Recently proposed self-supervised learning approaches have been successful for pre-
training speech representation models. The utility of these learned representations has been …

How can we learn unified representations for spoken utterances and their written text?
Learning similar representations for semantically similar speech and text is important for …

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 …

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 …

Given the strong results of self-supervised models on various tasks, there have been
surprisingly few studies exploring self-supervised representations for acoustic word …

Recently, a number of approaches to train speech models by incorporating text into end-to-
end models have been developed, with Maestro advancing state-of-the-art automatic …

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 …

Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length
speech segments. For zero-resource languages where labelled data is not available, one …

How can deep neural networks encode information that corresponds to words in human
speech into raw acoustic data? This paper proposes two neural network architectures for …

The high cost of data acquisition makes Automatic Speech Recognition (ASR) model
training problematic for most existing languages, including languages that do not even have …