<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rupak-raj-etal-2023-active">
    <titleInfo>
        <title>Active Learning Approach for Fine-Tuning Pre-Trained ASR Model for a Low-Resourced Language: A Case Study of Nepali</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ghimire</namePart>
        <namePart type="family">Rupak Raj</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bal</namePart>
        <namePart type="family">Bal Krishna</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Poudyal</namePart>
        <namePart type="family">Prakash</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>Fine tuning of the pre-trained language model is a technique which can be used to enhance the technologies of low-resourced languages. The unsupervised approach can fine-tune any pre-trained model with minimum or even no language-specific resources. It is highly advantageous, particularly for languages that possess limited computational resources. We present a novel approach for fine-tuning a pre-trained Automatic Speech Recognition (ASR) model that is suitable for low resource languages. Our methods involves iterative fine-tuning of pre-trained ASR model. mms-1b is selected as the pretrained seed model for fine-tuning. We take the Nepali language as a case study for this research work. Our approach achieved a CER of 6.77%, outperforming all previously recorded CER values for the Nepali ASR Systems.</abstract>
    <identifier type="citekey">rupak-raj-etal-2023-active</identifier>
    <location>
        <url>https://aclanthology.org/2023.icon-1.9</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>82</start>
            <end>89</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Active Learning Approach for Fine-Tuning Pre-Trained ASR Model for a Low-Resourced Language: A Case Study of Nepali
%A Rupak Raj, Ghimire
%A Bal Krishna, Bal
%A Prakash, Poudyal
%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 rupak-raj-etal-2023-active
%X Fine tuning of the pre-trained language model is a technique which can be used to enhance the technologies of low-resourced languages. The unsupervised approach can fine-tune any pre-trained model with minimum or even no language-specific resources. It is highly advantageous, particularly for languages that possess limited computational resources. We present a novel approach for fine-tuning a pre-trained Automatic Speech Recognition (ASR) model that is suitable for low resource languages. Our methods involves iterative fine-tuning of pre-trained ASR model. mms-1b is selected as the pretrained seed model for fine-tuning. We take the Nepali language as a case study for this research work. Our approach achieved a CER of 6.77%, outperforming all previously recorded CER values for the Nepali ASR Systems.
%U https://aclanthology.org/2023.icon-1.9
%P 82-89

Markdown (Informal)

[Active Learning Approach for Fine-Tuning Pre-Trained ASR Model for a Low-Resourced Language: A Case Study of Nepali](https://aclanthology.org/2023.icon-1.9) (Rupak Raj et al., ICON 2023)

• Active Learning Approach for Fine-Tuning Pre-Trained ASR Model for a Low-Resourced Language: A Case Study of Nepali (Rupak Raj et al., ICON 2023)

ACL

• Ghimire Rupak Raj, Bal Bal Krishna, and Poudyal Prakash. 2023. Active Learning Approach for Fine-Tuning Pre-Trained ASR Model for a Low-Resourced Language: A Case Study of Nepali. In Proceedings of the 20th International Conference on Natural Language Processing (ICON), pages 82–89, Goa University, Goa, India. NLP Association of India (NLPAI).