A Brief Overview of Unsupervised Neural Speech Representation Learning

By Lasse Borgholt, Jakob Drachmann Havtorn, Joakim Edin, Lars Maaløe, Christian Igel. 2022

13 citations recorded by the source corpus.

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.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Generative Spoken Dialogue Language Modeling (2022, background): “Here we capitalize on recent progress in selfsupervised learning and textless speech processing (Borgholt et al., 2022; Borsos et al., 2022; Lakhotia et al., 2021) to investigate the possibility to directly train a spoken dialogue model from raw audio, bypassing the need for text or ASR.”
Self-Supervised Speech Representation Learning: A Review (2022, background): “Recently, a brief overview with a general focus on speech representation learning was published [24].”