Multisource Decoding Overview  | Programme  | Contacts

Multisource decoding for speech in the presence of other sound sources


This project is concerned with generalising Automatic Speech Recognition decoding algorithms for natural listening conditions, where multiple sound sources are present. The processes used group together acoustic evidence likely to arise from a single source without deciding the identity of the source.


Overview of the Multisource Decoding project

Work Programme

Contact Details



These pages are maintained by Sue Harding: s.harding@dcs.shef.ac.uk
Last modified: Fri Jan 08 2004