Subject: On separating complex repeating patterns from recordings ... [from AUDITORY] From: Kevin Austin <kevin.austin@xxxxxxxx> Date: Thu, 20 Sep 2012 22:40:08 -0400 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>Begin forwarded message: > From: "garth@xxxxxxxx" <garth@xxxxxxxx> > Subject: [*electroacoustics*] Re: [cec-c] On separating complex repeating patterns from recordings ... [from AUDITORY] > Date: 2012 September 20 8:27:57 PM EDT > To: cec-conference@xxxxxxxx > Cc: ACMA <acma-l@xxxxxxxx>, electroacoustics@xxxxxxxx > Reply-To: electroacoustics@xxxxxxxx > > Izotope RX > http://www.izotope.com/products/audio/rx/ > > --- > Cheers > > Garth > Garth.Paine@xxxxxxxx > http://www.activatedspace.com > > > On Sep 20, 2012, at 1:59 PM, Kevin Austin wrote: > >> >> 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 >>> http://www.elec.qmul.ac.uk/digitalmusic/people/dans.htm >>> http://www.mcld.co.uk/ >> >> >> >> Dear Kyle, >> >> I dont have experience with MRI scanner sounds in particular, but it seems like such a structured interfering source should be a good match for the exemplar-based source separation techniques I have been using over the past few years. You can find more information on my website, www.amadana.nl , as well as a demo (matlab) and some links to related techniques that may be of use. >> >> Feel free to contact me directly if you think this can be of use, then we can give it a try. >> >> Jort Gemmeke >> Postdoctoral Researcher >> KU Leuven, ESAT-PSI Speech group >> www.amadana.nl >> >> >> >>> -----Original Message----- >>> From: AUDITORY - Research in Auditory Perception [mailto:AUDITORY@xxxxxxxx On Behalf Of Dan Stowell >>> Sent: Thursday, September 20, 2012 4:44 AM >>> To: AUDITORY@xxxxxxxx >>> Subject: Re: [AUDITORY] Subtracting regularly repeating sounds >>> >>> Kyle, >>> >>> 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. >>> http://dx.doi.org/10.1109/ICASSP.2011.5946488 >>> >>> Best >>> Dan >> >> >>> From: Bryan A Pardo <pardo@xxxxxxxx> >>> Subject: Re: [AUDITORY] Subtracting regularly repeating sounds >>> Date: 2012 September 20 12:27:42 PM EDT >>> To: AUDITORY@xxxxxxxx >>> Reply-To: Bryan A Pardo <pardo@xxxxxxxx> >>> >>> 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: >>> >>> http://music.cs.northwestern.edu/research.php?project=repet >>> >>> 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 >>> >> >> Dear all >> >> I've tried Bryan's repeated pattern extraction technique -- it worked pretty well, although it removed some of the speech. If you're curious about the results, the input and output files are here. https://www.dropbox.com/sh/nrj4j7mmefhf36w/WBrN8KmlhS >> >> Next I'll try Jort's approach. Thanks for the advice. >> >> Best >> Kyle >> >> >> >> The exemplar work looks like a good approach, as Jort has provided Matlab code, I would imagine that it could be readily tested for your particular case. >> >> Another approach to think about, if you have a section of isolated noise in your audio recording, is the pioneering work by Ephraim & Malah. >> They produced the statistical method of spectral noise estimation and removal ... the trick in your case would be to make sure that you are using an analysis window which is long enough to be able to capture the low frequency components of your noise source. >> >> You can find a SPDemo application in the downloads section on their web page : >> http://sipl.technion.ac.il/ >> >> Matt >> >> >> >> -- >> You received this message because you are subscribed to the "CEC-Conference" group. >> To post: cec-conference@xxxxxxxx >> To unsubscribe: cec-conference+unsubscribe@xxxxxxxx >> More options: https://groups.google.com/forum/#!forum/cec-conference >> CEC website: http://cec.sonus.ca >