@inproceedings{abdullah-etal-2023-nature,
title = "On the Nature of Discrete Speech Representations in Multilingual Self-supervised Models",
author = "Abdullah, Badr M. and
Shaik, Mohammed Maqsood and
Klakow, Dietrich",
editor = "Beinborn, Lisa and
Goswami, Koustava and
Murado{\u{g}}lu, Saliha and
Sorokin, Alexey and
Kumar, Ritesh and
Shcherbakov, Andreas and
Ponti, Edoardo M. and
Cotterell, Ryan and
Vylomova, Ekaterina",
booktitle = "Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigtyp-1.20",
doi = "10.18653/v1/2023.sigtyp-1.20",
pages = "159--161",
abstract = "Self-supervision has emerged as an effective paradigm for learning representations of spoken language from raw audio without explicit labels or transcriptions. Self-supervised speech models, such as wav2vec 2.0 (Baevski et al., 2020) and HuBERT (Hsu et al., 2021), have shown significant promise in improving the performance across different speech processing tasks. One of the main advantages of self-supervised speech models is that they can be pre-trained on a large sample of languages (Conneau et al., 2020; Babu et al.,2022), which facilitates cross-lingual transfer for low-resource languages (San et al., 2021). State-of-the-art self-supervised speech models include a quantization module that transforms the continuous acoustic input into a sequence of discrete units. One of the key questions in this area is whether the discrete representations learned via self-supervision are language-specific or language-universal. In other words, we ask: do the discrete units learned by a multilingual speech model represent the same speech sounds across languages or do they differ based on the specific language being spoken? From the practical perspective, this question has important implications for the development of speech models that can generalize across languages, particularly for low-resource languages. Furthermore, examining the level of linguistic abstraction in speech models that lack symbolic supervision is also relevant to the field of human language acquisition (Dupoux, 2018).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdullah-etal-2023-nature">
<titleInfo>
<title>On the Nature of Discrete Speech Representations in Multilingual Self-supervised Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Abdullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Maqsood</namePart>
<namePart type="family">Shaik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Beinborn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustava</namePart>
<namePart type="family">Goswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Shcherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Self-supervision has emerged as an effective paradigm for learning representations of spoken language from raw audio without explicit labels or transcriptions. Self-supervised speech models, such as wav2vec 2.0 (Baevski et al., 2020) and HuBERT (Hsu et al., 2021), have shown significant promise in improving the performance across different speech processing tasks. One of the main advantages of self-supervised speech models is that they can be pre-trained on a large sample of languages (Conneau et al., 2020; Babu et al.,2022), which facilitates cross-lingual transfer for low-resource languages (San et al., 2021). State-of-the-art self-supervised speech models include a quantization module that transforms the continuous acoustic input into a sequence of discrete units. One of the key questions in this area is whether the discrete representations learned via self-supervision are language-specific or language-universal. In other words, we ask: do the discrete units learned by a multilingual speech model represent the same speech sounds across languages or do they differ based on the specific language being spoken? From the practical perspective, this question has important implications for the development of speech models that can generalize across languages, particularly for low-resource languages. Furthermore, examining the level of linguistic abstraction in speech models that lack symbolic supervision is also relevant to the field of human language acquisition (Dupoux, 2018).</abstract>
<identifier type="citekey">abdullah-etal-2023-nature</identifier>
<identifier type="doi">10.18653/v1/2023.sigtyp-1.20</identifier>
<location>
<url>https://aclanthology.org/2023.sigtyp-1.20</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>159</start>
<end>161</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Nature of Discrete Speech Representations in Multilingual Self-supervised Models
%A Abdullah, Badr M.
%A Shaik, Mohammed Maqsood
%A Klakow, Dietrich
%Y Beinborn, Lisa
%Y Goswami, Koustava
%Y Muradoğlu, Saliha
%Y Sorokin, Alexey
%Y Kumar, Ritesh
%Y Shcherbakov, Andreas
%Y Ponti, Edoardo M.
%Y Cotterell, Ryan
%Y Vylomova, Ekaterina
%S Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F abdullah-etal-2023-nature
%X Self-supervision has emerged as an effective paradigm for learning representations of spoken language from raw audio without explicit labels or transcriptions. Self-supervised speech models, such as wav2vec 2.0 (Baevski et al., 2020) and HuBERT (Hsu et al., 2021), have shown significant promise in improving the performance across different speech processing tasks. One of the main advantages of self-supervised speech models is that they can be pre-trained on a large sample of languages (Conneau et al., 2020; Babu et al.,2022), which facilitates cross-lingual transfer for low-resource languages (San et al., 2021). State-of-the-art self-supervised speech models include a quantization module that transforms the continuous acoustic input into a sequence of discrete units. One of the key questions in this area is whether the discrete representations learned via self-supervision are language-specific or language-universal. In other words, we ask: do the discrete units learned by a multilingual speech model represent the same speech sounds across languages or do they differ based on the specific language being spoken? From the practical perspective, this question has important implications for the development of speech models that can generalize across languages, particularly for low-resource languages. Furthermore, examining the level of linguistic abstraction in speech models that lack symbolic supervision is also relevant to the field of human language acquisition (Dupoux, 2018).
%R 10.18653/v1/2023.sigtyp-1.20
%U https://aclanthology.org/2023.sigtyp-1.20
%U https://doi.org/10.18653/v1/2023.sigtyp-1.20
%P 159-161
Markdown (Informal)
[On the Nature of Discrete Speech Representations in Multilingual Self-supervised Models](https://aclanthology.org/2023.sigtyp-1.20) (Abdullah et al., SIGTYP 2023)
ACL