<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kurian-etal-2025-domain">
    <titleInfo>
        <title>Domain-Specific Adaptation for ASR through Text-Only Fine-Tuning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Betty</namePart>
        <namePart type="family">Kurian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abhinav</namePart>
        <namePart type="family">Upadhyay</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abhijeet</namePart>
        <namePart type="family">Sengupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ankita</namePart>
            <namePart type="family">Shukla</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sandeep</namePart>
            <namePart type="family">Kumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amrit</namePart>
            <namePart type="given">Singh</namePart>
            <namePart type="family">Bedi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mumbai, India</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-311-1</identifier>
    </relatedItem>
    <abstract>Speech recognition models often struggle in specialized domains due to the lack of domain-specific paired audio-text data, making it difficult to adapt general-purpose systems to unique terminology and linguistic patterns. In this work, we propose a text-only domain adaptation method for Whisper, fine-tuning only the decoder using domain-relevant text. Our approach introduces trainable cross-attention bias embeddings, extended with a gated mixture-of-experts routing mechanism, enabling the model to encode domain-specific linguistic priors without any audio data. Unlike ASR adaptation methods that require paired audio-text datasets, our approach is lightweight and resource-efficient. We observe up to a 56% relative improvement in word error rate over the baseline. Our findings demonstrate that text-only adaptation is a practical and effective strategy for improving speech recognition in specialized domains with limited or no domain-specific audio.</abstract>
    <identifier type="citekey">kurian-etal-2025-domain</identifier>
    <location>
        <url>https://aclanthology.org/2025.mmloso-1.7/</url>
    </location>
    <part>
        <date>2025-12</date>
        <extent unit="page">
            <start>78</start>
            <end>85</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Domain-Specific Adaptation for ASR through Text-Only Fine-Tuning
%A Kurian, Betty
%A Upadhyay, Abhinav
%A Sengupta, Abhijeet
%Y Shukla, Ankita
%Y Kumar, Sandeep
%Y Bedi, Amrit Singh
%Y Chakraborty, Tanmoy
%S Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-311-1
%F kurian-etal-2025-domain
%X Speech recognition models often struggle in specialized domains due to the lack of domain-specific paired audio-text data, making it difficult to adapt general-purpose systems to unique terminology and linguistic patterns. In this work, we propose a text-only domain adaptation method for Whisper, fine-tuning only the decoder using domain-relevant text. Our approach introduces trainable cross-attention bias embeddings, extended with a gated mixture-of-experts routing mechanism, enabling the model to encode domain-specific linguistic priors without any audio data. Unlike ASR adaptation methods that require paired audio-text datasets, our approach is lightweight and resource-efficient. We observe up to a 56% relative improvement in word error rate over the baseline. Our findings demonstrate that text-only adaptation is a practical and effective strategy for improving speech recognition in specialized domains with limited or no domain-specific audio.
%U https://aclanthology.org/2025.mmloso-1.7/
%P 78-85

Markdown (Informal)

[Domain-Specific Adaptation for ASR through Text-Only Fine-Tuning](https://aclanthology.org/2025.mmloso-1.7/) (Kurian et al., MMLoSo 2025)

• Domain-Specific Adaptation for ASR through Text-Only Fine-Tuning (Kurian et al., MMLoSo 2025)

ACL

• Betty Kurian, Abhinav Upadhyay, and Abhijeet Sengupta. 2025. Domain-Specific Adaptation for ASR through Text-Only Fine-Tuning. In Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025), pages 78–85, Mumbai, India. Association for Computational Linguistics.