@inproceedings{j-etal-2024-dravidian,
title = "{DRAVIDIAN} {LANGUAGE}@ {LT}-{EDI} 2024:Pretrained Transformer based Automatic Speech Recognition system for Elderly People",
author = "J, Abirami. and
Devi. S, Aruna and
Sasikumar, Dharunika and
B, Bharathi",
editor = {Chakravarthi, Bharathi Raja and
B, Bharathi and
Buitelaar, Paul and
Durairaj, Thenmozhi and
Kov{\'a}cs, Gy{\"o}rgy and
Garc{\'\i}a Cumbreras, Miguel {\'A}ngel},
booktitle = "Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.ltedi-1.31",
pages = "244--248",
abstract = "In this paper, the main goal of the study is to create an automatic speech recognition (ASR) system that is tailored to the Tamil language. The dataset that was employed includes audio recordings that were obtained from vulnerable populations in the Tamil region, such as elderly men and women and transgender individuals. The pre-trained model Rajaram1996/wav2vec2- large-xlsr-53-tamil is used in the engineering of the ASR system. This existing model is finetuned using a variety of datasets that include typical Tamil voices. The system is then tested with a specific test dataset, and the transcriptions that are produced are sent in for assessment. The Word Error Rate is used to evaluate the system{'}s performance. Our system has a WER of 37.733.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="j-etal-2024-dravidian">
<titleInfo>
<title>DRAVIDIAN LANGUAGE@ LT-EDI 2024:Pretrained Transformer based Automatic Speech Recognition system for Elderly People</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abirami.</namePart>
<namePart type="family">J</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aruna</namePart>
<namePart type="family">Devi. S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dharunika</namePart>
<namePart type="family">Sasikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thenmozhi</namePart>
<namePart type="family">Durairaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Kovács</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Ángel</namePart>
<namePart type="family">García Cumbreras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, the main goal of the study is to create an automatic speech recognition (ASR) system that is tailored to the Tamil language. The dataset that was employed includes audio recordings that were obtained from vulnerable populations in the Tamil region, such as elderly men and women and transgender individuals. The pre-trained model Rajaram1996/wav2vec2- large-xlsr-53-tamil is used in the engineering of the ASR system. This existing model is finetuned using a variety of datasets that include typical Tamil voices. The system is then tested with a specific test dataset, and the transcriptions that are produced are sent in for assessment. The Word Error Rate is used to evaluate the system’s performance. Our system has a WER of 37.733.</abstract>
<identifier type="citekey">j-etal-2024-dravidian</identifier>
<location>
<url>https://aclanthology.org/2024.ltedi-1.31</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>244</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DRAVIDIAN LANGUAGE@ LT-EDI 2024:Pretrained Transformer based Automatic Speech Recognition system for Elderly People
%A J, Abirami.
%A Devi. S, Aruna
%A Sasikumar, Dharunika
%A B, Bharathi
%Y Chakravarthi, Bharathi Raja
%Y B, Bharathi
%Y Buitelaar, Paul
%Y Durairaj, Thenmozhi
%Y Kovács, György
%Y García Cumbreras, Miguel Ángel
%S Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F j-etal-2024-dravidian
%X In this paper, the main goal of the study is to create an automatic speech recognition (ASR) system that is tailored to the Tamil language. The dataset that was employed includes audio recordings that were obtained from vulnerable populations in the Tamil region, such as elderly men and women and transgender individuals. The pre-trained model Rajaram1996/wav2vec2- large-xlsr-53-tamil is used in the engineering of the ASR system. This existing model is finetuned using a variety of datasets that include typical Tamil voices. The system is then tested with a specific test dataset, and the transcriptions that are produced are sent in for assessment. The Word Error Rate is used to evaluate the system’s performance. Our system has a WER of 37.733.
%U https://aclanthology.org/2024.ltedi-1.31
%P 244-248
Markdown (Informal)
[DRAVIDIAN LANGUAGE@ LT-EDI 2024:Pretrained Transformer based Automatic Speech Recognition system for Elderly People](https://aclanthology.org/2024.ltedi-1.31) (J et al., LTEDI-WS 2024)
ACL