1 code implementation • 3 Feb 2023 • Nathan Roll, Calbert Graham, Simon Todd
Self-attention mechanisms have enabled transformers to achieve superhuman-level performance on many speech-to-text (STT) tasks, yet the challenge of automatic prosodic segmentation has remained unsolved.
no code implementations • COLING 2016 • Russell Moore, Andrew Caines, Calbert Graham, Paula Buttery
In order to apply computational linguistic analyses and pass information to downstream applications, transcriptions of speech obtained via automatic speech recognition (ASR) need to be divided into smaller meaningful units, in a task we refer to as {`}speech-unit (SU) delimitation{'}.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • LREC 2016 • Andrew Caines, Christian Bentz, Calbert Graham, Tim Polzehl, Paula Buttery
We announce the release of the CROWDED CORPUS: a pair of speech corpora collected via crowdsourcing, containing a native speaker corpus of English (CROWDED{\_}ENGLISH), and a corpus of German/English bilinguals (CROWDED{\_}BILINGUAL).