@inproceedings{li-etal-2024-speech,
title = "Speech Recognition Corpus of the Khinalug Language for Documenting Endangered Languages",
author = "Li, Zhaolin and
Rind-Pawlowski, Monika and
Niehues, Jan",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1319",
pages = "15171--15180",
abstract = "Automatic Speech Recognition (ASR) can be a valuable tool to document endangered languages. However, building ASR tools for these languages poses several difficult research challenges, notably data scarcity. In this paper, we show the whole process of creating a useful ASR tool for language documentation scenarios. We publish the first speech corpus for Khinalug, an endangered language spoken in Northern Azerbaijan. The corpus consists of 2.67 hours of labeled data from recordings of spontaneous speech about various topics. As Khinalug is an extremely low-resource language, we investigate the benefits of multilingual models for self-supervised learning and supervised learning and achieve the performance of 6.65 Character Error Rate (CER) points and 25.53 Word Error Rate (WER) points. The benefits of multilingual models are further validated through experimentation with three additional under-resourced languages. Lastly, this work conducts quality assessments with linguists on new recordings to investigate the model{'}s usefulness in language documentation. We observe an evident degradation for new recordings, indicating the importance of enhancing model robustness. In addition, we find the inaudible content is the main cause of wrong ASR predictions, suggesting relating work on incorporating contextual information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-speech">
<titleInfo>
<title>Speech Recognition Corpus of the Khinalug Language for Documenting Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaolin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monika</namePart>
<namePart type="family">Rind-Pawlowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Speech Recognition (ASR) can be a valuable tool to document endangered languages. However, building ASR tools for these languages poses several difficult research challenges, notably data scarcity. In this paper, we show the whole process of creating a useful ASR tool for language documentation scenarios. We publish the first speech corpus for Khinalug, an endangered language spoken in Northern Azerbaijan. The corpus consists of 2.67 hours of labeled data from recordings of spontaneous speech about various topics. As Khinalug is an extremely low-resource language, we investigate the benefits of multilingual models for self-supervised learning and supervised learning and achieve the performance of 6.65 Character Error Rate (CER) points and 25.53 Word Error Rate (WER) points. The benefits of multilingual models are further validated through experimentation with three additional under-resourced languages. Lastly, this work conducts quality assessments with linguists on new recordings to investigate the model’s usefulness in language documentation. We observe an evident degradation for new recordings, indicating the importance of enhancing model robustness. In addition, we find the inaudible content is the main cause of wrong ASR predictions, suggesting relating work on incorporating contextual information.</abstract>
<identifier type="citekey">li-etal-2024-speech</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1319</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15171</start>
<end>15180</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech Recognition Corpus of the Khinalug Language for Documenting Endangered Languages
%A Li, Zhaolin
%A Rind-Pawlowski, Monika
%A Niehues, Jan
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F li-etal-2024-speech
%X Automatic Speech Recognition (ASR) can be a valuable tool to document endangered languages. However, building ASR tools for these languages poses several difficult research challenges, notably data scarcity. In this paper, we show the whole process of creating a useful ASR tool for language documentation scenarios. We publish the first speech corpus for Khinalug, an endangered language spoken in Northern Azerbaijan. The corpus consists of 2.67 hours of labeled data from recordings of spontaneous speech about various topics. As Khinalug is an extremely low-resource language, we investigate the benefits of multilingual models for self-supervised learning and supervised learning and achieve the performance of 6.65 Character Error Rate (CER) points and 25.53 Word Error Rate (WER) points. The benefits of multilingual models are further validated through experimentation with three additional under-resourced languages. Lastly, this work conducts quality assessments with linguists on new recordings to investigate the model’s usefulness in language documentation. We observe an evident degradation for new recordings, indicating the importance of enhancing model robustness. In addition, we find the inaudible content is the main cause of wrong ASR predictions, suggesting relating work on incorporating contextual information.
%U https://aclanthology.org/2024.lrec-main.1319
%P 15171-15180
Markdown (Informal)
[Speech Recognition Corpus of the Khinalug Language for Documenting Endangered Languages](https://aclanthology.org/2024.lrec-main.1319) (Li et al., LREC-COLING 2024)
ACL