Funded Research Projects
Currently these projects are active (in alphabetical order):
Previous projects include the following:
- REDRESS: Recognition and Reconstruction of Speech following
Laryngectomy
Phil Green, Roger Moore and Robin Hofe
- SPECS:
Speech-driven Electronic Control Systems
Phil Green and Roger Moore
- SERA: Social Engagement with
Robots and Agents
Roger Moore and Viktoria Maier
- S2S: Sound-to-Sense
Roger Moore and Guy Brown
- Phonetic
design of overlapping speech in talk-in-interaction: A
cross-linguistic study
Guy Brown
- ACORNS:
Acquisition of Communication and Recognition Skills
Roger Moore
- AMIDA: Augmented Multi-party Interaction with Distance Access
Main project
website | Sheffield project website
Thomas Hain, Phil Green, Asmaa El Hannani, Vincent Wan and
Stuart Wrigley
- POP: Perception On Purpose
Martin Cooke, Jon Barker, Heidi Christensen and Sue Harding
- GRID audiovisual
sentence corpus
Jon Barker, Martin Cooke, Stuart Cunningham and Xu Shao
- Robust Audio Visual Speech Recognition
Jon Barker and Xu Shao
- AMI:
Augmented Multi-party Interaction
Phil Green, Thomas Hain, Guy Brown, Vincent Wan and Stuart
Wrigley
- HOARSE: Hearing Organisation And
Recognition of Speech in Europe
Phil Green
- S3L: Statistical Summarization of Spoken
Language
Yoshi Gotoh, Heidi Christensen and Sarah Simpson
- Multisource decoding for speech in
the presence of other sound sources
Phil Green, Martin Cooke, Guy Brown, Jon Barker and Sue Harding
- M4: MultiModal Meeting Manager
Guy Brown and Stuart Wrigley
- OLP:
Ortho-Logo-Paedia
Phil Green and James Carmichael
- STARDUST: Speech training and
recognition for people with severe dysarthria
Phil Green and Athanassios Hatzis
- Inter-formant Intelligibility Dips for
Narrowband Speech
Phil Green, Martin Cooke and Stuart Cunningham
- RESPITE: REcognition of Speech by Partial
Information TEchniques
Phil Green, Martin Cooke and Jon Barker
- SPHEAR
TMR NETWORK: SPeech, HEaring and Recognition
Phil Green, Guy Brown and Martin Cooke
- Speech Summarization using Prosodic
Information
Steve Renals and Costis Koumpis
- THISL: Thematic Indexing of Spoken Language
Steve Renals
- SToBS: Structured Transcription of
Broadcast Speech
Steve Renals, Rob Gaizauskas,Yoshi Gotoh and Heidi Christensen
- SPRACH: Speech Recognition Algorithms
for Connectionist Hybrids
Steve Renals
- Large Vocabulary Speech Recognition
Steve Renals
- Inference of Optimal Auditory
Representations
Steve Renals
- Binaural Cues in a Computational
Model of Auditory Scene Analysis
Guy J. Brown
- Design and Collection of a
Multiple-Source, Multiple Sensor Acoustic Corpus
Martin Cooke and Guy J. Brown and Phil Green
- Modelling the Perceptual Grouping of
Musical Sounds
Guy J. Brown
- Keele: A Pitch Extraction Reference Database
Fabrice Plante, Georg Meyer, William A Ainsworth and Phil Green
- Speech Recognition from Occluded Data
Martin Cooke and Phil Green
- Incorporating Binaural Cues in a
Computational Model of Auditory Scene Analysis
Brian L. Karlsen and Guy J. Brown