[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Subtracting regularly repeating sounds

Hi all,

Our lab has been doing work on separating complex (and simple) repeating patterns from non-repeating audio (e.g. drum riff separated from person talking).  We have source code, published articles and audio examples available here:


We're also giving a tutorial along with Josh McDermott  on what we've been doing at the upcoming ISMIR conference called "Leveraging Repetition to Parse the Auditory Scene" http://ismir2012.ismir.net/event/tutorials

Bryan Pardo
Associate Professor
Electrical Engineering and Computer Science
Northwestern University

-----Original Message-----
From: AUDITORY - Research in Auditory Perception [mailto:AUDITORY@xxxxxxxxxxxxxxx] On Behalf Of Dan Stowell
Sent: Thursday, September 20, 2012 4:44 AM
To: AUDITORY@xxxxxxxxxxxxxxx
Subject: Re: [AUDITORY] Subtracting regularly repeating sounds


The task reminds me of some work done by colleagues of mine, separating the components heart sound signals from stethoscope recordings. In their case they wanted to keep the repeating part rather than suppress it, but the basic characteristics of the sound - regular but slowly varying - are a good match.

M. G. Jafari, F. L. Hedayioglu, M. T. Coimbra and M. D. Plumbley. Blind source separation of periodic sources from sequentially recorded instantaneous mixtures. In Proc 7th International Symposium on Image and Signal Processing and Analysis (ISPA 2011), Dubrovnik, Croatia, 4-6 Sept. 2011, pp 540-545, 2011.

F. L. Hedayioglu, M. G. Jafari, S. S. Mattos, M. D. Plumbley, M. T. 
Coimbra. Separating sources from sequentially acquired mixtures of heart signals. In Proc IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011), Prague, pp 653-656, May 22-27, 2011. 


On 19/09/12 21:59, Kyle Jasmin wrote:
> Dear all,
> I wonder if anyone has successfully removed the sound of a helium pump 
> from auditory recordings made in an MRI scanner. It occurs regularly 
> (every 1s), and changes over time (Praat thinks it is a formant with 
> downward trajectory). Any advice is appreciated on subtracting 
> regularly repeating sounds would be appreciated.
> With thanks,
> Kyle Jasmin
> Speech Communication Laboratory, UCL Institute of Cognitive 
> Neuroscience & Laboratory of Brain and Cognition, National Institute 
> of Mental Health

Dan Stowell
Postdoctoral Research Assistant
Centre for Digital Music
Queen Mary, University of London
Mile End Road, London E1 4NS