Learning meaningful and general representations from unannotated speech that are
applicable to a wide range of tasks remains challenging. In this paper we propose to use …

We investigate unsupervised models that can map a variable-duration speech segment to a
fixed-dimensional representation. In settings where unlabelled speech is the only available …

Training objectives based on predictive coding have recently been shown to be very
effective at learning meaningful representations from unlabeled speech. One example is …

Semantic association computation is the process of quantifying the strength of a semantic
connection between two textual units, based on different types of semantic relations …

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

Producing a large annotated speech corpus for training ASR systems remains difficult for
more than 95% of languages all over the world which are low-resourced, but collecting a …

In text, word2vec transforms each word into a fixed-size vector used as the basic component
in applications of natural language processing. Given a large collection of unannotated …

As one of the major sources in speech variability, accents have posed a grand challenge to
the robustness of speech recognition systems. In this paper, our goal is to build a unified end …

Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are
simpler to train, and more efficient to decode with, than sub-word systems. However, A2W …

Acoustic word embeddings are fixed-dimensional representations of variable-length speech
segments. In settings where unlabelled speech is the only available resource, such …