Edinburgh Research Explorer

Prof Steve Renals

Chair of Speech Technology

Profile photo

Willingness to take Ph.D. students: Yes

Research Interests

My research is about the development of interactive systems that can understand human communication. A lot of this work is grounded in speech recognition, and is based on building and applying statistical models to interpret communication signals. The Natural Speech Technology programme grant is concerned with core work in speech recognition and speech synthesis.

Speech to text transcription is a highly challenging task in itself, but ultimately we want to understand human communication, rather than only transcribing the words. Along these lines, we have done work concerned with interpreting and accessing information from speech, and multimodal interaction. For more than a decade now, a lot of our work has focussed on the recognition and interpretation of multiparty meetings, as part of the M4, AMI, AMIDA, and InEvent projects.

Qualifications

1991Doctor of Philosophy, PhD, University of Edinburgh
 Speech recognition and neural network dynamics
1987Master of Science, University of Edinburgh
 A connectionist approach to speech recognition
1986Bachelor of Science, 1st, University of Sheffield

Biography

Steve Renals is professor of Speech Technology in the School of Informatics, at the University of Edinburgh.  He received a BSc in Chemistry from the University of Sheffield in 1986, an MSc in Artificial Intelligence from the University of Edinburgh in 1987, and a PhD in Speech Recognition and Neural Networks, also from Edinburgh, in 1990. From 1991-92 he was a postdoctoral fellow at the International Computer Science Institute (ICSI), Berkeley, and was then an EPSRC postdoctoral fellow in Information Engineering at the University of Cambridge (1992-94). From 1994-2003 he was lecturer, then reader, in Computer Science at the University of Sheffield, moving to Edinburgh in 2003.

He has over 250 publications in speech and language processing, and has led several large projects in the field, including the EU project SUMMA, the EPSRC Programme Grant Natural Speech Technology and the AMI and AMIDA Integrated Projects.  He is a fellow of the IEEE, and a fellow of ISCA.

Research Groups

Centre for Speech Technology Research, http://www.cstr.ed.ac.uk

Research outputs

  1. End-to-end neural segmental models for speech recognition

    Research output: Contribution to journalArticle

  2. Simplifying very deep convolutional neural network architectures for robust speech recognition

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  3. Hierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

View all (197) »

Research activities & awards

  1. Fellow of the IEEE

    Activity: Awards and AccoladesElection to learned society

  2. Neural Networks for Distant Speech Recognition

    Activity: External academic engagementInvited talk

  3. ISCA Fellow

    Activity: Awards and AccoladesElection to learned society

View all (5) »

ID: 18623