We use a combo of modified mfcc and k-means at Mogees to get
over 95% accuracy of percussion sounds.
To add a few words to what Jamie says, on what I've learned
about working in this domain;
1) It really helps to understand your problem and the possible
ways it can be assisted by ML. Is real-time
thanks miller and school shoes,
my problem was grasping the „initial delay“ concept: its not adding one after
the other but always refering to timepoint 0.
(my long years of working with max/msp hit me once again. in max/msp´s line~
times are cumulatively added, one after another.)
the flossman
Excellent suggestion, thanks.
Miller
On Sun, Jul 24, 2016 at 11:14:51AM +0200, hans w. koch wrote:
> thanks miller and school shoes,
>
> my problem was grasping the „initial delay“ concept: its not adding one after
> the other but always refering to timepoint 0.
> (my long years of working with
Hi Jamie
I'd like to submit a paper for this, but it's doubtful that I can afford to
come to New York in November. Will you be giving selected authors the chance to
present online rather than in person?
From: Jaime Oliver
Sent: 21 July 2016 08:13
To: Pd-list
Subject: [PD] PdCon16 NYC Calls