Several useful ideas that are worth trying. My goal is to classify
Indian music into notated streams from audio samples. As I progress down
this path, I will publish my results to further research in this field.
________________________________________________
From:"Risto Holopainen" <ebel...@ristoid.net>
Sent:"A discussion list for music-related DSP"
<music-dsp@music.columbia.edu>
Date:Sat, July 12, 2014 6:39 pm
Subject:Re: [music-dsp] Frequency based analysis alternatives ?
>
> Adaptive models with frames or overcomplete representations might
be
> interesting. Then you can decompose the signal with a broader class
of
> basis functions, such as symmetrically windowed sinusoids, chirps,
> exponentially decaying sinusoids and whatever. The point is to have
a
> sparse representation of the signal by a small number of components
that
> describes it well. There is a book by Michael Goodwin and several
papers
> by Bob Sturm and others on this.
>
> I've also seen that some people have tried empirical mode
decomposition on
> audio signals. Seems to be worthwile looking into that too.
>
> Risto Holopainen
>
>
>
> 10 juli 2014, Rohit Agarwal <ro...@khitchdee.com> skrev:
>>
>>
>>
>> If I was to model music in general, it would be a sequence of 2
type
>> segments, non-stationary transitions would be the first and
quasi
>> stationary tones the second type. This would get more involved
with more
>> instruments, but for just one sound source this would work quite
well.
>> Assuming we had a good classifier that detected the type and
extent of
>> segs, we could then use chirplets on the transitions and the old
FFT for
>> the tonal segs. Hopefully the chirplets would help classify
the
>> different
>> type transitions for a sound source, based on their properties in
the
>> transform space.
>>
>
> --
> dupswapdrop -- the music-dsp mailing list and website:
> subscription info, FAQ, source code archive, list archive, book
reviews,
> dsp links
> http://music.columbia.edu/cmc/music-dsp
> http://music.columbia.edu/mailman/listinfo/music-dsp
>
--
dupswapdrop -- the music-dsp mailing list and website:
subscription info, FAQ, source code archive, list archive, book reviews, dsp
links
http://music.columbia.edu/cmc/music-dsp
http://music.columbia.edu/mailman/listinfo/music-dsp
