Research Associate in Speech Signal Processing
Mathematics and Statistics,Statistics,Computer Science,Computer Science,Languages, Literature and Culture,Linguistics
Short info about job
Company: University of Sheffield
Department: Faculty of Engineering - Department of Computer Science
Salary: £30,688 per annum, Grade 7
Hours: Full Time
Contract type: Fixed-Term/Contract
Type / Role: Academic or Research
Phone: +44-1386 1880279
Fax: +44-1304 1237304
E-mail: N\A
Site: N\A
Detail information about job Research Associate in Speech Signal Processing. Terms and conditions vacancy
Contract Type: Fixed-term for a period of 12 months
Summary:
Applications are invited for a Research Associate on a Google Research Award-funded project, DeepArt, which is developing novel deep-learning techniques for the recognition of dysarthric speech. The project is running alongside a European Initial Training Network, TAPAS, involving 12 partners across Europe and aimed at investigating the broader issues of pathological speech.
The DeepArt project targets dysarthria, a particular form of disordered speech arising from poor motor-control and a resulting lack of coordination of the articulatory system. At Sheffield, we have demonstrated that using state-of-the-art training techniques developed for mainstream HMM/DNN speech recognition, can raise baseline performance for dysarthric speech recognition. However, it is clear that to make truly usable systems for moderate to severely impacted speakers, speech models have to be tailored to the individual in ways that lie outside the scope of normal speaker adaptation. DeepArt will develop new adaptation approaches that leverage articulatory-based representations, articulartory synthesis for training data simulation and DNN-based speaker adaptive training.
This post offers excellent opportunities for publications, project and conference trips. For suitably qualified candidates, possibilities exist to contribute to teaching, for example as part of an MSc in Computer Science with Speech and Language Processing. Candidates must have a PhD or equivalent work experience and a strong publication record. Candidates will be expected to have a solid knowledge of speech processing and statistical modelling, as well as excellent programming skills. Candidates are expected to work well in research teams and contribute to research and advancement of the Speech and Hearing research group.