Noise Robust ASR Research Studentship

Cambridge University Engineering Department Speech Research Group is able to offer a well-funded three year PhD research studentship in Noise Robust Automatic Speech Recognition associated with a new grant from the Speech Technology Group at Toshiba Research Europe Limited. The aim of the project is to develop techniques that significantly improve the accuracy of automatic speech recognition systems in the presence of background noise. The schemes developed should be flexible, being able to handle a wide range of vocabulary sizes and operate at various computation loads.

The work will use the existing medium and large vocabulary recognition systems developed at Cambridge based on the publicly available HTK toolkit. This studentship gives an opportunity for study towards a PhD while working in a research group which has a world-leading reputation in speech recognition research. There are excellent opportunities for publication and travel to international conferences. The group has outstanding research facilities.

Candidates must have a very good first degree in a relevant discipline and a Masters degree (or equivalent) is an advantage. Since the project will use and extend the HTK large vocabulary speech recognition system, familiarity with the HTK toolkit and a good knowledge of C is a distinct advantage.

The research studentship is available from October 2003. The studentship will cover fees and a maintenance allowance in excess of current EPSRC awards from the UK Government. For non-EU candidates, the studentship will also cover all overseas fees. Interested candidates should contact Mark Gales (mjfg@eng.cam.ac.uk) for further details.