Kommentare für artificial musicality

Kommentar zu Comments enabled until I get fed up with spammers again von Matthias Mauch

Matthias Mauch — Fri, 30 Mar 2012 21:10:32 +0000

Just a quick update: so far, it seems to work — no spammers yet. No sincere commenters either though, so I have to bloomin’ comment myself.

Kommentar zu ‘Voice of the Future’ at the Houses of Parliament von Matthias Mauch

Matthias Mauch — Mon, 26 Mar 2012 20:31:47 +0000

I’m planning on enabling comments again, hope the spammers stay away, ahaha!

Kommentar zu The Anatomy of the UK Charts - some of my research on the Last.fm blog von Martin

Martin — Thu, 16 Jun 2011 20:07:14 +0000

Bravo!

Kommentar zu High Precision Frequency Estimation for Harpsichord Tuning Classification von artificial musicality » Blog Archive » TempEst temperament estimation is online

Tue, 22 Mar 2011 14:47:36 +0000

[...] are estimated using Fazekas’s VamPy implementation of my Matlab code originally used for last year’s ICASSP paper (with Dan Tidhar and Simon [...]

Kommentar zu Automatic Chord Transcription Using Computational Models of Musical Context von artificial musicality » Blog Archive » Recent MIR theses on chords, keys and harmony

Sun, 06 Mar 2011 06:00:01 +0000

[...] Matthias Mauch: Automatic chord transcription using computational models of musical context on this website [...]

Kommentar zu Ground Truth Session at the Dagstuhl Seminar and beyond von Matthias Mauch

Matthias Mauch — Wed, 16 Feb 2011 04:08:27 +0000

Hi Matt, thanks for the praise … not sure about any updates from McGill’s side, I think they said they’ve got nearly where they wanted to be, so I assume that ISMIR will reveal more.

Kommentar zu Ground Truth Session at the Dagstuhl Seminar and beyond von Matthias Mauch

Matthias Mauch — Wed, 16 Feb 2011 04:06:41 +0000

Hi Thierry,

First of all: congratulations to the Million Song Dataset! Promises to be a fabulous resource.

I’m not pessimistic about ground truth itself at all. And I could not agree more that computer-human interaction for ground truth generation is a way forward. I guess I’ll have to say more about that soon, especially if my grant application goes through — I propose to do more or less exactly that.

The only way in which I may be a bit pessimistic is that people might blindly data-mine and stop caring about actual ground truth data, or good modelling. So I hope that great efforts such as yours will broaden peoples minds, not narrow them.

Matthias

Kommentar zu Ground Truth Session at the Dagstuhl Seminar and beyond von Thierry BM

Thierry BM — Wed, 16 Feb 2011 03:42:32 +0000

Very interesting!
but you seem rather pessimistic about die-hard ground truth, have we really “done that”? How big/large have we tried, and is it enough to give up?
And isn’t there a third way, algorithm-aided annotation, with computers and humans in the same loop? For instance, you can find many critics of the Echo Nest “sections”, but they are still reasonable, could they help a human annotate faster (since he would not start from scratch)?

Kommentar zu Peep into my toolbox 3: Sonic Visualiser von Christopher Sutton

Christopher Sutton — Sun, 13 Feb 2011 09:43:57 +0000

Great post! I’m a huge fan of SV too, but have never articulated it quite as well as you have here.

In my past work I’ve occasionally tried Praat or Audacity for analysis, and continually made one-off plots in Matlab, but in my experience nothing comes close to Sonic Visualiser for letting you really get to grips with an audio track and delve into it in a satisfying (and informative) way.

Also - its UI is nicely designed, and it just does what it should, reliably. The value of these two features is not to be underestimated! (I’m looking at you, Audacity…)

Kommentar zu Ground Truth Session at the Dagstuhl Seminar and beyond von Matt McV

Matt McV — Fri, 11 Feb 2011 13:54:35 +0000

very nice!

Interesting to see that money isn’t a good motivation for ground truths. Was there any update on the McGill dataset? Best,

Matt