SongKong Jaikoz

SongKong and Jaikoz Music Tagger Community Forum

Questions about Mood

#1

I’m about to buy SongKong Pro, since I really like the idea of the Mood determination.
I havent found another program that determines the mood on itself.
I mean, I do have BeaTunes, but that software grabs the last.fm tags, input by users (which is lean).

So my questions are:

  1. How does SongKong Pro determine the mood of a song? Could you be more specific what is it doing in the background?

  2. On which theory-model are the tags based? Thayer, Hevner or made-up yourself?
    (Delighted, Excited, Astonished, Aroused, Tense, Alarmed, Angry, Afraid, Annoyed, Distressed, Frustrated, Miserable, Sad, Gloomy,
    Depressed, Bored, Droopy, Tired, Sleepy, Calm, Relaxed, Serene, Glad, Pleased)

  3. Where are those mood tags written to? ID3 tag or SongKong’s database?

  4. Could I buy the SongKongPro license and test it out for a couple of days, to see how the Mood-option is working out for me, and if i’m not happy, I can get my money back?

Kind regards,
snowseals

#2

Hi, SongKong primary database for song matching is MusicBrainz, and MusicBrainz has a sister project https://acousticbrainz.org that does mood analysis. So rather than do mood analysis itself once SongKong has matched to a MusicBrainz song we lookup that song in AcousticBrainz to get all the mood data, plus bpm and key. Because we don’t have to actually do the analysis ourselves just look it up it takes virtually no additional time then the matching. More details about the algorithms can be found on the acousticbrainz site

All the data is written to metadata fields inside the file itself, so is all accessible outside of SongKong, we write not only MOOD, BPM and KEY but also some other metrics such as how likley is it to be instrumental, or acoustic

The free trial lets you see exactly what would be added to your files including MOOD data, so you can check it all out before you buy.

#3

Awesome!

I was reading this thesis http://www.tdx.cat/bitstream/handle/10803/51582/tcfl.pdf?sequence=1 which looks like in-depth source material, until I found out by your answer, this is the source/method where/how AcousticBrainz gets its data :smiley:

I also found out beaTunes has a plugin, so it can use the database of AcousticBrainz aswell (next to last.fm’s db) to search for Mood-tags, but I want to compare SongKong against the results of beaTunes.

In beaTunes, I have a clear list of which songs actually got tagged mood-wise.
How can I view how many songs are tagged mood-wise via SongKong?
Is it somewhere in the Summary HTML report or…?

NOTE:
I made sure I disabled some features in SongKong, so it starts fresh and re-scans, re-fingerprints, removed Mood from the ‘‘If already excists, don’t override the following tags’’ where BPM/MOOD/KEY are put to default, etc. to make it a fair comparishment.

#4

Hi, its not summarised in the summary report actually, but that is a good idea, I will add that in a future release. In the SongChanges part of the report you can see the changes for any particular song but SongKong doesnt currently have a way to see all the changes in a table or spreadsheet view (we already have a feature request for this).

What may be easier for this purpose is to try Jaikoz (they both use the same acousticbrainz code) and then you can see all the changes made by simply enabling the Mood based columns.

#5

Thank you.

Tried out Jaikoz (for this purpose) today.
I’ve used the ‘Retrieve Acoustic ID’ button on top, enabled the Mood-column aswell, but so far no Moods showing up.
Well, highly 50 songs which were tagged, before using this function.

I’m now running the ‘AutoCorrector’ since a few hours…
Is that the way to get those Moods to show?

Or how should I proceed next time?

#6

Well, AutoCorrect Songs is done by now, but still no Moods showing, see screenshot:

I’m a lil’ wary by now, if this function is enabled in Jaikoz trial-version, since Moods still not showing and the download-page says the following about limitations with the free trial-license:

[quote]By default Jaikoz comes with a free trial license which is valid for 30 days. The free version is disabled in the following ways
You can test out all the functions on as many files as you wish (except for Pro only features) but changes can only be saved to 20 files during one use of Jaikoz[/quote]

Update:
I just did a ‘Retrieve Acoustic ID’ again, and after, ‘Submit MusicBrainz/AcousticID Pair to the Server’ but still no Moods…

#7

Oh sorry you are quite right, on Jaikoz (but not SongKong) the trial does not give you the Pro features so you cant test Mood on Jaikoz. Im not quite sure why I did it this way, okay if you would like to buy SongKongPro Ill let you get a refund if it doesnt work for you. You will be able to use the Jaikoz trial the view the moods added by SongKong

#8

I just bought SongKong Pro.
Thanks for giving me the heads up, I’ll let you know how it works out.

Kind regards,
Snowseals

#9

Great, we have just released SongKong 4.3 so make sure you have the latest version

#10

So I decided to compare results: SongKong 4.4 (Pro) vs. beaTunes 4.6.10.

I picked 10 tracks from 10 different genres.
The results are interesting.

See picture:

Why is there so much difference between the moods, when comparing the outcome of both programs on the same song?

I even dare to say, there are contradictions.
Like for ex. track 5, ‘Extremely Calm’ vs. ‘Very Excited’;
And what about track 10, ‘Very glad’ vs. ‘Very aroused, angry’.

Even the values of Happy/Happiness and Arousal are different.
I thought SongKong was just reading out the data in the database of AcousticBrainz (and beaTunes aswell using its plugin)?

Does SongKong keeps reason with all of the values, like Mood Happy, Arousal, Valence, Agressive, Dance, Party, Relaxed, Sad and divides them to create a distinguished textual tag, like ‘Very glad’ ?
Or is there just a a tag in the AcousticBrainz db written, called for ex. ‘Very glad’?

How does it work?

N.B.: I noticed the picture shows a little vague due tinypic’s compression, so I uploaded the pic, you can download it in higher quality here: http://www68.zippyshare.com/v/aOY5uef5/file.html

#11

Hi, looks like there is a problem there. AcousticBrainz doesnt actually store ‘Very glad’ what we do to work out is use the values that AcousticBrainz does provide to calculate a measure of Arousal and Valence. Arousal and Valence from the two axes of a graph, and when we plot the value that gives us a segment which then maps to the textual values of ‘Glad’, and a vector distance to give us the ‘Very’

The first thing to note is Beatunes Happiness field maps to the Mood Valence value not the Mood Happy value, but there is still a clear disparity between these values as well as the final Mood value.

The problem could be in where they are taking the data or how they are dong the calculation, some songs have more than one set of figures from different user submissions and we may be using a different figure, the fault could lie on my side or with Beatunes.

But what I need from you for these songs is the value of the MB Recording Id column so I can look up the data in AcousticBrainz.

#12

Hereby the MB Recording IDs pulled from Jaikoz: http://www94.zippyshare.com/v/0hvkpEXE/file.html

Track 1: 6941913b-f2c0-4638-a144-a19715df3517
Track 2: cb63543e-c6c9-4233-a3e9-b220101b1699
Track 3: 0519a10c-ad05-40d2-9928-2114472e5d60
Track 4: 0acc282b-c4db-44b2-a6ae-3c037fa3255a
Track 5: 7a6094ca-50e5-4973-bfb0-2c114d574577
Track 6: 5daaf5cf-5a75-43ee-92a2-ee72c6a40a1d
Track 7: 28651acc-1f13-4431-b2de-d93a33a50084
Track 8: 50c1d6f1-f2b2-4925-94c4-f4eacd4bd6f7
Track 9: 5124f0c4-c3eb-49cd-a312-3a4ff43b542b
Track 10: e3ed55e1-fa10-4b30-9cd0-798aef858da6

#13

Thanks Ive checked my figures against some of these songs and they appear to be correct. Im now speaking to Hendrik at Beatunes who is a nice fellow to see if we can work out where the discrepancy between our figures lie, will get back to you as soon as we have an answer.

#14

Spoke to Hendrik and those values are from his last.fm plugin. If you rerun Beatunes using only AcousticBrainz plugin you should get matching results.

#15

Thanks again!

I’ll do some testing asap.

I noticed AcousticBrainz is depending on user input.
I also noticed this blog http://blog.jthink.net/2014/11/how-to-easily-calculate-beats-per.html , where it says:

Is that already the case?

I mean, I do see Create Acoustic fingerprint under Fix Songs -> Match.
But does that mean, I’m contributing to AcousticBrainz aswell?

#16

No it isn’t yet done, it was intended to do it this year but I ended up spending alot more time then anticipated on the Classical music support. But there is a standalone tool available form acousticbrainz.org that you can use to submit data from your own files, then SongKong would be able to make use of that data.

Although similarly named Acoustid and AcousticBrainz are completely different projects, their only connection being they are both MusicBrainz aware.

#17

Thanks, I just installed that AcousticBrainz Extractor and submitted 133 tracks. It skipped 53 songs due lack of info on MusicBrainz-end.

So this means, it found half of them and now the info about Mood is available for the other half of the songs when using SongKong?

#18

It wont happen immediatley because acousticbrainz data is downloaded from acousticbrainz into albunack which is used by SongKong and allows much faster access then if download directly from acousticbrainz

#19

Ah, ok thanks.
Any Estimated Time of Arrival available?

#20

It might be a bit a bit longer than normal what with Xmas and all that, we also plan to have songkong looking up directly form acousticbrainz when no record found on albunack, and that might be in next release.