<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="millet-dunbar-2022-self">
    <titleInfo>
        <title>Do self-supervised speech models develop human-like perception biases?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Juliette</namePart>
        <namePart type="family">Millet</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ewan</namePart>
        <namePart type="family">Dunbar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Self-supervised models for speech processing form representational spaces without using any external labels. Increasingly, they appear to be a feasible way of at least partially eliminating costly manual annotations, a problem of particular concern for low-resource languages. But what kind of representational spaces do these models construct?Human perception specializes to the sounds of listeners’ native languages. Does the same thing happen in self-supervised models? We examine the representational spaces of three kinds of state of the art self-supervised models: wav2vec, HuBERT and contrastive predictive coding (CPC), and compare them with the perceptual spaces of French-speaking and English-speaking human listeners, both globally and taking account of the behavioural differences between the two language groups. We show that the CPC model shows a small native language effect, but that wav2vec and HuBERT seem to develop a universal speech perception space which is not language specific. A comparison against the predictions of supervised phone recognisers suggests that all three self-supervised models capture relatively fine-grained perceptual phenomena, while supervised models are better at capturing coarser, phone-level effects, and effects of listeners’ native language, on perception.</abstract>
    <identifier type="citekey">millet-dunbar-2022-self</identifier>
    <identifier type="doi">10.18653/v1/2022.acl-long.523</identifier>
    <location>
        <url>https://aclanthology.org/2022.acl-long.523</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>7591</start>
            <end>7605</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Do self-supervised speech models develop human-like perception biases?
%A Millet, Juliette
%A Dunbar, Ewan
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F millet-dunbar-2022-self
%X Self-supervised models for speech processing form representational spaces without using any external labels. Increasingly, they appear to be a feasible way of at least partially eliminating costly manual annotations, a problem of particular concern for low-resource languages. But what kind of representational spaces do these models construct?Human perception specializes to the sounds of listeners’ native languages. Does the same thing happen in self-supervised models? We examine the representational spaces of three kinds of state of the art self-supervised models: wav2vec, HuBERT and contrastive predictive coding (CPC), and compare them with the perceptual spaces of French-speaking and English-speaking human listeners, both globally and taking account of the behavioural differences between the two language groups. We show that the CPC model shows a small native language effect, but that wav2vec and HuBERT seem to develop a universal speech perception space which is not language specific. A comparison against the predictions of supervised phone recognisers suggests that all three self-supervised models capture relatively fine-grained perceptual phenomena, while supervised models are better at capturing coarser, phone-level effects, and effects of listeners’ native language, on perception.
%R 10.18653/v1/2022.acl-long.523
%U https://aclanthology.org/2022.acl-long.523
%U https://doi.org/10.18653/v1/2022.acl-long.523
%P 7591-7605

Markdown (Informal)

[Do self-supervised speech models develop human-like perception biases?](https://aclanthology.org/2022.acl-long.523) (Millet & Dunbar, ACL 2022)

• Do self-supervised speech models develop human-like perception biases? (Millet & Dunbar, ACL 2022)

ACL

• Juliette Millet and Ewan Dunbar. 2022. Do self-supervised speech models develop human-like perception biases?. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7591–7605, Dublin, Ireland. Association for Computational Linguistics.