Centre for Speech Technology Research
University of Edinburgh
Research Fellow in Speech Synthesis
The Centre for Speech Technology Research at the University of
Edinburgh is seeking a research fellow to work on the speech synthesis
project "Automatically-determined inventories for speech
synthesis". This project uses machine learning techniques to
automatically discover, from speech data, a set of units for speech
synthesis - that is, an alternative to manually-specified
phoneme-based units such as diphones. This research is currently being
conducted within a concatenative (i.e. unit selection) framework, but
we now seek to extend this to the other major synthesis technique:
statistical parametric synthesis, based on Hidden Markov Models (i.e.,
trajectory HMMs). The successful candidate will be expected to
contribute, plan and execute new research, as well as extend our
existing techniques.
You ideally will have a PhD in speech synthesis and experience of
trajectory Hidden Markov Models. You will have very good programming
skills, preferably in C++, and experience with one or more of:
concatenative speech synthesis techniques; statistical models of
speech; perceptual evaluations; Festival. An automatic speech
recognition background is also appropriate for this position. This
post is fixed term for 15 months.
For more information and application instructions:
vacancy number 3006866
This archive was generated by hypermail 2b29 : Tue Jan 16 2007 - 15:09:42 MET