<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-theory">
    <titleInfo>
        <title>A Theory of Unsupervised Speech Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Liming</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Hasegawa-Johnson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chang</namePart>
        <namePart type="family">Yoo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Unsupervised speech recognition (pasted macro ‘ASRU’/) is the problem of learning automatic speech recognition (ASR) systems from unpaired speech-only and text-only corpora. While various algorithms exist to solve this problem, a theoretical framework is missing to study their properties and address such issues as sensitivity to hyperparameters and training instability. In this paper, we proposed a general theoretical framework to study the properties of pasted macro ‘ASRU’/ systems based on random matrix theory and the theory of neural tangent kernels. Such a framework allows us to prove various learnability conditions and sample complexity bounds of pasted macro ‘ASRU’/. Extensive pasted macro ‘ASRU’/ experiments on synthetic languages with three classes of transition graphs provide strong empirical evidence for our theory (code available at https://github.com/cactuswiththoughts/UnsupASRTheory.gitcactuswiththoughts/UnsupASRTheory.git).</abstract>
    <identifier type="citekey">wang-etal-2023-theory</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.67</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.67</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1192</start>
            <end>1215</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Theory of Unsupervised Speech Recognition
%A Wang, Liming
%A Hasegawa-Johnson, Mark
%A Yoo, Chang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-theory
%X Unsupervised speech recognition (pasted macro ‘ASRU’/) is the problem of learning automatic speech recognition (ASR) systems from unpaired speech-only and text-only corpora. While various algorithms exist to solve this problem, a theoretical framework is missing to study their properties and address such issues as sensitivity to hyperparameters and training instability. In this paper, we proposed a general theoretical framework to study the properties of pasted macro ‘ASRU’/ systems based on random matrix theory and the theory of neural tangent kernels. Such a framework allows us to prove various learnability conditions and sample complexity bounds of pasted macro ‘ASRU’/. Extensive pasted macro ‘ASRU’/ experiments on synthetic languages with three classes of transition graphs provide strong empirical evidence for our theory (code available at https://github.com/cactuswiththoughts/UnsupASRTheory.gitcactuswiththoughts/UnsupASRTheory.git).
%R 10.18653/v1/2023.acl-long.67
%U https://aclanthology.org/2023.acl-long.67
%U https://doi.org/10.18653/v1/2023.acl-long.67
%P 1192-1215

Markdown (Informal)

[A Theory of Unsupervised Speech Recognition](https://aclanthology.org/2023.acl-long.67) (Wang et al., ACL 2023)

• A Theory of Unsupervised Speech Recognition (Wang et al., ACL 2023)

ACL

• Liming Wang, Mark Hasegawa-Johnson, and Chang Yoo. 2023. A Theory of Unsupervised Speech Recognition. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1192–1215, Toronto, Canada. Association for Computational Linguistics.