robert bristow-johnson <rbj@audioimagination.com> wrote:
>On Wednesday, September 21, 2016 at 11:12:02 PM UTC-4, Steve Pope wrote:
>> Unrelatedly, I notice my namesake DSP expert, Stephen Travis Pope,
>> is an MIR expert.
>> Was vaguely considering posing as said expert to the OP, but nah.
>i remember once i asked you if you was he. STP was also once the editor
>to Computer Music Journal.
Yes. We've been conflated many times. Most amusing, perhaps,
was the time U.C. Berkeley sent him my consulting contract.
Steve
Reply by robert bristow-johnson●September 22, 20162016-09-22
On Wednesday, September 21, 2016 at 11:12:02 PM UTC-4, Steve Pope wrote:
>
> Unrelatedly, I notice my namesake DSP expert, Stephen Travis Pope,
> is an MIR expert.
>
> Was vaguely considering posing as said expert to the OP, but nah.
>
i remember once i asked you if you was he. STP was also once the editor to Computer Music Journal.
r b-j
Reply by Evgeny Filatov●September 22, 20162016-09-22
On 22.09.2016 4:31, angrydude wrote:
> On Thursday, September 8, 2016 at 12:23:46 PM UTC-4, MatthewA wrote:
>> Hitting a little bit of a wall doing some sinusoid tracking and in an effort to work smarter not harder, I'd like to do some hanging out with someone experienced in MIR. Neural net knowledge a definite plus. This is a pretty fun project so hopefully it won't be too painful.
>>
>> Rates negotiable.
>>
>> Matt EstateSound Com
>
> "MIRU - MIR" (soviet communist slogan)
>
> Just don't do FFT for Christ sake...
>
>On Thursday, September 8, 2016 at 12:23:46 PM UTC-4, MatthewA wrote:
>> Hitting a little bit of a wall doing some sinusoid tracking and in an
>effort to work smarter not harder, I'd like to do some hanging out with
>someone experienced in MIR. Neural net knowledge a definite plus. This
>is a pretty fun project so hopefully it won't be too painful.
>> Rates negotiable.
>>
>> Matt EstateSound Com
>"MIRU - MIR" (soviet communist slogan)
>
>Just don't do FFT for Christ sake...
Unrelatedly, I notice my namesake DSP expert, Stephen Travis Pope,
is an MIR expert.
Was vaguely considering posing as said expert to the OP, but nah.
Steve
Reply by angrydude●September 21, 20162016-09-21
On Thursday, September 8, 2016 at 12:23:46 PM UTC-4, MatthewA wrote:
> Hitting a little bit of a wall doing some sinusoid tracking and in an effort to work smarter not harder, I'd like to do some hanging out with someone experienced in MIR. Neural net knowledge a definite plus. This is a pretty fun project so hopefully it won't be too painful.
>
> Rates negotiable.
>
> Matt EstateSound Com
"MIRU - MIR" (soviet communist slogan)
Just don't do FFT for Christ sake...
Reply by ●September 12, 20162016-09-12
I guessed if you had to ask what MIR stands for, you weren't the person he was looking for.
:-)
m
Reply by MatthewA●September 9, 20162016-09-09
On Friday, September 9, 2016 at 12:58:25 AM UTC-4, Eric Jacobsen wrote:
> On Thu, 8 Sep 2016 18:10:33 -0700 (PDT), MatthewA
> <matthewaudio@gmail.com> wrote:
>
> >> Is it music or isolated sinusoids that barely move?
> >
> >Both:
> >https://soundcloud.com/rajendra-bhagwat/rajendra-heggar-tabla-practice
> >
> >I've got it pretty good so far but I think someone who knows what they're d=
> >oing can identify these sinewaves much more accurately. I'm looking for th=
> >e first 6 overtones in the Dayan, (the higher drum). That means ignoring t=
> >he bayan (bass drum) and filtering out the onsets. As I said, I've done an=
> > Okay job already but it can be better.
>
> You mean, not isolated sinusoids that barely move. ;)
>
> As others have mentioned, not trivial. If you're doing well with it,
> kudos.
Thanks friends. Good to know I'm not banging my head against an easy one. Got a few responses.
Reply by Eric Jacobsen●September 9, 20162016-09-09
>> Is it music or isolated sinusoids that barely move?
>
>Both:
>https://soundcloud.com/rajendra-bhagwat/rajendra-heggar-tabla-practice
>
>I've got it pretty good so far but I think someone who knows what they're d=
>oing can identify these sinewaves much more accurately. I'm looking for th=
>e first 6 overtones in the Dayan, (the higher drum). That means ignoring t=
>he bayan (bass drum) and filtering out the onsets. As I said, I've done an=
> Okay job already but it can be better.
You mean, not isolated sinusoids that barely move. ;)
As others have mentioned, not trivial. If you're doing well with it,
kudos.
Reply by Tim Wescott●September 9, 20162016-09-09
On Thu, 08 Sep 2016 16:35:30 -0700, MatthewA wrote:
>> I think he means Music Information Retrieval since it appears to touch
>> on neural nets, but that's just a guess since he wasn't clear about it.
>
> Yes exactly and this task should be cake for the DSP engineers on this
> forum since these sinusoids barely move.
Eh, you mean the many, many sinusoids that are all piled on top of each
other and interspersed with just plain noise from things like percussion
instruments?
Unless you're just looking at flute solos, that is.
It doesn't sound easy to me (see, I wasn't your guy!). What's your end
goal? To write sheet music from a recording or some such?
--
Tim Wescott
Control systems, embedded software and circuit design
I'm looking for work! See my website if you're interested
http://www.wescottdesign.com
Reply by robert bristow-johnson●September 9, 20162016-09-09
On Thursday, September 8, 2016 at 7:35:33 PM UTC-4, MatthewA wrote:
> > I think he means Music Information Retrieval since it appears to touch
> > on neural nets, but that's just a guess since he wasn't clear about
> > it.
>
> Yes exactly and this task should be cake for the DSP engineers on this forum since these sinusoids barely move.
MIR is no piece of cake.
note onset detection is hard, especially if the note is not percussive. and note release is even harder.
since you're NYC, perhaps this person might interest you: http://www.nyu.edu/classes/bello/MIR_files/1-Introduction.pdf .
otherwise, most of the hardcore MIR folks are at the Left Coast or in Montreal (one of the few European cites on the North American continent).
rots-o-ruck.
r b-j