@inproceedings{basil-etal-2023-automatic,
title = "Automatic Speech Recognition System for {M}alasar Language using Multilingual Transfer Learning",
author = "Basil, K. Raju and
Leena, G. Pillai and
Kavya, Manohar and
Elizabeth, Sherly",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.41",
pages = "472--477",
abstract = "This study pioneers the development of an automatic speech recognition (ASR) system for the Malasar language, an extremely low-resource ethnic language spoken by a tribal community in the Western Ghats of South India. Malasar is primarily an oral language which does not have a native script. Therefore, Malasar is often transcribed in Tamil script, a closely related major language. This work presents the first ever effort of leveraging the capabilities of multilingual transfer learning for recognising malasar speech. We fine-tune a pre-trained multilingual transformer model with Malasar speech data. In our endeavour to fine-tune this model using a Malasar speech corpus, we could successfully bring down the WER to 48.00{\%} from 99.08{\%} (zero shot baseline). This work demonstrates the efficacy of multilingual transfer learning in addressing the challenges of ASR for extremely low-resource languages, contributing to the preservation of their linguistic and cultural heritage.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basil-etal-2023-automatic">
<titleInfo>
<title>Automatic Speech Recognition System for Malasar Language using Multilingual Transfer Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="given">Raju</namePart>
<namePart type="family">Basil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">G</namePart>
<namePart type="given">Pillai</namePart>
<namePart type="family">Leena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manohar</namePart>
<namePart type="family">Kavya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sherly</namePart>
<namePart type="family">Elizabeth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study pioneers the development of an automatic speech recognition (ASR) system for the Malasar language, an extremely low-resource ethnic language spoken by a tribal community in the Western Ghats of South India. Malasar is primarily an oral language which does not have a native script. Therefore, Malasar is often transcribed in Tamil script, a closely related major language. This work presents the first ever effort of leveraging the capabilities of multilingual transfer learning for recognising malasar speech. We fine-tune a pre-trained multilingual transformer model with Malasar speech data. In our endeavour to fine-tune this model using a Malasar speech corpus, we could successfully bring down the WER to 48.00% from 99.08% (zero shot baseline). This work demonstrates the efficacy of multilingual transfer learning in addressing the challenges of ASR for extremely low-resource languages, contributing to the preservation of their linguistic and cultural heritage.</abstract>
<identifier type="citekey">basil-etal-2023-automatic</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.41</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>472</start>
<end>477</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Speech Recognition System for Malasar Language using Multilingual Transfer Learning
%A Basil, K. Raju
%A Leena, G. Pillai
%A Kavya, Manohar
%A Elizabeth, Sherly
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F basil-etal-2023-automatic
%X This study pioneers the development of an automatic speech recognition (ASR) system for the Malasar language, an extremely low-resource ethnic language spoken by a tribal community in the Western Ghats of South India. Malasar is primarily an oral language which does not have a native script. Therefore, Malasar is often transcribed in Tamil script, a closely related major language. This work presents the first ever effort of leveraging the capabilities of multilingual transfer learning for recognising malasar speech. We fine-tune a pre-trained multilingual transformer model with Malasar speech data. In our endeavour to fine-tune this model using a Malasar speech corpus, we could successfully bring down the WER to 48.00% from 99.08% (zero shot baseline). This work demonstrates the efficacy of multilingual transfer learning in addressing the challenges of ASR for extremely low-resource languages, contributing to the preservation of their linguistic and cultural heritage.
%U https://aclanthology.org/2023.icon-1.41
%P 472-477
Markdown (Informal)
[Automatic Speech Recognition System for Malasar Language using Multilingual Transfer Learning](https://aclanthology.org/2023.icon-1.41) (Basil et al., ICON 2023)
ACL