It seems like I didn't realise the effect that having MELODIA (and other vamp plug-ins) included in the curriculum of a course on digital sound design on coursera.org was going to have... in 2 days, MELODIA has been downloaded over 800 times and the total count is now above 1200!
Not quite the "slashdot effect", but the closest I've ever experienced :) Beside boosting the download count, I hope this will increase students' interest in melody extraction and help introduce a new generation of artists to MELODIA. I'm sure they'll find ways to exploit it I've never thought of before... Once the "coursera-burst" is over I'll post again with some interesting download stats and (hopefully) some insights.
0 Comments
Today I've come to learn that my MELODIA vamp plug-in, which implements the melody extraction algorithm developed as part of my PhD thesis, has been included in the course material of an online course on digital sound design. More specifically the course includes an introduction to Sonic Visualiser, and as part of this introduction the students are encouraged to experiment with the plug-ins available on the vamp plug-in download page, one of which is MELODIA.
As a result, MELODIA has been downloaded more than 100 times in the last 24 hours, and the overall download count has now surpassed 500! Whilst it is clear that for some students the plug-in will prove to be more useful than for others, and most probably not all those who've downloaded it will end up using it on a regular basis, this is nonetheless an exciting example of how MELODIA can be used for educational purposes, and of the impact it can have outside the research community. The next step will be to try and get some feedback on MELODIA from this large group of users, so that we can further understand what people are using it for, when it is useful and when it isn't, and perhaps also get some recommendations and how they would like to see it improved. MELODIA, our melody extraction vamp plug-in reached its 200th download yesterday!
Apart from obviously being excited about the interest in the plug-in, I was also really surprised by the wide range of uses people have found for it. In addition to the perhaps more expected research purposes (transcription, query-by-humming, computational musicology and ethnomusicology, music similarity, structure analysis, etc.), people have downloaded it for educational use in schools and universities, for music composition (for example for synthesizing natural sounding vibrato by using the pitch curve generated by a real singer, or for vocaloid compositions), for checking out the current state-of-the-art (including some commercial companies...), and even just to "view music in a different way" and "for fun". So... what next? :) If you haven't already, you can try out MELODIA for yourself, it's free. http://mtg.upf.edu/technologies/melodia Our paper:
J. Salamon, J. Serrà and E. Gómez, "Tonal Representations for Music Retrieval: From Version Identification to Query-by-Humming", International Journal of Multimedia Information Retrieval, special issue on Hybrid Music Information Retrieval, In Press. has now been officially accepted for publication. The paper compares different tonal representations (melody, bass line and harmony) for version identification (automatically detecting cover songs). We also show how our approach for vesrion ID can be easily adapted for query-by-humming (QBH, i.e. searching for a song stuck in your head by singing or humming part of the melody), and since both the melody extraction (using MELODIA) and the matching is fully automatic, this is a fully automatic audio-to-audio QBH system prototype! We're also planning to put all the queries we recorded for the experiments online, together with a list of the songs in the music collections we used for evaluation (unfortunately we can't share the songs themselves because they are protected by copyright law). I'll write a new post once the files are up. I'd like to thank my co-authors Joan Serrà and Emilia Gómez for their excellent work. Hope you find article interesting! 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)! 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! |
NEWSMachine listening research, code, data & hacks! Archives
March 2023
Categories
All
|