PhD position available on automatic speaker recognition

[Stefan Bleeck <bleeck@xxxxxxxxx>]

4 year fully funded (£15K p.a.) PhD position is available at the ISVR
in Southampton, UK

“My voice is my passport”. This technique serves as person
identification method in Hollywood since 1992 (‘Sneakers’). In the
real world, things are not so simple and even the best commercial and
research systems have intolerable error rates. In this PhD, your task
is to use bio-inspired signal processing methods based on latest brain
research to overcome this barrier. We are not after incremental
improvement of existing technology, but aim to utilize fundamentally
novel bio-inspired algorithms using knowledge of human auditory and
music processing to create a step change for future technologies.
In your PhD, you will generate sparse representation of individual
speaker features that are based on our human auditory perception model
(www.acousticscale.org). You will also design algorithms that can
identify speakers in the real world using  recordings from speaker
databases. The goal of this project is to develop a stand-alone
demonstrator that is error tolerant in challenging environment and
will form the basis of a commercial product. We are looking for a
highly motivated EU student with a solid background in signal
processing and at least one of the following: physics, electrical
engineering, acoustics, hearing research, computer science or
complexity science.
You will working for 4 years in the world leading Institute of Sound
and Vibration Research with unique interdisciplinary expertise in
acoustical engineering, audiology and signal processing, the perfect
setting for this challenging project (www.isvr.soton.ac.uk).

If you wish to discuss any details of the project informally, please contact me!
-- 
Dr. Stefan Bleeck
Institute of Sound and Vibration Research
Faculty of Engineering & the Environment
University of Southampton, SO17 1BJ, UK
Room 4093, Tizard building (13)
bleeck@xxxxxxxxx Tel.: 02380 596682