Conference Paper, Publication »

[28 Jan 2014 | No Comment | 232 views]
Abstract: In the past decade, non-negative matrix factorisation (NMF) and probabilistic latent component analysis (PLCA) have been used widely in automatic music transcription. Despite their successes, these methods only guarantee that the decomposition converges to a local minimum in the cost function. In order to find better local minima, we propose to extend an existing PLCA-based transcription method with the deterministic annealing EM (DAEM) algorithm. The PLCA update rules are modified by introducing a “temperature” parameter. At higher temperatures, general areas of the search space containing good solutions are found. As the temperature is gradually decreased, distinctions in the data are sharpened, resu…

from me to you »

[7 Jan 2014 | No Comment | 214 views]
Just a quick reminder that you can still apply for a funded PhD position in Signal Processing and Data Mining Tools for the Analysis of Musical Evolution, as previously posted. Job description is here (at

Done and Liked »

[6 Jan 2014 | No Comment | 354 views]
I’d already sent it out to the world on Twitter and the music-ir list, but here’s just a quick note to say that there’s quite a lot of new software out from me and the C4DM at large. Four different things! Here’s approximately what I wrote on the music-ir list: Segmentino — this is my 2009 segmentation method, which we have recently implemented as a Vamp plugin. This version is what ran at MIREX this year. BeatRoot Vamp Plugin — this is a C++ implementation of Simon Dixon’s trusty beat tracker (originally implemented in Java). This is the second serious beat tracker QM offers (the other one comes with the qm-vamp-plugins). pYIN is “probabilistic YIN” — my generalisation of the time-tested YIN algorithm for monophonic pitch tracking. Also implements YIN, but pYIN is more robust than YIN alone. Also implements a note tracker. Tony is a tool for melody annotation. A little brother of Sonic Visualiser, which is simpler but specialised on note editing. A collaboration between Chris Cannam, George Fazekas and me — WARNING: still a prototype (don’t expect too much). All these are also linked from my Software page.…

Done and Liked »

[25 Nov 2013 | No Comment | 474 views] I’m very lucky to be able to offer a funded PhD position for next year, in combined MIR and evolutionary music analysis. So if you know someone who’d be a good fit, let them know! They will be based here at the Centre for Digital Music, I will supervise, and Prof. Armand Leroi at Imperial College will advise on evolutionary matters. This should be one of the most fun PhDs in the universe (if that’s your idea of fun—it is mine!). You can find the serious description on the website. Go for it!

Featured, from me to you »

[31 Okt 2013 | No Comment | 449 views] I’m about to embark on a tour promoting our new album, well: paper, called “The Audio Degradation Toolbox and its Application to Robustness Evaluation” (pdf here). You can read all about the toolbox, listen to examples and get the source code on My little tour first leads me to New York, where I’ll give a little presentation at LabROSA, Dan Ellis’s lab at Columbia University. Only two nights though, then I’ll be off to Curitiba in Brazil, for the ISMIR conference. There I’ll be presenting the ADT “officially” with a poster. Tian Cheng, my first PhD student, has some interesting stuff to tell abo…

Done and Liked, Featured »

[27 Sep 2013 | No Comment | 337 views] There’s a new DarwinTunes, and we’re going to reveal it today at the Discovery Festival in the Amsterdam, Rotterdam and Eindhoven. So what is DarwinTunes 2.0? It’s a music evolution machine, wrapped into a shiny web app, in which a community of music lovers can breed musical loops. This community is going to be the visitors of the three sites of the discovery festival tonight, and when everything goes well, we’ll announce the URL at midnight Central European Summer Time, so the whole world can join. Some of you may know the original DarwinTunes, with which we successfully evolved pleasant loops (see SoundCloud) and which led to a super scientific paper and even a prestigious prize (I reported). But in the or…

Done and Liked, Featured »

[16 Sep 2013 | No Comment | 310 views]
Watch me talk about our work on the Evolution of Music by Public Choice in this interview with FACULTI. It’s mainly a pop science view on our paper (available here). I think they did a good job at editing (except possibly the little flattering still of me on the video thumbnail…).

from me to you »

[14 Sep 2013 | No Comment | 489 views] I know this off-topic on this Music Informatics website, but I couldn’t resist some data analysis on, yes!, Germans political parties. This is, of course, because general elections are looming. Where I got the data from? From the Wahl-o-mat website, run by an independent body whose mission is political awareness. Here’s how it works. Wahl-o-mat have compiled a questionnaire of political statements which you can answer “agree”, “neutral”, “not agree” (in German) on-line. This will then be matched to the answers of 28 political parties (which the parties have officially given to Wahl-o-mat), and you get a score of which party you agree with most. Crucially, after the exerci…

AIST Series, Done and Liked, Featured, Seen and Liked »

[7 Sep 2013 | No Comment | 298 views] AIST have gone a step further with, including YouTube content. Previously only less mainstream music from SoundCloud and independent MP3 sources and the Vocaloid community could be found on the site. Songle is a miraculous shop window for Music Informatics Research, with many of the core MIR tasks performed on the song, and with the crucial ability for users to improve on the automatic detection. Chord detection, beat and bar detection, chorus detection, vocal activity detection, melody estimation, and song similarity, are all part of the chic web interface. Take this Muse track, for example. Now I’m, of course, partial, having been involved in the early stages of the project (see our 2011 paper), but the guys ar…

AIST Series, from me to you »

[31 Aug 2013 | No Comment | 371 views] Only a few days and I’ll be back at AIST in Japan, working with Masataka Goto again — but this time it’ll be for six weeks only. I’m quite looking forward to it, not only because I will meet and work with Masataka himself and good old Yoshii-san again, but also because Matthew Davies, an old colleague formerly at Queen Mary, is going to be there, as is Matt McVicar, a friendly connection formerly at Bristol. And the work itself should be fascinating, too: looking forward to get an inside view of how is developing alongside the newer Songrium project. And then there’s the food as well! And maybe I can squeeze in a visit at the University of Tokyo as well, should contact Ono-sensei soon.