Leading or member of several research groups in the University of Sheffield - Speech and Hearing Research, the , Machine Intelligence for Natural Interfaces , the Machine Learning research group, and the Voicebase Centre for Speech and Language Technologies. I am also associated with the Nagoya Institute of Technology.
Almost 25 years experience in machine learning oriented research to speech, language, audio, hearing, visual and mutli-modal technology, in industry and at university. (Co-)author of more than 150 peer reviewed papers and several patents.
Participating in the community with various acitivities, as elected member of the IEEE Speech technical committee, Asossciate Editor Computer Speech & Language, as member of the EPSRC Review College and others. More details are here.
- machine learning
sequence modelling, adapation, multi-task learning, represenation learning, deep learning reinforcement learning
- speech recognition
media, interviews, far field, conversational, found speech
- speech analysis
language, speaker, emotion
- learning systems
articulation, pronunciation, fluency
- making us of speech processing integration with downstream processes, e.g. machine translation, summarisation, analytics
- man-machine conversation
- multi-agent systems
distribution of learning and processing
- big sensor networks
multi-modality and crose mode integration
- complex software system optimsation
meta organisation and structuring
Links to pages relating to publications, or other home pages can be found in the footer of this page.