Today we've announced the new builds of our MELODIA - Melody Extraction vamp plug-in for OSX and Linux! Here is the announcement:

"Dear list,

Following the launch of our MELODIA - Melody Extraction vamp plug-in a few weeks ago, I'm glad to announce we have now added builds for OSX (Universal 32/64-bit) and for Linux (32-bit and 64-bit) in addition to the existing Windows version.

You can download the plug-in (all versions) here: http://mtg.upf.edu/technologies/melodia

Below I've included the text of the original announcement with further information in case you haven't seen it yet.

Cheers,

Justin"

Hopefully this will facilitate the use of MELODIA by the research community which makes extensive use of these platforms (Linux and OSX)!

Yesterday we launched the wiki site of the Audio Melody Extraction Annotation Initiative: http://ameannotationinitiative.wikispaces.com/

Introduction

The Audio Melody Extraction Annotation Initiative (AMEAI) is an initiative driven by the research community working in Music Information Retrieval and related fields. Its primary goal is to compile an open, large, representative and carefully annotated dataset for evaluating what is commonly referred to as Audio Melody Extraction algorithms.

In order to compile this dataset, the AME Annotation Initiative must first address the following topics:

• Define what should be considered as the "melody" in the context of AME evaluation
• Provide a clear definition of the Audio Melody Extraction task (i.e. what should an AME algorithm do)
• Describe the evaluation measures used to evaluate AME algorithms
• Determine the music material that should be included in the new dataset
• Define a clear protocol for generating new annotations
• Compile a list of supplementary resources related to AME

Each one of these topics has a dedicated page on this wiki. Once these topics have been addressed, the AME Annotation Initiative wiki can serve for coordinating and reporting on the progress of the annotation effort, and hopefully also as a general information source about Audio Melody Extraction.

Why do we need a new initiative?

This initiative stems from recent (2012) discussions on evaluation within the research community:

• J. Salamon and J. Urbano, "Current Challenges in the Evaluation of Predominant Melody Extraction Algorithms", in Proc. 13th International Society for Music Information Retrieval Conference (ISMIR 2012), Porto, Portugal, October 2012.
• The panel session on Evaluation Initiatives in MIR during ISMIR 2012
• Discussions on the MUSIC-IR mailing list.

How to contributeThe AME Annotation Initiative wiki has just been launched! (25/10/2012). The best way to contribute is by adding your ideas/proposals to the "discussion page" of each topic, or if you prefer, directly to the wiki page.

We already have several members sign-up to the wiki, I hope the number will grow with time and that the initiative will turn out to be a success. Let's see how this pans out!

Just before ISMIR 2012 we announced the release of MELODIA, our melody extraction vamp plug-in.

In the first week following its announcement MELODIA was downloaded over 50 time by people from all over the globe! 

Equally exciting is the variety of uses people are finding for MELODIA - ranging from high school and university teaching, research, benchmarking, synthesis for music creation, visualisation for DJ sets, and many more! It looks like MELODIA might be handy for more things than we originally thought =)

Since my return from ISMIR 2012 I've been hard at work to compile versions for other operating systems (currently only a windows version is available). In the next few days we'll be announcing releases for OSX, Linux 32-bit and Linux 64-bit!

If you're using MELODIA and happen to read this blog post, please share your experience! It's really exciting for me to see the work of my PhD released into the real world and hear about what people are doing with it!

The ISMIR 2012 conference is now over and it was a very productive experience, and quite intense too! 

The week started off with the tutorials on Monday, of which I'd like to highlight the tutorial on Reusable software and reproducibility in music informatics research, which discussed important issues in software development which are often overlooked by the research community.

On Tuesday I didn't have to present anything and so could enjoy a relaxed day of interesting presentations, posters, and conversations with the members of the MIR community who with each conference become more and more like an extended "academic family" :)

Wednesday was definitely the most intense: it started off with my oral presentation which was the first of the day, describing our work in:

J. Salamon, G. Peeters and A. Röbel, "Statistical Characterisation of Melodic Pitch Contours and its Application for Melody Extraction", in Proc. 13th International Society for Music Information Retrieval Conference (ISMIR 2012), Porto, Portugal, October 2012.

The talk was well received, even though it being the first session of the day meant the audience didn't attack with the usual set of feisty questions as they often do. Thanks to Kazuyoshi Yoshii for the interesting question and suggestion!

Next up was our poster presentation with Julián:

J. Salamon and J. Urbano, "Current Challenges in the Evaluation of Predominant Melody Extraction Algorithms", in Proc. 13th International Society for Music Information Retrieval Conference (ISMIR 2012), Porto, Portugal, October 2012.

The poster managed to attract considerable interest, which is good, because it means the Audio Melody Extraction Annotation Initiative might become a reality after all! Stay posted on this topic...

On thursday we presented two posters, one on tonic detection in Indian classical music and another on tracking melodic patterns in Flamenco music:

J. Salamon, S. Gulati and X. Serra, "A Multipitch Approach to Tonic Identification in Indian Classical Music", in Proc. 13th International Society for Music Information Retrieval Conference (ISMIR 2012), Porto, Portugal, October 2012.

A. Pikrakis, F. Gómez, S. Oramas, J. M. D. Báñez, J. Mora, F. Escobar, E. Gómez and J. Salamon, "Tracking Melodic Patterns in Flamenco Singing by Analyzing Polyphonic Music Recordings", in Proc. 13th International Society for Music Information Retrieval Conference (ISMIR 2012), Porto, Portugal, October 2012.

On Friday Emilia presented our work on Flamenco transcription:

E. Gómez, F. Cañadas, J. Salamon, J. Bonada, P. Vera and P. Cabañas, "Predominant Fundamental Frequency Estimation vs Singing Voice Separation for the Automatic Transcription of Accompanied Flamenco Singing", in Proc. 13th International Society for Music Information Retrieval Conference (ISMIR 2012), Porto, Portugal, October 2012.

And in the afternoon during the Late Breaking / Demo Session I demo'ed MELODIA, our recently released Melody Extraction vamp plug-in, which was a great opportunity to get some feedback from the community regarding the plug-in.

I should also mention that this year there was massive MTG participation, which you can read more about here. To get an idea, here's a photo we took of all MTG current and ex-members who attended ISMIR 2012, and even here there are a couple of people missing because they didn't make it in time for the photo:

Finally, ISMIR was of course also a good chance for enjoying portuguese food, wine (vino de porto) and beer together with fellow researchers.

On a more serious note though, it was an excellent forum to get feedback for my work, and I highly recommend ISMIR for PhD students working in a related area.

Next year... Brazil!

I'm very excited to report that we have finally announced "MELODIA - Melody Extraction", the vamp plug-in I have been working on for the past few months which implements the melody extraction algorithm I have been working on as part of my PhD. Here is the official announcement post sent to various relevant mailing lists:

Finally, take a look at the new MELODIA logo :)