[Elsnet-list] Research Associate in Noise Robust/Environment Aware Speech Recognition

M. J. F. Gales mjfg at eng.cam.ac.uk
Fri Sep 7 13:17:24 CEST 2007

Research Associate in Noise Robust/Environment Aware Speech Recognition

Cambridge University Engineering Department

A position exists for a Research Associate to work on Environment Aware 
Speech Processing. The project is funded by Toshiba Research Europe Ltd, 
Cambridge Research Laboratory. The aim of the project is to develop 
approaches that
allow Automatic Speech Recognition systems to rapidly respond to 
changing acoustic conditions, while maintaining high levels of 
recognition accuracy. The schemes developed should be flexible, in that 
they are applicable to a wide range of tasks, for example small 
vocabulary to large vocabulary systems. At the same time the 
computational load associated with
the techniques should be tunable depending on the nature of the 
environment and the available resources. The project will initially 
build on the current research work on Joint Uncertainty Decoding which 
has been successfully
applied to a range of noisy speech tasks. This work will be extended to 
allow rapid tracking and adaptation to changes in the environment. In 
addition there is the opportunity to develop novel schemes for improving 
robustness to
changes in the acoustic environment. For further details see:


This is an opportunity to work in a research group which has a 
world-leading reputation in many aspects of speech recognition including 
noise robust speech recognition, speaker adaptation and state-of-the-art 
large vocabulary systems. There are excellent opportunities for 
publications, travel and conference visits. The group has outstanding 
research facilities. For suitably
qualified candidates there may also be the chance to contribute to 
project supervision on the MPhil in Computer Speech, Text and Internet 


Candidates must have a very good first degree in a relevant discipline 
and preferably have a higher degree. Since the project will use and 
extend the HTK toolkit (http://htk.eng.cam.ac.uk), a good knowledge of C 
or C++ is required. In addition, experience in one or more of the 
following technical areas is a distinct advantage: - speech recognition 
with the HTK toolkit; -
noise robust speech recognition; - speaker adaptation; - machine 
learning and statistical pattern processing techniques.

The project starts on 1 January 2008 and has a three year duration. 
Salary on appointment will be in the range from £25,134 to £32,796

Further details and an application form may be obtained from Dr Mark 
Gales, Department of Engineering, Trumpington Street, Cambridge, CB2 
1PZ, (Tel +44 (0)1223 332733, Fax +44 (0)1223 332662, email 
mjfg at eng.cam.ac.uk), to whom a letter of application and a CV should be 
sent so as to reach him not laterthan 17th September 2007.

Mark Gales, Reader in Information Eng.  Tel: (+44) 1223 332733
Cambridge University Engineering Dept.  Fax: (+44) 1223 332662
Trumpington Street, Cambridge, CB2 1PZ. Email: mjfg at eng.cam.ac.uk

More information about the Elsnet-list mailing list