Subject: PhD studentship at Stirling University (Scotland) From: Leslie Smith <l.s.smith@xxxxxxxx> Date: Tue, 16 Sep 2008 09:03:53 +0100 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>
Dear all: Bio-inspired Feature Detection for Sound Streaming and Interpretation This Department has set aside funds to fund a 3 year PhD studentship (UK/EC students only) starting as soon as possible. This project aims to develop biologically inspired techniques for the detection of spectro-temporal features in sound which may be used (i) for separating foreground sound streams from background sound streams and (ii) for the interpretation of the foreground sound streams. Most current work is speech recognition based, and assumes (incorrectly) that the speech is the only signal present. In recent years there has been work on Computer Audio Scene Analysis (CASA), which attempts to separate the sound into a number of sound streams, each from a different sound source. This normally starts off by band pass filtering the sound into multiple channels, using a biologically inspired filter bank, unlike the Fourier-transform approach taken in earlier speech recognition systems. We have followed this approach, and extended it by using an (auditory nerve like) spike-based coding approach which provides precise timing and can cope with the very wide dynamic range of sound signals, and have already used onset features detected for sound source direction finding and some basic interpretation [1, 2]. Recently, we have extended the types of (proto-) feature that can be discovered by using a two dimensional spectro-temporal window operator, implemented as a set synapses (whose weights and delays encode these window operators) from the spike-coded signal to a leaky integrate and fire neuron. This approach appears promising, since proto-feature detection can be made signal level independent, and proto-features which are invariant under the usual variation in listening environments can be chosen. Further, this approach can use greedy (parallel) processing, taking advantage of modern CPUs and signal processing technologies. The research will assess proto-features and combinations of these features which are useful in foreground/background sound signal separation, and which are useful in sound (including, but not only) speech. The techniques will recode the sound as a set of sequences of proto-features (and features combined from these proto-features), and these sequences will be interpreted, and the mapping from proto-features to features adapted (for example, using neural net technologies). The Department has a lab which can be used for multi-stream sound acquisition. It also enables the reverberance of the environment to be varied. Further details: see http://www.cs.stir.ac.uk/~lss/research/proposedproject2008.html --Leslie Smith Professor Leslie S. Smith, Head, Dept of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA, Scotland l.s.smith@xxxxxxxx Tel (44) 1786 467435 Fax (44) 1786 464551 www http://www.cs.stir.ac.uk/~lss/ -- Academic Excellence at the Heart of Scotland. The University of Stirling is a charity registered in Scotland, number SC 011159.