonian children‘s speech. Our research focuses on fine-tuning large ASR models with a 10-hour Estonian children‘s speech dataset to create accurate transcriptions. Our results show that large pre-trained models hold great potential when fine-tuned first with a more substantial Estonian adult speech corpus and then further trained with children‘s speech.
%U https://aclanthology.org/2023.nodalida-1.70/
%P 705-709
Markdown (Informal)
[Automatic Transcription for Estonian Children’s Speech](https://aclanthology.org/2023.nodalida-1.70/) (Luhtaru et al., NoDaLiDa 2023)
ACL
- Agnes Luhtaru, Rauno Jaaska, Karl Kruusamäe, and Mark Fishel. 2023. Automatic Transcription for Estonian Children’s Speech. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 705–709, Tórshavn, Faroe Islands. University of Tartu Library.