Re: [AUDITORY] review of harmonic+noise segmentation software

[Kevin Austin <kevin.austin@xxxxxxxxxxxx>]

Hi

I read the request two ways, and one would be called 'segmentation', as for example the segmenting of the audio stream /t/ /I/ into a noise component followed by a 'tonal' component = speech segmentation https://en.wikipedia.org/wiki/Speech_segmentation. I understood this request from this point of view because of the interest to do more than monophonic segmentation.

If the term were to be used in the [ASA] sense of segregation / decomposition -- the extraction of spectral or / and  frequency components, such as the noise and the tonal components of /z/, I am not quite sure what would be meant by 'more than monophonic'. Would this be initially stream segregation in conjunction with spectral analysis?

Kevin



On 2013, Oct 1, at 6:44 AM, Esteban Maestre <esteban.maestre@xxxxxxx> wrote:

> Hi Matt,
> 
> I'm not sure whether I understand what you refer to as 'segmentation'.
> If you mean 'decomposition', you might want to check out some recent tools developed around the work of Serra and Smith:
> 
> http://mtg.upf.edu/technologies/sms
> 
> Cheers,
> Esteban
> 
> On 9/30/2013 1:48 PM, Matt Flax wrote:
>> Hi there,
>> 
>> Back about 10 or 15 years I remember that some people on this list were researching the segmentation of sound into tonal components and noise components.
>> 
>> I was wondering whether anyone on the list has used any free software libraries which come from this research to do this and if so whether you could let the list know ?
>> 
>> I am intersted in software which can do more then monophonic segmentation ... if possible.
>> 
>> thanks
>> Matt
> 
> 
> -- 
> 
> 
> Esteban Maestre
> MTG - Universitat Pompeu Fabra
> http://ccrma.stanford.edu/~esteban