In recent years large transformer model architectures have become available which provide
a novel means of generating high-quality vector representations of speech audio. These …

Abstract Domain-informed probing of large speech recognition transformer-based models
offers an opportunity to investigate how phonetic information is captured and transformed in …

While the deep learning revolution has led to significant performance improvements in
speech recognition, accented speech remains a challenge. Current approaches to this …

Non-lexical items are expressive devices used in conversations that are not words but are
nevertheless meaningful. These items play crucial roles, such as signaling turn-taking or …

Automatic Speech Recognition (ASR) systems exhibit the best performance on speech that
is similar to that on which it was trained. As such, underrepresented varieties including …

A child who is unfamiliar with the correct spelling of a word often employs a “sound it out”
approach: breaking the word down into its constituent sounds and then choosing letters to …

S-capade (s pelling c orrection a imed at pa rticularly d eviant e rrors) is a phonemic
distance based spellchecking tool (Source code repository may be found in the references …

Extensively used in commercial products, automatic speech recognition (ASR) systems,
which process human speech into sequences of characters, are now part of many human …

S-capade (spelling correction aimed at particularly deviant errors) is a phonemic distance
based spellchecking tool (Source code repository may be found in the references section …