12 Mar
2009
12 Mar
'09
12:18 p.m.
Chris Cannam wrote:
On Wed, Mar 11, 2009 at 4:15 PM, Olivier Guilyardi
<list(a)samalyse.com> wrote:
That's a very interesting idea.
Plus, before removal, visual/auditive review of
the detected noises (in some
sort of audio editor) sounds quite important: there's alway a risk to confuse a
noise with the end of a phrase or an other element of speech. So I might need to
craft a little gui, or manage to integrate this detection into rezound, ardour,
etc..
I'm not sure I have any useful thoughts about the actual detection
method, but I notice your screenshots use SV. If you could make a
Vamp plugin (turning, say, frequency-domain input into output features
with duration that identify the noisy regions), you would then be able
to review the results in either SV or Audacity.
And although you can't edit the audio in SV, by chance I'm just
planning to make a little command-line program to split audio files
according to the feature locations returned by Vamp plugins run on
them, which might help to provide one of the missing pieces.
I don't think splitting would do the job. Any chance that the noise regions
reported by the vamp plugin could turn into selected regions in Audacity? So
that one can edit them, for example to ignore a false positive, before silencing
all remaining regions at once?
What about vamp and ardour? Any other hosts for vamp plugins?
--
Olivier