A MIR paper published on Nature (the Journal): “Measuring the Evolution of Contemporary Western Popular Music”

Measuring the Evolution of Contemporary Western Popular Music : Scientific Reports : Nature Publishing Group.

Really nice to see (and read) such an interesting Music Information Retrieval (MIR) study in such a prestigious journal as Nature. Congratulations to the authors!

In addition to that, this seems a clear sign that Music Information Retrieval is no “obscure” topic, and research work done in this field  is taken seriously by the overall scientific community, finding its way into the most prestigious and relevant scientific journals in the world (and not only in the filed of MIR, Computer Science, Musicology, etc).

In fact, there’s at least another important milestone in the MIR field that shows exactly that: “Xavier Serra is awarded an ERC Advanced Grant“.

Music Recommendation Datasets from Last.fm, by Oscar Celma

:: Music Recommendation Datasets ::.

One more dataset for MIR and Music Recommendation, compiled by Oscar Celma, and based around Last.fm data and APIs.

And some more detailed info here.

Open source music identification using Audio Fingerprints

 

The guys at Echnest just realease their Echoprint – Open source music identification service. Looks really neat. There’s even an iOS app example here.

Last.FM also recently provided a audio fingerprinting API. More about this here.

So now it’s really simple to integrate audio fingerprinting in opensource apps. Looking forward to try it out soon.

 

Million Song Dataset | scaling MIR research

An impressive feature data set extracted from music audio files by LabRosa using the Echonest API:

Million Song Dataset | scaling MIR research.

However, the feature set is (obviously) fixed and you have no access to the audio content of each music piece in the dataset (and there are some understandable reasons for that – check the FAQ). Nevertheless, a lot can already be done using this data (mainly for the machine learning, data mining, Information Retrieval folks), and this effort is a great contribution for the development of more advanced music recommendation systems.

Personally, I’m still very much into audio signal processing (mainly related to sound segregation, where I’m still trying to explore the basics of machine listening), so for now this dataset is not that useful to me…

Congratulations to LabRosa and Echonest for the effort and for making this public and available to the R&D community!