Welcome to my research pages. I am a PhD student studying in the Centre for Doctoral Training in Speech and Language Technologies at the University of Sheffield. My supervisor is Prof. Thomas Hain. The title of my PhD project is "Meeting Transcription for Highly Reverberant Environments". Please see the links below to find out more.About Research Contacts
The unifying theme of my academic background is in the statistical modelling of time-varying signals. I have an MEng degree in Electronic Engineering with Music Technology Systems from the University of York. During this course I focused heavily on signal processing techniques for speech and audio. My dissertation researched auto-regressive modelling for audio restoration where damaged signal segments were completely unrecoverable. Following this I gained an MSc in Mathematical Finance from the University of York. I gained a lot of knowledge around stochastic processes and statistical modelling from this course. It was also where I first gained exposure to machine learning and artificial intelligence techniques. For my dissertation I researched least squares Monte-Carlo estimation techniques for option pricing. In my current research I hope to unify my knowledge of statistical modelling and signal processing for speech processing applications.
My research interest primarily revolve around speech processing in difficult acoustic environments. In particular I am interested in:
Other affiliations: The Department of Computer Science, Machine Intelligence for Natural Interfaces (MINI)
My current research is focused on meeting transcription technology for highly reverberant environments. A particular area of interest for this research is in clinical applications of this for doctor patient conversations. This project is being part funded by partners at 3M.