I came to Edinburgh after completing the MPhil in Computer Speech, Text and Internet Technology at Cambridge University, where I took my first degree, in Mathematics, a few years earlier.
My primary speech recognition research is conducted within the EPSRC-funded, Natural Speech Technology project, a five-year programme grant held jointly with the University of Cambridge and University of Sheffield. Our aim is to significantly advance the state-of-the-art in speech technology. I am particularly involved in the themes of structuring diverse data and generating systems with wide domain coverage, for example, through the use of adaptive neural network features. One of our primary tasks has been dealing with highly diverse broadcast data from the BBC (See my publications for more details.) I am an organiser of the MGB challenge for ASRU 2015.
I am a firm believer in the commercial value of speech technology, and passionate about bringing cutting-edge advances in the research sphere to commercial benefit as rapidly as possible. Notably in this area I have worked as a consultant for France Telecom's R&D labs in London, advising on the adoption of new technologies in speech recognition and synthesis, work which lead to a Knowlege Transfer Partnership funded by the UK government's Technology Strategy Board. I also provide consultancy services to startup companies requiring speech technology expertise.
I also have a role as Senior Speech Recognition Scientist at Quorate Technology Ltd, a recent spin-out from the University of Edinburgh.
I worked on a project to integrating speech recognition capability into the Beetle system for tutoring in basic electronics, funded by the Office for Naval Research. This domain is an interesting one for speech recognition: since research has shown that learning achievement is highly correlated with the amount of contentful speech from the learner, the system must be designed to elict, and recognise, unstructured, large vocabulary speech, in contrast to typical spoken dialogue systems where small, prescribed grammars are often used. However, the task is different to other large vocabulary recognition tasks in that there exist tight semantic constraints.
I have been working to create the first speech recogniser for Scottish Gaelic, funded by iDEA lab. The scarcity of resources for this language makes the task challenging, and is a good testing ground for recent advances in cross-lingual speech recognition. More recently, I have worked on this task in collaboration with Ramya Rasipuram and Mathew Magimai-Doss at IDIAP.
In Edinburgh, we have collected a 6-hour corpus of spoken gaelic from BBC Radio nan Gàidheal's Aithris na Maidne, fully transcribed at utterance level to modern digital standards. The corpus is available to interested researchers on request.
For my PhD thesis I investigated the use of full covariance gaussian models for speech recognition. Full covariance models have hugely increased modelling power compared to the standard diagonal covariance model, but suffer from a number of deficiences when the quantity of training data is limited. The problem is essentially one of generalisation. I investigated two solutions: imposing sparse Gaussian Graphical Model structure on the covariance matrices by using l1-norm penalised likelihood maximisation; and by the use of a "shrinkage estimator".My PhD supervisor was Prof. Simon King.
For my master's thesis, I investigated methods for adapting prosodic phrasing models, supervised by Tina Burrows (then Toshiba Research Cambridge) and Paul Taylor (then Cambridge University Engineering Department).
I am a keen hillwalker, and especially enjoy walking in the Scottish Highlands. I previously enjoyed climbing new Munros with the Edinburgh University Hillwalking Club; I've climbed them all now, so am gradually working my way through the list of Corbetts, hills in the range 2,500-3,000ft.