<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2024-parameter">
    <titleInfo>
        <title>Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abhishek</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amruta</namePart>
        <namePart type="family">Parulekar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sameep</namePart>
        <namePart type="family">Chattopadhyay</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Preethi</namePart>
        <namePart type="family">Jyothi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jonne</namePart>
            <namePart type="family">Sälevä</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abraham</namePart>
            <namePart type="family">Owodunni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address such low-resource settings. In this work, we investigate how these techniques can be effectively combined using a multilingual multimodal model like SeamlessM4T. Multimodal models are able to leverage unlabeled text via text-only adaptation with further parameter-efficient ASR fine-tuning, thus boosting ASR performance. We also show cross-lingual transfer from a high-resource language, achieving up to a relative 17% WER reduction over baseline in an extremely low-resource setting without any labeled speech.</abstract>
    <identifier type="citekey">gupta-etal-2024-parameter</identifier>
    <location>
        <url>https://aclanthology.org/2024.mrl-1.13</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>175</start>
            <end>185</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR
%A Gupta, Abhishek
%A Parulekar, Amruta
%A Chattopadhyay, Sameep
%A Jyothi, Preethi
%Y Sälevä, Jonne
%Y Owodunni, Abraham
%S Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F gupta-etal-2024-parameter
%X Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address such low-resource settings. In this work, we investigate how these techniques can be effectively combined using a multilingual multimodal model like SeamlessM4T. Multimodal models are able to leverage unlabeled text via text-only adaptation with further parameter-efficient ASR fine-tuning, thus boosting ASR performance. We also show cross-lingual transfer from a high-resource language, achieving up to a relative 17% WER reduction over baseline in an extremely low-resource setting without any labeled speech.
%U https://aclanthology.org/2024.mrl-1.13
%P 175-185

Markdown (Informal)

[Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR](https://aclanthology.org/2024.mrl-1.13) (Gupta et al., MRL 2024)

• Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR (Gupta et al., MRL 2024)

ACL

• Abhishek Gupta, Amruta Parulekar, Sameep Chattopadhyay, and Preethi Jyothi. 2024. Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR. In Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024), pages 175–185, Miami, Florida, USA. Association for Computational Linguistics.