Self-supervised speech representation learning (speech SSL) has demonstrated the benefit
of scale in learning rich representations for Automatic Speech Recognition (ASR) with …

Recent work on unsupervised speech segmentation has used self-supervised models with
phone and word segmentation modules that are trained jointly. This paper instead revisits …

We review autoregressive predictive coding (APC), an approach to learn speech
representation by predicting a future frame given the past frames. We present three different …

The success of deep learning comes from its ability to capture the hierarchical structure of
data by learning high-level representations defined in terms of low-level ones. In this paper …

Compressing self-supervised models has become increasingly necessary, as self-
supervised models become larger. While previous approaches have primarily focused on …

We identify a performance trade-off between the tasks of phoneme categorization and
phoneme and word segmentation in several self-supervised learning algorithms based on …

We study phrase structure induction from visually-grounded speech. The core idea is to first
segment the speech waveform into sequences of word segments, and subsequently induce …

Textless spoken language processing research aims to extend the applicability of standard
NLP toolset onto spoken language and languages with few or no textual resources. In this …

While several self-supervised approaches for learning discrete speech representation have
been proposed, it is unclear how these seemingly similar approaches relate to each other. In …

Self-supervised learning has achieved remarkable success for learning speech
representations from unlabeled data. The masking strategy plays an important role in the …