A Brief Overview of Unsupervised Neural Speech Representation Learning

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

A Brief Overview of Unsupervised Neural Speech Representation Learning. / Borgholt, Lasse; Havtorn, Jakob D.; Edin, Joakim; Maaløe, Lars; Igel, Christian.

Proceedings of 2nd Workshop on Self-supervised Learning for Audio and Speech Processing. Association for the Advancement of Artificial Intelligence, 2022.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Borgholt, L, Havtorn, JD, Edin, J, Maaløe, L & Igel, C 2022, A Brief Overview of Unsupervised Neural Speech Representation Learning. i Proceedings of 2nd Workshop on Self-supervised Learning for Audio and Speech Processing. Association for the Advancement of Artificial Intelligence, Workshop on Self-supervised Learning for Audio and Speech Processing, 28/02/2022.

APA

Borgholt, L., Havtorn, J. D., Edin, J., Maaløe, L., & Igel, C. (2022). A Brief Overview of Unsupervised Neural Speech Representation Learning. I Proceedings of 2nd Workshop on Self-supervised Learning for Audio and Speech Processing Association for the Advancement of Artificial Intelligence.

Vancouver

Borgholt L, Havtorn JD, Edin J, Maaløe L, Igel C. A Brief Overview of Unsupervised Neural Speech Representation Learning. I Proceedings of 2nd Workshop on Self-supervised Learning for Audio and Speech Processing. Association for the Advancement of Artificial Intelligence. 2022

Author

Borgholt, Lasse ; Havtorn, Jakob D. ; Edin, Joakim ; Maaløe, Lars ; Igel, Christian. / A Brief Overview of Unsupervised Neural Speech Representation Learning. Proceedings of 2nd Workshop on Self-supervised Learning for Audio and Speech Processing. Association for the Advancement of Artificial Intelligence, 2022.

Bibtex

@inproceedings{aa80558a05584ba7bbf5a90521cfb32e,
title = "A Brief Overview of Unsupervised Neural Speech Representation Learning",
abstract = "Unsupervised representation learning for speech processing has matured greatly in the last few years. Work in computer vision and natural language processing has paved the way, but speech data offers unique challenges. As a result, methods from other domains rarely translate directly. We review the development of unsupervised representation learning for speech over the last decade. We identify two primary model categories: self-supervised methods and probabilistic latent variable models. We describe the models and develop a comprehensive taxonomy. Finally, we discuss and compare models from the two categories.",
author = "Lasse Borgholt and Havtorn, {Jakob D.} and Joakim Edin and Lars Maal{\o}e and Christian Igel",
year = "2022",
language = "English",
booktitle = "Proceedings of 2nd Workshop on Self-supervised Learning for Audio and Speech Processing",
publisher = "Association for the Advancement of Artificial Intelligence",
note = "Workshop on Self-supervised Learning for Audio and Speech Processing ; Conference date: 28-02-2022",
url = "https://aaai-sas-2022.github.io/",

}

RIS

TY - GEN

T1 - A Brief Overview of Unsupervised Neural Speech Representation Learning

AU - Borgholt, Lasse

AU - Havtorn, Jakob D.

AU - Edin, Joakim

AU - Maaløe, Lars

AU - Igel, Christian

N1 - Conference code: 2

PY - 2022

Y1 - 2022

N2 - Unsupervised representation learning for speech processing has matured greatly in the last few years. Work in computer vision and natural language processing has paved the way, but speech data offers unique challenges. As a result, methods from other domains rarely translate directly. We review the development of unsupervised representation learning for speech over the last decade. We identify two primary model categories: self-supervised methods and probabilistic latent variable models. We describe the models and develop a comprehensive taxonomy. Finally, we discuss and compare models from the two categories.

AB - Unsupervised representation learning for speech processing has matured greatly in the last few years. Work in computer vision and natural language processing has paved the way, but speech data offers unique challenges. As a result, methods from other domains rarely translate directly. We review the development of unsupervised representation learning for speech over the last decade. We identify two primary model categories: self-supervised methods and probabilistic latent variable models. We describe the models and develop a comprehensive taxonomy. Finally, we discuss and compare models from the two categories.

M3 - Article in proceedings

BT - Proceedings of 2nd Workshop on Self-supervised Learning for Audio and Speech Processing

PB - Association for the Advancement of Artificial Intelligence

T2 - Workshop on Self-supervised Learning for Audio and Speech Processing

Y2 - 28 February 2022

ER -

ID: 338603013