@inproceedings{zhang-etal-2024-evaluation-croatian,
title = "An Evaluation of {C}roatian {ASR} Models for {\v{C}}akavian Transcription",
author = "Zhang, Shulin and
Hale, John and
Renwick, Margaret and
Vrzi{\'c}, Zvjezdana and
Langston, Keith",
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.98",
pages = "1098--1104",
abstract = "To assist in the documentation of {\v{C}}akavian, an endangered language variety closely related to Croatian, we test four currently available ASR models that are trained with Croatian data and assess their performance in the transcription of {\v{C}}akavian audio data. We compare the models{'} word error rates, analyze the word-level error types, and showcase the most frequent Deletion and Substitution errors. The evaluation results indicate that the best-performing system for transcribing {\v{C}}akavian was a CTC-based variant of the Conformer model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-evaluation-croatian">
<titleInfo>
<title>An Evaluation of Croatian ASR Models for Čakavian Transcription</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shulin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Hale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margaret</namePart>
<namePart type="family">Renwick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zvjezdana</namePart>
<namePart type="family">Vrzić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="family">Langston</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>To assist in the documentation of Čakavian, an endangered language variety closely related to Croatian, we test four currently available ASR models that are trained with Croatian data and assess their performance in the transcription of Čakavian audio data. We compare the models’ word error rates, analyze the word-level error types, and showcase the most frequent Deletion and Substitution errors. The evaluation results indicate that the best-performing system for transcribing Čakavian was a CTC-based variant of the Conformer model.</abstract>
<identifier type="citekey">zhang-etal-2024-evaluation-croatian</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.98</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1098</start>
<end>1104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Evaluation of Croatian ASR Models for Čakavian Transcription
%A Zhang, Shulin
%A Hale, John
%A Renwick, Margaret
%A Vrzić, Zvjezdana
%A Langston, Keith
%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 zhang-etal-2024-evaluation-croatian
%X To assist in the documentation of Čakavian, an endangered language variety closely related to Croatian, we test four currently available ASR models that are trained with Croatian data and assess their performance in the transcription of Čakavian audio data. We compare the models’ word error rates, analyze the word-level error types, and showcase the most frequent Deletion and Substitution errors. The evaluation results indicate that the best-performing system for transcribing Čakavian was a CTC-based variant of the Conformer model.
%U https://aclanthology.org/2024.lrec-main.98
%P 1098-1104
Markdown (Informal)
[An Evaluation of Croatian ASR Models for Čakavian Transcription](https://aclanthology.org/2024.lrec-main.98) (Zhang et al., LREC-COLING 2024)
ACL
- Shulin Zhang, John Hale, Margaret Renwick, Zvjezdana Vrzić, and Keith Langston. 2024. An Evaluation of Croatian ASR Models for Čakavian Transcription. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1098–1104, Torino, Italia. ELRA and ICCL.