beaTunes News

Friday, June 3, 2011

beaTunes 3 Key Detection Accuracy

beaTunes2 logoI promised yesterday that I'm going to back up my claim that beaTunes 3's key detection works pretty well. To make it short, I tested against the Beatles studio albums. They make testing easy, because reference keys are published at Isopohonics. It also means that you can easily verify my results.

The graph shows correctly recognized keys.

Not so bad, right?



Anonymous Anonymous said...

Does it mean the key detection of beaTunes is significant better than the key detection of MIK?

June 14, 2011 at 10:30:00 AM EST  
Blogger beaTunes said...

More or less.. It means that for the Beatles test set, beaTunes 3 with online resources turned off performs a lot better than MIK 4.1. Things may look different with other test sets.

June 14, 2011 at 10:34:00 AM EST  
Blogger beaTunes said...

That said... I'm actually surprised none of the DJ sites/mags have picked this up yet. Somebody should tell them.. ;-)

June 15, 2011 at 6:07:00 AM EST  
Blogger alexndr said...

Made small comparison between version 2 & 3: - difference is noticeable. Waiting for full comparison before buying v3.

July 5, 2011 at 7:44:00 AM EST  
Blogger beaTunes said...

Are you planning to conduct a full comparison? I will not..

July 5, 2011 at 7:57:00 AM EST  
Blogger alexndr said...

No, I will wait for someone qualified :)

July 6, 2011 at 5:13:00 AM EST  
Blogger beaTunes said...

Seriously, the comparison with b2 will be useless unless you also compare against a reference dataset (i.e. a ground truth). Only then you can make meaningful statements about accuracy of either version. That said, in internal testing b2 performed pretty much as well as MIK41 on the Beatles testset, i.e. roughly 53%, if I remember correctly.

July 6, 2011 at 5:19:00 AM EST  
Blogger The Mekong Riverkeeper said...

I don't see error bars... what's your p value there? :o)

July 10, 2011 at 8:40:00 AM EST  
Blogger beaTunes said...

Stevie, besides this blog post not being a scientific paper, I'm not sure you understand the nature of this graph and the experiment it describes.
The experiment is repeatable, i.e. it always delivers the same results. And the actual probability of any of the algorithms delivering the correct result (i.e. the null hypothesis) is unknown.
It appears to me that a p-value therefore does not make any sense.

July 10, 2011 at 9:04:00 AM EST  
Anonymous Anonymous said...

Hi is there a way to, instead of having beatunes detect key in letters, have it detect it in numbers such as 8b or 9A, etc.

July 17, 2011 at 12:15:00 PM EST  
Blogger beaTunes said...

beaTunes detects keys, not letters, not numbers.
It then displays this information in their proper musical name and also in the Open Key Notation, a number based format.
beaTunes does not display the key information in Camelot notation, because the inventor of that notation requires other companies to license that particular notation. Feel free to google "beaTunes Camelot notation" to find more information about this topic.

July 18, 2011 at 3:10:00 AM EST  
Anonymous Billy Carey said...

So how does it's detection rate compare with dance music?

October 5, 2011 at 3:20:00 PM EST  
Blogger beaTunes said...

I wish I could tell, but I'm not aware of a publicly available reference set. And as long as that's not available, anybody who claims to do really well on dance music is spreading myths.

That said, if you know of a good reference set, I'd be more than happy to run the test and post the numbers.

October 11, 2011 at 1:38:00 PM EST  
Blogger Unknown said...


Could you please run a comparison against MIK 5? I own and love your software, but I am very curious to see if MIK 5 has managed to close the gap in terms of accuracy.


October 29, 2011 at 11:22:00 AM EST  
Anonymous Anonymous said...

Hi, I compose through MIDI devices and softwares. Can your program determine the key of a MIDI file ? Or is it audio only ?

November 18, 2011 at 5:48:00 PM EST  
Blogger beaTunes said...

Audio only.

November 18, 2011 at 7:09:00 PM EST  
Anonymous Anonymous said...

It seems your program doesnt work that well (regarding key detection, I still love it to keep my metadata consistent and the creative suggestions for playlists):

The test contains also a list of the 50 songs which are used for testing.

January 31, 2012 at 3:35:00 AM EST  
Blogger beaTunes said...

Yep, beaTunes does not do well in that test. However, with just 50 tested songs, the 95% confidence interval is probably around plus/minus 12%. (please correct my math, if this sounds off to you)

January 31, 2012 at 10:39:00 AM EST  
Anonymous Steve C said...

Songs on beatport have the key listed? Could you use that as a test?

May 1, 2012 at 2:39:00 PM EST  
Anonymous sven said...

" Steve C said...

Songs on beatport have the key listed? Could you use that as a test?"

I would be interested in this as well :D

October 3, 2012 at 7:33:00 AM EST  
Anonymous Anonymous said...

Beatport uses software to detect the key. It's not provided by the artist.

February 26, 2013 at 3:00:00 PM EST  
Blogger beaTunes said...

Any idea which software they use?
(given the state of the art - it could also be wrong)

March 11, 2013 at 11:28:00 AM EST  

Post a Comment

<< Home