PhD Research

My PhD research focusses on the use of auditory models for automatic speech recognition and sound classification. The Auditory Image Model (AIM) is used as the base platform for the testing of new algorithms and approaches to:

• Compressive filtering
• Event-detection
• Feature extraction

Software Development

• Developer of AIM-C, a version of the Auditory Image Model written in C++ and designed for realtime processing.
• Current maintainer of AIM2006, an implementation of the Auditory Image Model in MATLAB.

Education

MA(Cantab.), MSci Natural Sciences, Christ's College, University of Cambridge

Part IA 50% Computer Science with Physics and Mathematics
Part IB Advanced Physics and Mathematics
Part II Experimental and Theoretical Physics
Part III Experimental and Theoretical Physics