Connectionists: IJCNN 2015: Special Session on Sound and speech interpretation in real environments

[Prof Leslie Smith]

IJCNN 2015: Special Session: Sound and speech interpretation in real
environments
http://www.cs.stir.ac.uk/~lss/IJCNN2015SessionProposal.html

Killarney, Eire (Ireland), 12-17 July 2015.

Scope & Motivation:
Sounds in real environments arise from many concurrent sound sources, with
reverberation induced smearing changing their spectrotemporal content.
Eventually, sound (including speech) arrives at the ear or at the
microphone as a time-varying signal, with the components of interest being
between about 20 and 15,000 Hz. This is, of course, a mix of all the sound
sources, all smeared by multiple reflections. How this signal should be
processed to provide input to an interpreting system (which presumably
would prefer to interpret only the signal of interest) is very much a
matter of debate, particularly between those who use traditional MFCC
techniques, and those who prefer something more neurally inspired, like a
set of spike trains, and perhaps feature detectors as well. How should the
sounds from a particular source of interest be segregated? How should
interpretation be made invariant under listening conditions? Whatever
techniques are used, the result is a time series of some type, and there
are many neural techniques of possible interest for different aspects of
this problem, from deep neural networks to learning-based spiking neural
systems.
This session builds on the IJCNN Special Session in 2011, organised by the
late Harry Erwin.

Topics
Sound preprocessing for interpretation: creating suitable spectrotemporal
representations for interpretation.
Making spectrotemporal representations invariant under listening conditions;
Interpretation techniques: what type of network might be used: e.g. purely
trained, or using self-organisation as well. Can the network help with
listening condition invariance?
Implementation techniques: how to aim for real-time sound and speech
interpretation for computer and robotic systems: hardware and
hardware/software approaches.
Auditory scene analysis using neural networks: separating out streams of
sound in multi-source reverberant environments.

Dates and submission
Paper submission:	January 15th, 2015
Paper Decision notification:	March 15th, 2015
Camera-ready submission:	April 15th, 2015
Conference Dates:	July 12 - 17th, 2015

For further information contact Leslie Smith (l.s.smith at cs.stir.ac.uk) or
Shih-Chii Liu (shih at ini.phys.ethz.ch)

-- 
Prof Leslie Smith
Computing Science and Mathematics
University of Stirling, Stirling FK9 4LA
Scotland, UK.
Tel (44) 1786 467435

-- 
The University of Stirling has been ranked in the top 12 of UK universities for graduate employment*.
94% of our 2012 graduates were in work and/or further study within six months of graduation.
*The Telegraph
The University of Stirling is a charity registered in Scotland, number SC 011159.