We present a method for visually-grounded spoken term discovery. After training either a
HuBERT or wav2vec2. 0 model to associate spoken captions with natural images, we show …

Many self-supervised speech models (S3Ms) have been introduced over the last few years,
improving performance and data efficiency on various speech tasks. However, these …

Recent progress in self-supervised or unsupervised machine learning has opened the
possibility of building a full speech processing system from raw audio without using any …

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 …

Many self-supervised speech models (S3Ms) have been introduced over the last few years,
producing performance and data efficiency improvements for a variety of speech tasks …

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 …

Finding word boundaries in continuous speech is challenging as there is little or no
equivalent of a 'space'delimiter between words. Popular Bayesian non-parametric models …

In this paper, we show that representations capturing syllabic units emerge when training a
self-supervised speech model with a visually-grounded training objective. We demonstrate …

In this paper, we propose an unsupervised kNN-based approach for word segmentation in
speech utterances. Our method relies on self-supervised pre-trained speech …

Acoustic word embeddings (AWEs) are fixed-dimensional vector representations of speech
segments that encode phonetic content so that different realisations of the same word have …