@inproceedings{rajkhowa-etal-2024-evaluating-efficacy,
title = "Evaluating the Efficacy of Large Acoustic Model for Documenting Non-Orthographic Tribal Languages in {I}ndia",
author = "Rajkhowa, Tonmoy and
Chowdhury, Amartya Roy and
Karande, Hrishikesh Ravindra and
Prasanna, S. R. Mahadeva",
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.574",
pages = "6475--6483",
abstract = "Pre-trained Large Acoustic Models, when fine-tuned, have largely shown to improve the performances in various tasks related to spoken language technologies. However, their evaluation has been mostly on datasets that contain English or other widely spoken languages, and their potential for novel under-resourced languages is not fully known. In this work, four novel under-resourced tribal languages that do not have a standard writing system were introduced and the application of such large pre-trained models was assessed to document such languages using Automatic Speech Recognition and Direct Speech-to-Text Translation systems. The transcriptions for these tribal languages were generated by adapting scripts from those languages that held a prominent presence in the geographical regions where these tribal languages are spoken. The results from this study suggest a viable direction to document these languages in the electronic domain by using Spoken Language Technologies that incorporate LAMs. Additionally, this study helped in understanding the varying performances exhibited by the Large Acoustic Model between these four languages. This study not only informs the adoption of appropriate scripts for transliterating spoken-only languages based on the language family but also aids in making informed decisions in analyzing the behavior of particular Large Acoustic Model in linguistic contexts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajkhowa-etal-2024-evaluating-efficacy">
<titleInfo>
<title>Evaluating the Efficacy of Large Acoustic Model for Documenting Non-Orthographic Tribal Languages in India</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tonmoy</namePart>
<namePart type="family">Rajkhowa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amartya</namePart>
<namePart type="given">Roy</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrishikesh</namePart>
<namePart type="given">Ravindra</namePart>
<namePart type="family">Karande</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">S</namePart>
<namePart type="given">R</namePart>
<namePart type="given">Mahadeva</namePart>
<namePart type="family">Prasanna</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>Pre-trained Large Acoustic Models, when fine-tuned, have largely shown to improve the performances in various tasks related to spoken language technologies. However, their evaluation has been mostly on datasets that contain English or other widely spoken languages, and their potential for novel under-resourced languages is not fully known. In this work, four novel under-resourced tribal languages that do not have a standard writing system were introduced and the application of such large pre-trained models was assessed to document such languages using Automatic Speech Recognition and Direct Speech-to-Text Translation systems. The transcriptions for these tribal languages were generated by adapting scripts from those languages that held a prominent presence in the geographical regions where these tribal languages are spoken. The results from this study suggest a viable direction to document these languages in the electronic domain by using Spoken Language Technologies that incorporate LAMs. Additionally, this study helped in understanding the varying performances exhibited by the Large Acoustic Model between these four languages. This study not only informs the adoption of appropriate scripts for transliterating spoken-only languages based on the language family but also aids in making informed decisions in analyzing the behavior of particular Large Acoustic Model in linguistic contexts.</abstract>
<identifier type="citekey">rajkhowa-etal-2024-evaluating-efficacy</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.574</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6475</start>
<end>6483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Efficacy of Large Acoustic Model for Documenting Non-Orthographic Tribal Languages in India
%A Rajkhowa, Tonmoy
%A Chowdhury, Amartya Roy
%A Karande, Hrishikesh Ravindra
%A Prasanna, S. R. Mahadeva
%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 rajkhowa-etal-2024-evaluating-efficacy
%X Pre-trained Large Acoustic Models, when fine-tuned, have largely shown to improve the performances in various tasks related to spoken language technologies. However, their evaluation has been mostly on datasets that contain English or other widely spoken languages, and their potential for novel under-resourced languages is not fully known. In this work, four novel under-resourced tribal languages that do not have a standard writing system were introduced and the application of such large pre-trained models was assessed to document such languages using Automatic Speech Recognition and Direct Speech-to-Text Translation systems. The transcriptions for these tribal languages were generated by adapting scripts from those languages that held a prominent presence in the geographical regions where these tribal languages are spoken. The results from this study suggest a viable direction to document these languages in the electronic domain by using Spoken Language Technologies that incorporate LAMs. Additionally, this study helped in understanding the varying performances exhibited by the Large Acoustic Model between these four languages. This study not only informs the adoption of appropriate scripts for transliterating spoken-only languages based on the language family but also aids in making informed decisions in analyzing the behavior of particular Large Acoustic Model in linguistic contexts.
%U https://aclanthology.org/2024.lrec-main.574
%P 6475-6483
Markdown (Informal)
[Evaluating the Efficacy of Large Acoustic Model for Documenting Non-Orthographic Tribal Languages in India](https://aclanthology.org/2024.lrec-main.574) (Rajkhowa et al., LREC-COLING 2024)
ACL