Harriet Nock

More recent information and publications can be found on my IBM web page .

I finished my PhD in the Speech, Vision and Robotics Group at Cambridge University Engineering Department in 2001. My advisor was Professor Steve Young. I spent some of my PhD at Center for Language and Speech Processing in The Johns Hopkins University, where I worked with Dr Bill Byrne and Dr Sanjeev Khudanpur, and at SSLI Lab in the University of Washington, where I worked with Professor Mari Ostendorf. I will be spending 2001-2003 at IBM Research, specifically the TJ Watson Research Center in Yorktown Heights, New York.

My thesis research looked at techniques for improving the robustness of automatic speech recognition systems to variation in speaking style, including:

explicit modelling of pronunciation change in conversational speech, using statistical techniques motivated by linear phonology;
implicit modelling of pronunciation change, through the use of a variety of directed graphical models motivated by nonlinear phonology;
articulatory and phonological representations of speech;
automatic induction of acoustic modelling units.

I also did a little work on the DARPA meeting transcription project and the SPINE noise robustness task.

A postscript list of publications can be found here. Some are available on-line from the SVR ftp site.

Email:
hjn11 AT eng.cam.ac.uk
Post:
Cambridge University Engineering Department,
Trumpington Street,
Cambridge, CB2 1PZ. UK.

Last modified: Thu Jan 16 00:19:34 GMT 2003