<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nachesa-niculae-2025-knn">
    <titleInfo>
        <title>kNN For Whisper And Its Effect On Bias And Speaker Adaptation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maya</namePart>
        <namePart type="given">K</namePart>
        <namePart type="family">Nachesa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vlad</namePart>
        <namePart type="family">Niculae</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-195-7</identifier>
    </relatedItem>
    <abstract>Speech recognition performance varies by language, domain, and speaker characteristics such as accent, but fine-tuning a model on any of these categories may lead to catastrophic forgetting. Token-level k nearest neighbor search (kNN), first proposed for neural sequence decoders for natural language generation (NLG) and machine translation (MT), is a non-parametric method that instead adapts using inference-time search in an external datastore, without training the underlying model. We show that Whisper, a transformer end-to-end speech model, benefits from kNN. We investigate the differences between the speech and text setups. We discuss implications for speaker adaptation, and analyze improvements by gender, accent, and age.</abstract>
    <identifier type="citekey">nachesa-niculae-2025-knn</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-naacl.369</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-naacl.369/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>6621</start>
            <end>6627</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T kNN For Whisper And Its Effect On Bias And Speaker Adaptation
%A Nachesa, Maya K.
%A Niculae, Vlad
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F nachesa-niculae-2025-knn
%X Speech recognition performance varies by language, domain, and speaker characteristics such as accent, but fine-tuning a model on any of these categories may lead to catastrophic forgetting. Token-level k nearest neighbor search (kNN), first proposed for neural sequence decoders for natural language generation (NLG) and machine translation (MT), is a non-parametric method that instead adapts using inference-time search in an external datastore, without training the underlying model. We show that Whisper, a transformer end-to-end speech model, benefits from kNN. We investigate the differences between the speech and text setups. We discuss implications for speaker adaptation, and analyze improvements by gender, accent, and age.
%R 10.18653/v1/2025.findings-naacl.369
%U https://aclanthology.org/2025.findings-naacl.369/
%U https://doi.org/10.18653/v1/2025.findings-naacl.369
%P 6621-6627

Markdown (Informal)

[kNN For Whisper And Its Effect On Bias And Speaker Adaptation](https://aclanthology.org/2025.findings-naacl.369/) (Nachesa & Niculae, Findings 2025)

• kNN For Whisper And Its Effect On Bias And Speaker Adaptation (Nachesa & Niculae, Findings 2025)

ACL

• Maya K. Nachesa and Vlad Niculae. 2025. kNN For Whisper And Its Effect On Bias And Speaker Adaptation. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 6621–6627, Albuquerque, New Mexico. Association for Computational Linguistics.