In this paper, we explore neural network models that learn to associate segments of spoken
audio captions with the semantically relevant portions of natural images that they refer to …

With recent advances in machine-learning techniques for automatic speech analysis (ASA)-
the computerized extraction of information from speech signals-there is a greater need for …

In this paper, we present a method for learning discrete linguistic units by incorporating
vector quantization layers into neural models of visually grounded speech. We show that our …

This paper discusses how automatic speech recognition systems are and could be
designed, in order to best exploit the discriminative information encoded in human speech …

Recent research has shown that word embedding spaces learned from text corpora of
different languages can be aligned without any parallel data supervision. Inspired by the …

Zero-resource speech technology is a growing research area that aims to develop methods
for speech processing in the absence of transcriptions, lexicons, or language modelling text …

Systems that can associate images with their spoken audio captions are an important step
towards visually grounded language learning. We describe a scalable method to …

Unsupervised segmentation and clustering of unlabelled speech are core problems in zero-
resource speech processing. Most approaches lie at methodological extremes: some use …

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 …

Query-by-example search often uses dynamic time warping (DTW) for comparing queries
and proposed matching segments. Recent work has shown that comparing speech …