@inproceedings{lee-etal-2022-self,
title = "Self-supervised Representation Learning for Speech Processing",
author = "Lee, Hung-yi and
Mohamed, Abdelrahman and
Watanabe, Shinji and
Sainath, Tara and
Livescu, Karen and
Li, Shang-Wen and
Yang, Shu-wen and
Kirchhoff, Katrin",
editor = "Ballesteros, Miguel and
Tsvetkov, Yulia and
Alm, Cecilia O.",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-tutorials.2",
doi = "10.18653/v1/2022.naacl-tutorials.2",
pages = "8--13",
abstract = "There is a trend in the machine learning community to adopt self-supervised approaches to pre-train deep networks. Self-supervised representation learning (SSL) utilizes proxy supervised learning tasks, for example, distinguishing parts of the input signal from distractors, or generating masked input segments conditioned on the unmasked ones, to obtain training data from unlabeled corpora. BERT and GPT in NLP and SimCLR and BYOL in CV are famous examples in this direction. These approaches make it possible to use a tremendous amount of unlabeled data available on the web to train large networks and solve complicated tasks. Thus, SSL has the potential to scale up current machine learning technologies, especially for low-resourced, under-represented use cases, and democratize the technologies. Recently self-supervised approaches for speech processing are also gaining popularity. There are several workshops in relevant topics hosted at ICML 2020 (\url{https://icml-sas.gitlab.io/}), NeurIPS 2020 (\url{https://neurips-sas-2020.github.io/}), and AAAI 2022 (\url{https://aaai-sas-2022.github.io/}). However, there is no previous tutorial about a similar topic based on the authors{'} best knowledge. Due to the growing popularity of SSL, and the shared mission of the areas in bringing speech and language technologies to more use cases with better quality and scaling the technologies for under-represented languages, we propose this tutorial to systematically survey the latest SSL techniques, tools, datasets, and performance achievement in speech processing. The proposed tutorial is highly relevant to the special theme of ACL about language diversity. One of the main focuses of the tutorial is leveraging SSL to reduce the dependence of speech technologies on labeled data, and to scale up the technologies especially for under-represented languages and use cases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2022-self">
<titleInfo>
<title>Self-supervised Representation Learning for Speech Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tara</namePart>
<namePart type="family">Sainath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Livescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shang-Wen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu-wen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Kirchhoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Ballesteros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cecilia</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Alm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There is a trend in the machine learning community to adopt self-supervised approaches to pre-train deep networks. Self-supervised representation learning (SSL) utilizes proxy supervised learning tasks, for example, distinguishing parts of the input signal from distractors, or generating masked input segments conditioned on the unmasked ones, to obtain training data from unlabeled corpora. BERT and GPT in NLP and SimCLR and BYOL in CV are famous examples in this direction. These approaches make it possible to use a tremendous amount of unlabeled data available on the web to train large networks and solve complicated tasks. Thus, SSL has the potential to scale up current machine learning technologies, especially for low-resourced, under-represented use cases, and democratize the technologies. Recently self-supervised approaches for speech processing are also gaining popularity. There are several workshops in relevant topics hosted at ICML 2020 (https://icml-sas.gitlab.io/), NeurIPS 2020 (https://neurips-sas-2020.github.io/), and AAAI 2022 (https://aaai-sas-2022.github.io/). However, there is no previous tutorial about a similar topic based on the authors’ best knowledge. Due to the growing popularity of SSL, and the shared mission of the areas in bringing speech and language technologies to more use cases with better quality and scaling the technologies for under-represented languages, we propose this tutorial to systematically survey the latest SSL techniques, tools, datasets, and performance achievement in speech processing. The proposed tutorial is highly relevant to the special theme of ACL about language diversity. One of the main focuses of the tutorial is leveraging SSL to reduce the dependence of speech technologies on labeled data, and to scale up the technologies especially for under-represented languages and use cases.</abstract>
<identifier type="citekey">lee-etal-2022-self</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-tutorials.2</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-tutorials.2</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>8</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-supervised Representation Learning for Speech Processing
%A Lee, Hung-yi
%A Mohamed, Abdelrahman
%A Watanabe, Shinji
%A Sainath, Tara
%A Livescu, Karen
%A Li, Shang-Wen
%A Yang, Shu-wen
%A Kirchhoff, Katrin
%Y Ballesteros, Miguel
%Y Tsvetkov, Yulia
%Y Alm, Cecilia O.
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F lee-etal-2022-self
%X There is a trend in the machine learning community to adopt self-supervised approaches to pre-train deep networks. Self-supervised representation learning (SSL) utilizes proxy supervised learning tasks, for example, distinguishing parts of the input signal from distractors, or generating masked input segments conditioned on the unmasked ones, to obtain training data from unlabeled corpora. BERT and GPT in NLP and SimCLR and BYOL in CV are famous examples in this direction. These approaches make it possible to use a tremendous amount of unlabeled data available on the web to train large networks and solve complicated tasks. Thus, SSL has the potential to scale up current machine learning technologies, especially for low-resourced, under-represented use cases, and democratize the technologies. Recently self-supervised approaches for speech processing are also gaining popularity. There are several workshops in relevant topics hosted at ICML 2020 (https://icml-sas.gitlab.io/), NeurIPS 2020 (https://neurips-sas-2020.github.io/), and AAAI 2022 (https://aaai-sas-2022.github.io/). However, there is no previous tutorial about a similar topic based on the authors’ best knowledge. Due to the growing popularity of SSL, and the shared mission of the areas in bringing speech and language technologies to more use cases with better quality and scaling the technologies for under-represented languages, we propose this tutorial to systematically survey the latest SSL techniques, tools, datasets, and performance achievement in speech processing. The proposed tutorial is highly relevant to the special theme of ACL about language diversity. One of the main focuses of the tutorial is leveraging SSL to reduce the dependence of speech technologies on labeled data, and to scale up the technologies especially for under-represented languages and use cases.
%R 10.18653/v1/2022.naacl-tutorials.2
%U https://aclanthology.org/2022.naacl-tutorials.2
%U https://doi.org/10.18653/v1/2022.naacl-tutorials.2
%P 8-13
Markdown (Informal)
[Self-supervised Representation Learning for Speech Processing](https://aclanthology.org/2022.naacl-tutorials.2) (Lee et al., NAACL 2022)
ACL
- Hung-yi Lee, Abdelrahman Mohamed, Shinji Watanabe, Tara Sainath, Karen Livescu, Shang-Wen Li, Shu-wen Yang, and Katrin Kirchhoff. 2022. Self-supervised Representation Learning for Speech Processing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts, pages 8–13, Seattle, United States. Association for Computational Linguistics.