tag:blogger.com,1999:blog-28898943152575951362024-03-13T10:49:33.674+00:00MIR ResearchEliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.comBlogger117125tag:blogger.com,1999:blog-2889894315257595136.post-88540518932752626992010-03-07T02:05:00.003+00:002010-03-07T03:14:10.616+00:00Fading OutI first started learning about MIR around spring 2001. Back then I never would have guessed what a wonderful journey I was about to embark on. The journey had way more highlights than I ever deserved and I'm very grateful to so many people I've met on the journey. <br /><br />I recently returned to Vienna to be closer to my family and friends again, and to settle down and start a new chapter in Gwen's and my life. Part of this transition has also been switching jobs. I'm in telecommunications now and uncertain if I'll ever return to MIR research.<br /><br />I'll always continue following all the great stuff that's going on in the community from the side lines - but my already very infrequent blogging frequency is very likely to continue to decrease. When I started writing there was basically just Paul's blog. Now there's still <a href="http://musicmachinery.com/">Paul's blog</a>, but also lots of other great MIR related blogs. Some of which are listed in the side bar.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com2tag:blogger.com,1999:blog-2889894315257595136.post-75428024918021140492010-03-07T00:18:00.004+00:002010-03-07T02:07:31.555+00:00Updated List of MIR PhDsThere's a long-overdue updated version of the <a href="http://pampalk.at/mir-phds">list of MIR PhDs</a>. The new entries I've added are Stéphane Rossignol (2000), Juan José Burred (2008), Iman S. H. Suyoto (2008), Matti Ryynänen (2008), Enric Guaus (2009), Claudio Baccigalupo (2009), Klaas Bosteels (2009), Katy Noland (2009), Tim Pohle (2010), and Jouni Paulus (2010). I've also updated some other links. Thanks to everyone who sent me information!!<br /><br />I've had the pleasure of reading the <a href="http://www2.iiia.csic.es/~claudio/papers/Baccigalupo-2009-PhdThesis.pdf">thesis</a> of Claudio and I can highly recommend it. His enthusiasm is inspiring. It's a great point to start for anyone researching playlist generation.<br /><br />Another pleasure I've had was to attend the defense of <a href="http://www.last.fm/user/klbostee">Klaas'</a> thesis. I've been closely following his work for a very long time. I've had the honor to collaborate with him on several occasions, and I'm very pleased that it's him who has taken over some of my previous responsibilities at Last.fm.<br /><br />I've also been following Katy's and Tim's work for many years. Which makes me wonder how soon until all MIR PhD students I know are done. Until that happens I'll infrequently continue updating this blog and the list.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com1tag:blogger.com,1999:blog-2889894315257595136.post-35632375135709699552009-10-23T11:39:00.004+01:002009-10-23T17:00:01.416+01:0010 Reasons to Work for Last.fmI've moved to Vienna, and I'm about to leave Last.fm. Looking back, here are 10 reasons why I love to work for Last.fm:<br /><br /><b>1. Staff</b><br /><a href="http://www.last.fm/about/team">My colleagues</a> turn work into play and have created an environment that feels like a family. I've learned a lot from many of them. Some have become very close friends. All of them have inspired me with their passion, enthusiasm, motivation and curiosity for everything related to technology and music. Also they've always been very patient with me and always very helpful. I admire their intelligence, creativity, and how determined they are to make music more enjoyable.<br /><br /><b>2. Users</b><br />There is a constant flow of very valuable feedback from our users. Many are as passionate about Last.fm as we are. They have enabled us to run countless experiments (A/B tests and similar) - from which we learned more than we could have ever learned in a standard academic environment.<br /><br /><b>3. Data</b><br />If you love data mining and working with large data sets, you'll love working at Last.fm. There are a lot of fascinating things that can be learned about music from Last.fm's data. And there is a lot of fascinating things to learn about dealing with data at such a scale.<br /><br /><b>4. Technology</b><br />Last.fm has been on the front-line of some very interesting developments. Always using the tools that work best and developing new ones when needed. Always trying to push scalability limits and trying to make things work faster and better. Before joining Last.fm I didn't realize how fascinating technology can be that solves large scale problems. I've learned new programming languages, things like Hadoop, and many algorithms I had never heard of before. I caught a glimpse of the amazing technology (both software and hardware) behind serving tens of millions every month. If you love technology, you'll love working at Last.fm.<br /><br /><b>5. Openness</b><br />The data is easily available through APIs. Last.fm staffers constantly contribute to open source projects and parts of Last.fm are open source. Every staff member (even I) can post anything they want on the company blog. We are constantly attending events where we talk about the things we do and share our experiences. Also the communication within Last.fm is very open.<br /><br /><b>5. Fun</b><br />We have a table tennis table standing around in the office, a foosball table, there was always a skateboard around, and for a while we even turned one of the meeting rooms into a ball pit (and had meetings in there). There were remote controlled helicopters flying around in the office, XBoxes, we have colored bears telling us about the state of our code, highlight words on IRC include "pub", on IRC we also constantly share the newest coolest stuff we find on the Internet, servers have names like "<a href="http://www.badgerbadgerbadger.com/">badger</a>", ...<br /><br /><b>6. Lunch Discussions & Techmosis</b><br />One of the things I've already started missing since I moved to Vienna are the daily (informal) lunch discussions. In particular the discussions in which Norman Casagrande was involved - he's like a living encyclopedia. We talked about why C++ templates are so useful, how to solve the problems in the middle east, inconsistencies in religious beliefs, objectivity as a concept, world history, politics, the daily show, ...<br /><br />We also have something we call Techmosis, where we teach each other things. Usually Friday evenings we reserve a one hour slot to learn about something cool. Sometimes we'd also have non-staffers teach us. Today it will be a presentation on manga by Japanese manga artists. Generally I found the atmosphere of teaching each other extremely inspiring.<br /><br /><b>7. London</b><br />London is an amazing city. There is so much happening, there is more stuff to check out every day than I could absorb in a year. I'd love to move Last.fm to Vienna, but I can see why East London is the perfect place for Last.fm. As one of my colleagues says: it rubs off on you. If you haven't lived in London yet, you should definitely give it a try. <br /><br /><b>8. Free Stuff</b><br />My favorites are my Last.fm t-shirts (one of which I'm wearing right now) and the fruit. (I herewith admit that every week I probably eat about half of our weekly supplies all on my own.) Pizza lunches and the occasional pub visits with a company credit card were nice to have, too.<br /><br /><b>9. Rooftop Barbecues</b><br />We made sure our neighbors knew they lived (or worked) next to us. But I think the best part always was how the parties just seemed to spontaneously happen.<br /><br /><b>10. Music</b><br />Last on this list, but not least: If you love music, you'll have a hard time finding a better place to work than Last.fm where you are surrounded by music, and people who love music. You might also like the band practice room.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com3tag:blogger.com,1999:blog-2889894315257595136.post-1438232275691409922009-10-20T17:18:00.009+01:002009-10-20T18:31:40.624+01:00Wittgenstein Award: Gerhard Widmer (!!)<a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://3.bp.blogspot.com/_ccNNXQ8yqZQ/St3p9FVjDYI/AAAAAAAAAdw/0IxWJtb2Uxs/s1600-h/gerhard.jpg"><img style="float:right; margin:0 0 10px 10px;cursor:pointer; cursor:hand;width: 230px; height: 351px;" src="http://3.bp.blogspot.com/_ccNNXQ8yqZQ/St3p9FVjDYI/AAAAAAAAAdw/0IxWJtb2Uxs/s400/gerhard.jpg" border="0" alt=""id="BLOGGER_PHOTO_ID_5394725164273569154" /></a>The <a href="http://www.wittgenstein-club.at/det-eng.htm">Wittgenstein award</a> is kind of like the Austrian version of the Nobel prize. It's worth €1.5M and the most prestigious research award I'm aware of. Yesterday <a href="http://www.cp.jku.at/people/widmer/">Gerhard Widmer</a> received the prize for his outstanding research work. <br /><br />Gerhard is one of the hardest working I know, he has an amazing talent of communicating research to non-researchers, creating very productive work environments, and bringing the right people together. Also he has conducted, supervised, and inspired lots of great research. He also gave me my first (paid) job in MIR and supervised my PhD. I've learned a lot from him and I'm very grateful. So I'm particularly happy to see Gerhard received this award he well deserves. <br /><br />My favorite <a href="http://derstandard.at">daily newspaper</a> wrote about it. And here's a quick, shortened, and far from accurate translation of what they wrote:<br /><br /><b>Frustrations and Fortunes with Ludwig van Beethoven</b><br /><br />Among Gerhard Widmer's favorite music you find Beethoven's piano sonatas. He doesn't have a preferred interpret. For some phrases he prefers Friedrich Gulda, for others Alfred Brendel, or other pianists.<br /><br />It is also Beethoven who is to blame that Gerhard did not pursue a career as musician and instead became a internationally renowned researcher on algorithms to study music. Work for which he was now awarded with the Wittgenstein prize.<br /><br />Gerhard was an early talent but gave up his career as pianist after frustrations with Beethoven's sonatas as a teenager. Instead he took a quick dip in Jazz and more or less randomly ended up studying computer science.<br /><br />He received an MSc in Vienna and at the University of Wisconsin. It was also in Wisconsin that Gerhard briefly returned to the Jazz piano. Back in Vienna he completed his PhD in computer science which finalized his career as researcher.<br /><br />Gerhard's research started with analyzing the performances of a single artist and as a side effect he tried to teach computers to interpret music. Later his group started focusing on developing algorithms that enable organizing and retrieving content from very large music collections. The work of his group can also be found in the <a href="http://mir-research.blogspot.com/2009/08/bang-olufsen-and-ofai.html">newest devices by Bang & Olufsen</a>.<br /><br />Music has always been more than just a research subject to Gerhard. And he says that the scientific analysis of music does not take away any of its magic - instead it makes the music even more beautiful when you start to understand its structure.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com1tag:blogger.com,1999:blog-2889894315257595136.post-46362344210464287632009-09-06T17:41:00.003+01:002009-09-06T20:29:36.869+01:00Updated MIR PhD Theses ListI've updated the <a href="http://pampalk.at/mir-phds/">list of MIR PhD theses</a> to include the recent work by <a href="http://research.nokia.com/people/antti_eronen/">Antti Eronen</a> on <a href="http://urn.fi/URN:NBN:fi:tty-200906301085">Signal Processing Methods for Audio Classification and Music Content Analysis</a>. Antti covers a broad range of fascinating audio content processing topics such as: instrument classification, classification of ambient environments/backgrounds (libraries, cars, ...), chorus detection, and meter analysis.<br /><br />Seems like I'm the list is still far from complete. As the following two theses indicate. If you know of any more that I'm missing please let me know. (Thank you <a href="www.linkedin.com/in/arijitbiswas">Arijit Biswas</a> for your help!)<br /><br />One that I missed is the work of Michael J. Bruderer on <A href="http://alexandria.tue.nl/extra2/200810559.pdf">Perception and Modeling of Segment Boundaries in Popular Music</a>. Which describes an interesting series of experiments in which Michael explores which cues listeners use when segmenting music and how they can be modeled.<br /><br />Another older one I've added is the work of <a href="http://www.linkedin.com/in/pichenettes">Olivier Gillet</a> <a href="http://pastel.paristech.org/2805/">Transcription des signaux percussifs. Application à l'analyse de scènes musicales audiovisuelles</a>. Olivier joined Google after his PhD where he worked on the optimization of Google's ad product and on technologies now being used by Google China Music. Olivier is now joining us at <a href="http://last.fm">Last.fm's</a> to work on fun next generation MIR technologies.<br /><br />I would also like to mention the Master thesis <a href="http://www.nada.kth.se/utbildning/grukth/exjobb/rapportlistor/2009/rapporter09/bernhardsson_erik_09071.pdf">Implementing a scalable music recommender</a> by <a href="http://www.linkedin.com/pub/erik-bernhardsson/4/397/725">Erik Bernhardsson</a>. I really like how Spotify has given him access to their data and let him publish the results. Seems like Spotify was also very happy with his work as they have hired him.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-87346491108054590772009-08-04T11:51:00.005+01:002009-08-04T12:07:46.423+01:00Bang & Olufsen and OFAI<a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://2.bp.blogspot.com/_ccNNXQ8yqZQ/SngUGAQ33QI/AAAAAAAAAbw/lExtBRoAtjM/s1600-h/bs5-1.jpg"><img style="cursor:pointer; cursor:hand;width: 256px; height: 198px;" src="http://2.bp.blogspot.com/_ccNNXQ8yqZQ/SngUGAQ33QI/AAAAAAAAAbw/lExtBRoAtjM/s400/bs5-1.jpg" border="0" alt=""id="BLOGGER_PHOTO_ID_5366061049394486530" /></a><br /><br />This is probably very old news to some, but I'm a bit behind in blogging.<br /><br />Yet another really cool product my former colleagues at OFAI have been working on over the last years: integration of content-based playlist generation technologies into the most awesome music hardware out there.<br /><br />Read more about it <a href="http://www.bang-olufsen.com/beosound5-digital-music_mots">here</a> (English) and <a href="http://futurezone.orf.at/stories/1608825/">here</a> (German).<br /><br />If you can't read German, the perhaps most interest bits: retail price per unit €4.765, 500 pre-orders before the device was available, OFAI and B&O will continue the collaboration, size of the features representing each song: 3.2KB.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-53390411978341467372009-08-04T11:33:00.006+01:002009-08-04T11:50:13.742+01:00FM4 Soundpark and OFAIMy former colleagues at OFAI have been experimenting with audio content based music recommendation for FM4 Soundpark for a while now. (I blogged about it <a href="http://mir-research.blogspot.com/2008/05/applying-audio-based-similarity.html">here</a>.) Now they (and in particular <a href="http://www.ofai.at/~martin.gasser/">Martin Gasser</a>) have taken it a few steps further and implemented a 3D exploration interface using the islands of music metaphor. <br /><br />It's all in Java and requires special privileges because it needs access to low level graphics card functions. But if you get passed those hurdles here's what you'd see:<br /><br /><a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://4.bp.blogspot.com/_ccNNXQ8yqZQ/SngRatgjS7I/AAAAAAAAAbo/SY6Krm1MjKI/s1600-h/soundpark.jpg"><img style="cursor:pointer; cursor:hand;width: 328px; height: 258px;" src="http://4.bp.blogspot.com/_ccNNXQ8yqZQ/SngRatgjS7I/AAAAAAAAAbo/SY6Krm1MjKI/s400/soundpark.jpg" border="0" alt=""id="BLOGGER_PHOTO_ID_5366058106602343346" /></a><br /><br />(Navigation: space bar, A,W,S,D and mouse)<br /><br />There is more information about this and other recommendation tools they have developed for Soundpark <a href="http://fm4.orf.at/stories/1622427/">here</a> (in German).Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-34073425265551861682009-05-03T00:49:00.003+01:002009-05-03T01:05:53.040+01:00Last.fm Artist ConnectionsPlaying with Last.fm similar artist data, trying to connect one artist to another through similar artists:<br /><br /><a href="http://www.last.fm/music/The+Beatles"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/100199.jpg" /></a><a href="http://www.last.fm/music/John+Lennon"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/303702.jpg" /></a><a href="http://www.last.fm/music/Sean+Lennon"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/270616.jpg" /></a><a href="http://www.last.fm/music/Joseph+Arthur"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/3681912.png" /></a><a href="http://www.last.fm/music/Howie+Day"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/615411.jpg" /></a><a href="http://www.last.fm/music/Teddy+Geiger"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/372523.jpg" /></a><a href="http://www.last.fm/music/Jonas+Brothers"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/8955949.jpg" /></a><br /><br /><a href="http://www.last.fm/music/The+Beatles">The Beatles</a> -> <a href="http://www.last.fm/music/John+Lennon">John Lennon</a> -> <a href="http://www.last.fm/music/Sean+Lennon">Sean Lennon</a> -> <a href="http://www.last.fm/music/Joseph+Arthur">Joseph Arthur</a> -> <a href="http://www.last.fm/music/Howie+Day">Howie Day</a> -> <a href="http://www.last.fm/music/Teddy+Geiger">Teddy Geiger</a> -> <a href="http://www.last.fm/music/Jonas+Brothers">Jonas Brothers</a><br /><br /><a href="http://www.last.fm/music/ABBA"><img alt="" src="http://userserve-ak.last.fm/serve/64s/53720.jpg" width="64"></a><a href="http://www.last.fm/music/Cher"><img alt="" src="http://userserve-ak.last.fm/serve/64s/376334.jpg" width="64"></a><a href="http://www.last.fm/music/Madonna"><img alt="" src="http://userserve-ak.last.fm/serve/64s/20801125.jpg" width="64"></a><a href="http://www.last.fm/music/R%C3%B3is%C3%ADn+Murphy"><img alt="" src="http://userserve-ak.last.fm/serve/64s/4166988.png" width="64"></a><a href="http://www.last.fm/music/Bj%C3%B6rk"><img alt="" src="http://userserve-ak.last.fm/serve/64s/270328.jpg" width="64"></a><a href="http://www.last.fm/music/Radiohead"><img alt="" src="http://userserve-ak.last.fm/serve/64s/7057955.jpg" width="64"></a><br /><br /><a href="http://www.last.fm/music/ABBA">ABBA</a> -> <a href="http://www.last.fm/music/Cher">Cher</a> -> <a href="http://www.last.fm/music/Madonna">Madonna</a> -> <a href="http://www.last.fm/music/R%C3%B3is%C3%ADn+Murphy">Róisín Murphy</a> -> <a href="http://www.last.fm/music/Bj%C3%B6rk">Björk</a> -> <a href="http://www.last.fm/music/Radiohead">Radiohead</a><br /><br /><a href="http://www.last.fm/music/Metallica"><img alt="" src="http://userserve-ak.last.fm/serve/64s/3679639.jpg" width="64"></a><a href="http://www.last.fm/music/Iron+Maiden"><img alt="" src="http://userserve-ak.last.fm/serve/64s/61088.jpg" width="64"></a><a href="http://www.last.fm/music/Paul+Di%27Anno"><img alt="" src="http://userserve-ak.last.fm/serve/64s/587298.jpg" width="64"></a><a href="http://www.last.fm/music/Numbers+From+The+Beast"><img alt="" src="http://userserve-ak.last.fm/serve/64s/11876379.jpg" width="64"></a><a href="http://www.last.fm/music/Scott+Lavender"><img alt="" src="http://userserve-ak.last.fm/serve/64s/2147947.jpg" width="64"></a><a href="http://www.last.fm/music/Ark+Sano"><img alt="" src="http://userserve-ak.last.fm/serve/64s/277466.jpg" width="64"></a><a href="http://www.last.fm/music/Fr%C3%A9d%C3%A9ric+Chopin"><img alt="" src="http://userserve-ak.last.fm/serve/64s/4757830.jpg" width="64"></a><a href="http://www.last.fm/music/Wolfgang+Amadeus+Mozart"><img alt="" src="http://userserve-ak.last.fm/serve/64s/13583481.jpg" width="64"></a><br /><br /><a href="http://www.last.fm/music/Metallica">Metallica</a> -> <a href="http://www.last.fm/music/Iron+Maiden">Iron Maiden</a> -> <a href="http://www.last.fm/music/Paul+Di%27Anno">Paul Di'Anno</a> -> <a href="http://www.last.fm/music/Numbers+From+The+Beast">Numbers From The Beast</a> -> <a href="http://www.last.fm/music/Scott+Lavender">Scott Lavender</a> -> <a href="http://www.last.fm/music/Ark+Sano">Ark Sano</a> -> <a href="http://www.last.fm/music/Fr%C3%A9d%C3%A9ric+Chopin">Frédéric Chopin</a> -> <a href="http://www.last.fm/music/Wolfgang+Amadeus+Mozart">Wolfgang Amadeus Mozart</a><br /><br /><a href="http://www.last.fm/music/Brian+Eno"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/782012.jpg" /></a><a href="http://www.last.fm/music/Roxy+Music"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/519416.jpg" /></a><a href="http://www.last.fm/music/Bryan+Ferry"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/3960576.jpg" /></a><a href="http://www.last.fm/music/Eurythmics"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/2226474.jpg" /></a><a href="http://www.last.fm/music/Annie+Lennox"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/2669950.jpg" /></a><a href="http://www.last.fm/music/Madonna"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/20801125.jpg" /></a><a href="http://www.last.fm/music/Britney+Spears"><img width="64" alt="" src="http://userserve-ak.last.fm/serve/64s/14877993.jpg" /></a><br /> <br /><a href="http://www.last.fm/music/Brian+Eno">Brian Eno</a> -> <a href="http://www.last.fm/music/Roxy+Music">Roxy Music</a> -> <a href="http://www.last.fm/music/Bryan+Ferry">Bryan Ferry</a> -> <a href="http://www.last.fm/music/Eurythmics">Eurythmics</a> -> <a href="http://www.last.fm/music/Annie+Lennox">Annie Lennox</a> -> <a href="http://www.last.fm/music/Madonna">Madonna</a> -> <a href="http://www.last.fm/music/Britney+Spears">Britney Spears</a>Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com3tag:blogger.com,1999:blog-2889894315257595136.post-60284336905122674682009-04-19T17:09:00.003+01:002009-04-19T17:20:00.089+01:00MIR PhD Thesis: Luís Gustavo Martins<a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://3.bp.blogspot.com/_ccNNXQ8yqZQ/SetNSiDj6-I/AAAAAAAAAaQ/d3dwedNv5ME/s1600-h/luis.jpg"><img style="float:right; margin:0 0 10px 10px;cursor:pointer; cursor:hand;width: 166px; height: 192px;" src="http://3.bp.blogspot.com/_ccNNXQ8yqZQ/SetNSiDj6-I/AAAAAAAAAaQ/d3dwedNv5ME/s400/luis.jpg" border="0" alt=""id="BLOGGER_PHOTO_ID_5326435965070470114" /></a><a href="http://web.me.com/lgustavomartins/">Luís Gustavo Martins</a> recently completed his PhD thesis titled <a href="http://web.me.com/lgustavomartins/research/phd/phd.html">A computational Framework for Sound Segregation in Music Signals</a>.<br /><br />From the abstract: <i>"[...] This dissertation proposes a flexible and extensible Computational Auditory Scene Analysis framework for modeling perceptual grouping in music listening. The goal of the proposed framework is to partition a monaural acoustical mixture into a perceptually motivated topological description of the sound scene (similar to the way a naive listener would perceive it) instead of attempting to accurately separate the mixture into its original and physical sources. [...]"</i><br /><br />Luis is probably best known in the MIR community for his contributions to <a href="http://marsyas.sness.net/">Marsyas</a> (the awesome open source software framework for audio processing with specific emphasis on MIR applications).<br /><br />If you know of any other dissertations missing in the <a href="http://www.pampalk.at/mir-phds">list of MIR PhDs</a> please let me know.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com1tag:blogger.com,1999:blog-2889894315257595136.post-31012107244717895712009-04-15T01:18:00.006+01:002009-04-15T01:34:51.672+01:00Visual Listening Charts (Part 2)Here's a follow-up to my <a href="http://mir-research.blogspot.com/2009/04/since-ismir-ive-been-listening-to.html">previous attempt</a> to visualize my listening history differently.<br /><br />Basically, I've been looking for a fun project that would give me plenty of reasons to play with <a href="http://matplotlib.sourceforge.net/">matplotlib</a>. <br /><br />My preliminary conclusion is that matplotlib is awesome. They couldn't have made it much easier to use for someone already familiar with Matlab.<br /><br /><a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://4.bp.blogspot.com/_ccNNXQ8yqZQ/SeUqCeajc9I/AAAAAAAAAaA/n4Osk3PYRcE/s1600-h/e1i45.png"><img style="cursor:pointer; cursor:hand;width: 332px; height: 360px;" src="http://4.bp.blogspot.com/_ccNNXQ8yqZQ/SeUqCeajc9I/AAAAAAAAAaA/n4Osk3PYRcE/s400/e1i45.png" border="0" alt=""id="noborder" usemap="#lastfm"/></a><map name="lastfm"><area shape="rect" coords="300,288,332,320" href="http://last.fm/music/Ayla Nereo" alt="Ayla Nereo (65 plays)" title="Ayla Nereo (65 plays)"><area shape="rect" coords="300,256,332,288" href="http://last.fm/music/Gilberto Gil" alt="Gilberto Gil (66 plays)" title="Gilberto Gil (66 plays)"><area shape="rect" coords="300,224,332,256" href="http://last.fm/music/Barney Kessel" alt="Barney Kessel (66 plays)" title="Barney Kessel (66 plays)"><area shape="rect" coords="300,192,332,224" href="http://last.fm/music/Le Volume Courbe" alt="Le Volume Courbe (67 plays)" title="Le Volume Courbe (67 plays)"><area shape="rect" coords="300,160,332,192" href="http://last.fm/music/Nick Drake" alt="Nick Drake (68 plays)" title="Nick Drake (68 plays)"><area shape="rect" coords="300,128,332,160" href="http://last.fm/music/Glenn Gould" alt="Glenn Gould (69 plays)" title="Glenn Gould (69 plays)"><area shape="rect" coords="300,96,332,128" href="http://last.fm/music/Kimya Dawson" alt="Kimya Dawson (83 plays)" title="Kimya Dawson (83 plays)"><area shape="rect" coords="300,64,332,96" href="http://last.fm/music/Essie Jain" alt="Essie Jain (88 plays)" title="Essie Jain (88 plays)"><area shape="rect" coords="300,32,332,64" href="http://last.fm/music/Ani DiFranco" alt="Ani DiFranco (93 plays)" title="Ani DiFranco (93 plays)"><area shape="rect" coords="300,0,332,32" href="http://last.fm/music/Jack Johnson" alt="Jack Johnson (118 plays)" title="Jack Johnson (118 plays)"></map>Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com1tag:blogger.com,1999:blog-2889894315257595136.post-25417550789845936352009-04-06T02:07:00.007+01:002009-04-06T03:36:04.207+01:00Recent MIR PhDsI'm slowly catching up. The following dissertations were added to the <a href="http://www.pampalk.at/mir-phds/">list of MIR PhDs</a>:<br /><br />"Real Time Automatic Harmonisation" by Giordano Cabra. I couldn't find a link to the thesis, but I found a <A href="http://video.google.com/videoplay?docid=7175739188944047625">video of the defense</a>. I'd love to see more defense videos (preferably in English).<br /><br />"<a href="http://cosmal.ucsd.edu/arshia/index.php?n=Main.Thesis">Modeling musical anticipation: From the time of music to the music of time</a>" by Arshia Cont.<br /><br />"<a href="http://www.iua.upf.edu/~ocelma/PhD/">Music Recommendation and Discovery in the Long Tail</a>" by Oscar Celma. I highly recommend it! <br /><br />"<a href="http://www.nue.tu-berlin.de/people/burred/phd/">From Sparse Models to Timbre Learning: New Methods for Musical Source Separation</a>" by Juan Jose Burred.<br /><br />UPDATE: I totally missed Yves' announcement on the Music-IR list on Friday. I've added him now too:<br /><br />"<a href="http://moustaki.org/phd/">A Distributed Music Information System</a>" by Yves Raimond.<br /><br />UPDATE 2: Almost forgot that Kris finished recently too:<br /><br />"<a href="http://www.kriswest.com/wp-content/uploads/2009/01/kw_thesis_final.pdf">Novel Techniques for Audio Music Classification and Search</a>" by Kris West.<br /><br />Please send me any I might have missed - thanks!Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-12067544322813084612009-04-05T23:36:00.004+01:002009-04-06T00:05:55.194+01:00Since ISMIR I've been listening to...I'm currently a bit fascinated with different ways of representing my listening history. <br /><br />I really like <a href="http://lastgraph.aeracode.org/">LastGraph</a> which was inspired by <a href="http://www.leebyron.com/what/lastfm/">Lee Byron</a>. The graphs show how my listening preferences (and in particular how often I listen to my favorite artists) change over time.<br /><br />I also like <a href="http://playground.audioscrobbler.com/martind/chart_arcs/">these visualizations</a> by Martin. They show how artists move up or down over time in my chart.<br /><br />Recently I tried to visualize my top artist chart using artist images, and readjusting their sizes so they correspond to how often I've listened to each artist respectively. Here's what I've been listening to since my last blogpost at ISMIR 2008:<br /><br /><a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://3.bp.blogspot.com/_ccNNXQ8yqZQ/SdjXmZPXlBI/AAAAAAAAAZo/991zl280fes/s1600-h/106055.jpg"><img style="cursor:pointer; cursor:hand;width: 385px; height: 290px;" src="http://3.bp.blogspot.com/_ccNNXQ8yqZQ/SdjXmZPXlBI/AAAAAAAAAZo/991zl280fes/s400/106055.jpg" border="0" alt=""id="noborder" usemap="#lastfm" /></a><map name="lastfm"><area shape="rect" coords="48,234,96,287" href="http://last.fm/music/Kaki King" alt="Kaki King (22 plays)" title="Kaki King (22 plays)"><area shape="rect" coords="1,235,49,288" href="http://last.fm/music/Ani DiFranco" alt="Ani DiFranco (22 plays)" title="Ani DiFranco (22 plays)"><area shape="rect" coords="342,142,383,204" href="http://last.fm/music/Cake" alt="Cake (22 plays)" title="Cake (22 plays)"><area shape="rect" coords="292,142,343,195" href="http://last.fm/music/Yo-Yo Ma" alt="Yo-Yo Ma (23 plays)" title="Yo-Yo Ma (23 plays)"><area shape="rect" coords="249,156,292,220" href="http://last.fm/music/Nick Drake" alt="Nick Drake (24 plays)" title="Nick Drake (24 plays)"><area shape="rect" coords="202,136,250,194" href="http://last.fm/music/Brian Eno" alt="Brian Eno (24 plays)" title="Brian Eno (24 plays)"><area shape="rect" coords="155,148,203,206" href="http://last.fm/music/Robert Lockwood Jr." alt="Robert Lockwood Jr. (24 plays)" title="Robert Lockwood Jr. (24 plays)"><area shape="rect" coords="106,161,155,218" href="http://last.fm/music/Davy Graham" alt="Davy Graham (24 plays)" title="Davy Graham (24 plays)"><area shape="rect" coords="53,181,107,235" href="http://last.fm/music/Kimya Dawson" alt="Kimya Dawson (25 plays)" title="Kimya Dawson (25 plays)"><area shape="rect" coords="1,181,54,235" href="http://last.fm/music/Antônio Carlos Jobim" alt="Antônio Carlos Jobim (25 plays)" title="Antônio Carlos Jobim (25 plays)"><area shape="rect" coords="304,95,365,142" href="http://last.fm/music/Radiohead" alt="Radiohead (25 plays)" title="Radiohead (25 plays)"><area shape="rect" coords="252,95,305,156" href="http://last.fm/music/Barney Kessel" alt="Barney Kessel (28 plays)" title="Barney Kessel (28 plays)"><area shape="rect" coords="203,67,253,137" href="http://last.fm/music/Baden Powell" alt="Baden Powell (30 plays)" title="Baden Powell (30 plays)"><area shape="rect" coords="151,82,203,149" href="http://last.fm/music/Art Tatum" alt="Art Tatum (30 plays)" title="Art Tatum (30 plays)"><area shape="rect" coords="90,82,152,162" href="http://last.fm/music/Pablo Casals" alt="Pablo Casals (43 plays)" title="Pablo Casals (43 plays)"><area shape="rect" coords="1,116,91,181" href="http://last.fm/music/Herb Ellis" alt="Herb Ellis (51 plays)" title="Herb Ellis (51 plays)"><area shape="rect" coords="279,1,343,96" href="http://last.fm/music/Julian Bream" alt="Julian Bream (53 plays)" title="Julian Bream (53 plays)"><area shape="rect" coords="181,1,280,68" href="http://last.fm/music/John Fahey" alt="John Fahey (58 plays)" title="John Fahey (58 plays)"><area shape="rect" coords="78,1,182,83" href="http://last.fm/music/Essie Jain" alt="Essie Jain (74 plays)" title="Essie Jain (74 plays)"><area shape="rect" coords="1,1,79,117" href="http://last.fm/music/Jack Johnson" alt="Jack Johnson (79 plays)" title="Jack Johnson (79 plays)"></map><br /><br />I think this montage says it all: I like black and white music from solo artists playing guitars.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com5tag:blogger.com,1999:blog-2889894315257595136.post-43234201213615162202009-04-05T23:02:00.004+01:002009-04-05T23:36:41.900+01:00C++ Software Engineer, Data & RecommendationsIf you are interested in data structures, algorithms, and scalability, you might also be interested in <a href="http://www.last.fm/about/jobs#job_C%2B%2B+Software+Engineer%2C+Data+and+Recommendations">joining</a> the data and recommendations team at Last.fm.<br /><br />You'd be working with Norman Casagrande, Mark Levy, me and other highly motivated colleagues trying to solve lots of fun challenges in music information retrieval.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-29776343547503133582008-09-18T22:02:00.009+01:002008-09-19T14:00:31.853+01:00ISMIR 2008 DemosOne of the best parts about ISMIR was the <a href="http://ismir2008.ismir.net/program#demo">demo session</a>. <br /><br />Paul Lamere and Francois Maillet demonstrated Explaura which enables users to directly interact with tag clouds by resizing individual tags for tag-based recommendations. Increasing the size of a tag puts more emphasis on it, shrinking it reduces the impact to the point where it's ignored. Increasing the "negative size" of a tag filters results by the respective tag. They also allow combining artists with tags in the search query. Paul <a href="http://blogs.sun.com/plamere/entry/the_aura_music_explaura">blogged</a> about it. There's also a short ISMIR <a href="http://ismir2008.ismir.net/latebreak/lamere.pdf">abstract</a>. I like the idea of interacting with the individual tags in a tag cloud and found it very intuitive to use.<br /><br />Another demo which was presented (and I already <a href="http://mir-research.blogspot.com/2008/05/applying-audio-based-similarity.html">previously blogged</a> about) was the work of Martin Gasser and his colleagues on how they <a href="http://ismir2008.ismir.net/latebreak/gasser.pdf">integrated audio-similarity</a> into FM4 Soundpark (a platform for independent Austrian artists). The numbers they presented show that using audio-similarity helped Soundpark users find older and more obscure items in the catalogue. It would be nice to see more real world applications using audio-similarity.<br /><br />Òscar Celma and Marcelo Nunes presented GeoMuzik which allows drawing a route on a world map. Their system then generates a playlist according to this route. They implemented genre/tag filters. They can also visualize the artists in <a href="http://last.fm/user/e1i45">my Last.fm profile</a> on top of a map. There's an <a href="http://ismir2008.ismir.net/latebreak/celma.pdf">ISMIR abstract</a>. I liked the demo very much and would like to play a bit more with it. The picture below shows a screenshot of a playlist generated from the interface.<br /><br /><a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://4.bp.blogspot.com/_ccNNXQ8yqZQ/SNOcLqAQiHI/AAAAAAAAAPU/3TJztwn7dBg/s1600-h/playlist2.png"><img style="cursor:pointer; cursor:hand;" src="http://4.bp.blogspot.com/_ccNNXQ8yqZQ/SNOcLqAQiHI/AAAAAAAAAPU/3TJztwn7dBg/s400/playlist2.png" border="0" alt=""id="BLOGGER_PHOTO_ID_5247709714884626546" /></a><br /><br />Luke Barrington and his colleagues demonstrated their new tagging game <a href="http://ismir2008.ismir.net/latebreak/barrington.pdf">Herd it</a> which they implemented in the Facebook application framework. If I understood them correctly they still want to do some testing before releasing it publicly, so I'll write more when they are ready. Anyway, I've heard from others how difficult it can be to get something to work seamlessly on Facebook. I'm impressed that Luke and his colleagues are doing this. It would be nice to see researchers use Facebook and similar platforms more frequently for their work.<br /><br />One demo I unfortunately didn't have enough time to see (but at least I got the handout) was the work <a href="http://thesis.flyingpudding.com/">Anita Lillie</a> presented. There's also a <a href="http://thesis.flyingpudding.com/?cat=13">video</a>. In the video Anita shows different ways to visualize the same music collection from different perspectives using a PCA (principal component analysis, a linear projection of a high-dimensional space onto 2-dimensions). Seems like Anita just finished her MSc thesis on <a href="http://thesis.flyingpudding.com/documents/Anita_FINAL_THESIS.pdf">MusicBox: Navigating the space of your music</a>. I've been told the demonstration was implemented in <a href="http://processing.org">processing</a>. Very nice! One thing I didn't see were playcounts. It would be great if playcounts (or ratings per track) could also be visualized (size of the circles?). The picture below shows a screenshot of her MusicBox.<br /><br /><a onblur="try {parent.deselectBloggerImageGracefully();} catch(e) {}" href="http://2.bp.blogspot.com/_ccNNXQ8yqZQ/SNOd9P9cMqI/AAAAAAAAAPk/iGYAHrgZxcQ/s1600-h/musicbox-screenshot.jpg"><img style="cursor:pointer; cursor:hand;" src="http://2.bp.blogspot.com/_ccNNXQ8yqZQ/SNOd9P9cMqI/AAAAAAAAAPk/iGYAHrgZxcQ/s400/musicbox-screenshot.jpg" border="0" alt=""id="BLOGGER_PHOTO_ID_5247711666398573218" /></a><br /><br />Another demo I really liked was <a href="http://oldwww.iiia.csic.es/~claudio/">Claudio Baccigalupo's</a> work on <a href="http://www.iiia.csic.es/~claudio/keynotes/Baccigalupo-2007-ICCBR-Presentation.pdf">Poolcasting</a>. The idea is to have several people tune into the same radio station at the same time, and to have them rate the songs, and use that rating to optimize the overall listening experience. I could easily see Gwen and myself sharing the same radio stream frequently. What I found particularly interesting is how Claudio tries to maximize happiness for everyone in a situation where compromises are unavoidable and where he does not want the majority to completely ruin the experience for an individual.<br /><br />Btw, if you like demos, you might also be interested in <a href="http://playground.last.fm">Last.fm's playground</a>.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-33272831795552579432008-09-17T20:05:00.003+01:002008-09-17T20:32:49.419+01:00MIREX 2008<a href="http://www.music-ir.org/mirex/2008/index.php/Main_Page">This year's MIREX</a> evaluation task has been one of my personal ISMIR 2008 highlights. Stephen Downie and his team computed more numbers than I could possible keep track of for lots of different algorithms in 12 different MIR tasks. That's a lot more than in any of the previous years, and that's a lot of interesting data to dig into.<br /><br />I've been particularly interested in the <a href="http://www.music-ir.org/mirex/2008/index.php/Audio_Tag_Classification_Results#Beta-Binomial_test_results">auto-tagging task</a>. It's the first time MIREX ran this form of task, and there have been only few research papers in the MIR community on the subject. As far as I understood there is no agreement yet as to how to exactly evaluate the algorithms, which is also reflected on the result page. Kris West has added information on the statistical significant of the results which show that none of the submissions was consistently and significantly better than others. Nevertheless, there's a lot to learn from the evaluation and I hope we'll see many more participants next year.<br /><br />Paul has a <a href="http://blogs.sun.com/plamere/entry/ismir_2008_mirex_panel">good summary</a> of the discussion of this year's MIREX panel.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-34884716835540807682008-09-17T13:01:00.004+01:002008-09-17T14:36:54.128+01:001000 years of music to listen toYoungmoo Kim had asked everyone on the ISMIR recommendation panel to briefly summarize what they think will happen in the next 5 years of music recommendation. However, it's really hard to do so in less than 4 minutes.<br /><br />From my perspective the most interesting development in the next 5 years will be the increase in the amount of data we will be working with. We will have a lot more of the same and we will have additional sources. Combining different sources is an interesting challenge, but the main challenge will be to scale things up.<br /><br />All of this additional information will lead to much better recommendations overall, and in particular in the long tail. We'll be able to detect new trends such as an up-and-coming artists or the emergence of a new subgenre much sooner. We'll be able to localize recommendations a lot more.<br /><br />At the same time there'll obviously be a lot more music to choose from. I'd roughly estimate about 200 million tracks in Last.fm's recommendation engine in the next 5 years. That's more than 1000 years of continuous listening. Subcultures and genres will emerge faster.<br /><br />In 5 years recommendation engines will have a much better understanding of listeners. While Last.fm, Pandora, and others already do a lot to understand what listeners are interested in, I'm sure there is room for a lot more improvements.<br /><br />Another interesting development I'm looking forward to is data portability and openness. In particular, I'm looking forward to users being able to move freely with their personal data from one site to another. Similar to how Last.fm users can already today allow other sites to access their data.<br /><br />I'm also expecting to see a lot more artists and labels embrace recommendation engines. Similar to SEO (search engine optimization) more artist and labels will try to do a lot more REO (recommendation engine optimization). <br /><br />Obviously mobile applications will be very important, and so will mobile music recommendations. And I have no doubts that human-to-human recommendations (which are strongly supported by Last.fm) will continue to be very important, maybe even more than they are today.<br /><br />Anthony Volodkin made a great point that we'll see a lot happen in terms of user interfaces, how recommendations are represented, how recommendations are explained. I believe Paul Lamere would call that steerable and transparent recommendations. I like how Last.fm explains recommendations by explaining a recommendation in terms of a bunch of similar artists I'm familiar with. However, there's obviously room for a lot more. On the other side, I wouldn't mind no explanation at all, as long as every recommendation is spot on. Anthony also made a great point by pointing to <a href="http://www.thesixtyone.com">playful discovery systems</a>. <br /><br />I believe it was Brian Whitman who said that recommendations will be a commodity. Every music site will have recommendations. Just like almost every web 2.0 site out there supports tagging. I believe Etienne Handman made a similar point when he previously explained to me why he expects the word "personalization" to fade away. Everything will be personalized, it will be the default option.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-47360334228852501402008-09-16T20:53:00.004+01:002008-09-16T21:08:54.218+01:00ISMIR ThoughtsInspired by <a href="http://blogs.sun.com/plamere/">Paul's constant flow</a> of ISMIR blog posts I thought I should give it a try and post some thoughts as well.<br /><br />First of all, the organizers did a wonderful job organizing ISMIR. I <a href="http://mir-research.blogspot.com/2008/08/ismir-proceedings-2008-wow.html">already wrote about</a> what I think about the electronic proceedings. I was also very happy to see that they did not waste unnecessary resources and skipped the silly conference bag thing.<br /><br />I very much enjoyed giving the social tags tutorial with Paul. It worked out really well, and although I knew Paul's slides since weeks, I found it fascinating to listen to Paul talk about them.<br /><br />So far ISMIR has by far exceeded my expectations. I've had the pleasure to meet many in person that I previously hadn't had the opportunity to meet. I've also had the pleasure to see many very interesting posters. Unfortunately I've also managed to miss many that I wanted to see. I guess there's never enough time to see everything.<br /><br />Last night's banquet was great too. In particular I enjoyed the conversations with Etienne from Pandora.<br /><br />The recommendation panel today was fun, too.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-91861973433670492062008-09-11T22:23:00.004+01:002008-09-11T23:03:37.304+01:00ISMIR 2008 Tutorial: Social Tags and Music Information RetrievalWhen Paul originally asked me if I'd be interested in helping him put together a tutorial proposal for ISMIR I was a bit reluctant. I did an ISMIR tutorial <a href="http://ismir2005.ismir.net/documents/pampalk_ismir_05_similarity_tutorial_c.pdf">a long time ago</a>, and I didn't forget how much work it was (although it was only a one hour mini tutorial). In fact, only last year Paul and Oscar told me how much work it was to put together their <a href="http://mtg.upf.edu/~ocelma/MusicRecommendationTutorial-ISMIR2007/">recommendation tutorial</a> (which I liked <a href="http://mir-research.blogspot.com/2007/09/ismir-highlight-recommendation-tutorial.html">a lot</a>). <br /><br />Anyway, somehow I couldn't say no and looking back I don't regret it at all. I'm totally fascinated by social tags. There's no tutorial topic I'd rather talk about. Working together with Paul has been a great pleasure, and I've learned a lot. However, I'm very much looking forward to have a free weekend or even just a free evening again. (Free as in not-MIR-related.)<br /><br />Paul and I have put together about 200 slides for our <a href="http://ismir2008.ismir.net/tutorials">tutorial</a>. I think we still need to figure out our time budget. Hopefully we'll have plenty of time for interesting discussions.<br /><br />Btw, as part of the tutorial we started compiling a list of relevant papers. That list started to grow. Then we thought it would be a good idea to group papers into topics (e.g. autotagging). Then we realized that several papers were in several categories... which is when we moved everything to <a href="http://delicious.com">delicious</a>. In particular, we started using the tag "SocialMusicResearch" to mark interesting things we found in the Internet. Here's <A href="http://delicious.com/search?p=socialmusicresearch">a list</a> of some of the items we have tagged. We hope that others will start using that tag as well.<br /><br />Btw, if you are going to ISMIR, please say hi! If you don't know what I look like: try to spot the guy wearing a Last.fm t-shirt.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com3tag:blogger.com,1999:blog-2889894315257595136.post-45153056462914462762008-08-27T23:50:00.004+01:002008-08-27T23:57:59.651+01:00ISMIR Proceedings 2008! Wow!I'm extremely impressed. The ISMIR proceedings <a href="http://www.lulu.com/content/3804316">are online</a>. Whoever wants a printed copy can organize it themselves (it couldn't be much easier). Some might also want to only print the papers they are interested in. And some might be happy to have only an electronic version. <br /><br />It's always been a pain to drag the heavy ISMIR proceedings home. And it always felt like a huge waste of paper.<br /><br />I heard Juan and Youngmoo talk about this idea a year ago in Vienna (at last year's ISMIR). I'm very happy to see that they found a solution that should make everyone happy.<br /><br />Juan writes in his email:<br /><i>We hope that you will like this new approach to printing the proceedings which we intend to be more cost effective, more convenient, and, with luck, more environmentally friendly than mass printing of proceedings for all attendees who may not wish to carry a printed copy around.</i><br /><br />Wonderful! :-)Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-46047769343366844442008-08-25T14:04:00.003+01:002008-08-25T14:06:48.449+01:00Librarians and Tags<A href="http://blog.dbtune.org/">Yves</a> pointed me to this really nice presentation by a librarian who seems to have a really good understanding of tagging. The only part missing in that presentation is music.<br /><br /><div style="width:425px;text-align:left" id="__ss_472422"><a style="font:14px Helvetica,Arial,Sans-serif;display:block;margin:12px 0 3px 0;text-decoration:underline;" href="http://www.slideshare.net/ellyssa/libraries-and-the-hive-mind-folksonomies-and-tagging?src=embed" title="Libraries and the Hive Mind: Folksonomies and Tagging">Libraries and the Hive Mind: Folksonomies and Tagging</a><object style="margin:0px" width="425" height="355"><param name="movie" value="http://static.slideshare.net/swf/ssplayer2.swf?doc=folksonomiesmetro-1213727058174924-8&stripped_title=libraries-and-the-hive-mind-folksonomies-and-tagging" /><param name="allowFullScreen" value="true"/><param name="allowScriptAccess" value="always"/><embed src="http://static.slideshare.net/swf/ssplayer2.swf?doc=folksonomiesmetro-1213727058174924-8&stripped_title=libraries-and-the-hive-mind-folksonomies-and-tagging" type="application/x-shockwave-flash" allowscriptaccess="always" allowfullscreen="true" width="425" height="355"></embed></object><div style="font-size:11px;font-family:tahoma,arial;height:26px;padding-top:2px;">View SlideShare <a style="text-decoration:underline;" href="http://www.slideshare.net/ellyssa/libraries-and-the-hive-mind-folksonomies-and-tagging?src=embed" title="View Libraries and the Hive Mind: Folksonomies and Tagging on SlideShare">presentation</a> or <a style="text-decoration:underline;" href="http://www.slideshare.net/upload?src=embed">Upload</a> your own. (tags: <a style="text-decoration:underline;" href="http://slideshare.net/tag/tagging">tagging</a> <a style="text-decoration:underline;" href="http://slideshare.net/tag/tags">tags</a>)</div></div>Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-10348448192294214382008-08-25T03:15:00.007+01:002008-08-25T04:11:31.555+01:00Getting Last.fm Tags for MP3s with PythonPaul (who is already distributing a <a href="http://blogs.sun.com/plamere/entry/open_research_the_data_lastfm">large chunk</a> of Last.fm tags) and I are planing to include a few slides in our <a href="http://blogs.sun.com/plamere/entry/social_tags_and_mir_a">ISMIR tutorial</a> on how to obtain tag data. <br /><br />Below is some Python code that basically takes an MP3 file as input and outputs a list of Last.fm tags (for both artist and track). The MP3s don't need correct ID3 tags, but they need to be full length (clips won't work).<br /><br />The Python code uses Norman's command line <a href="http://www.last.fm/user/nova77LF/journal/2007/10/12/4kaf_fingerprint_(command_line)_client">finger printing client</a> to find the correct artist and track name. The path to the executable needs to be set in the code. Norman supports Win32, OSX Intel, Linux - 32.<br /><br />The output is written to a file. For each MP3 file passed as argument there are up to two rows in the output file: one for the artist tags, and one for the track tags. Each row has the format: "<mp3filename> <encoded artist or artist/track name> <tag> <score> [<tag> <score> ...]". Tabs are used as delimiters. <br /><br />The data from the <a href="http://www.audioscrobbler.net/data/webservices/">Last.fm API</a> is available under the <a href="http://creativecommons.org/licenses/by-nc-sa/2.0/uk/">Creative Commons Attribution-Non-Commercial-Share Alike License</a>.<br /><br />Btw, special thanks to Eric Casteleijn for various Python recommendations (lxml etc). (Which reminds me that I still need to fix the other Python code I posted.) As usual any feedback is much appreciated.<br /><br /><pre style='color:#000000;background:#ffffff;'><span style='color:#800000; font-weight:bold; '>import</span> subprocess<span style='color:#808030; '>,</span> sys<span style='color:#808030; '>,</span> re<span style='color:#808030; '>,</span> time<span style='color:#808030; '>,</span> urllib<br /><span style='color:#800000; font-weight:bold; '>from</span> lxml <span style='color:#800000; font-weight:bold; '>import</span> etree<br /><br />FP_CLIENT_PATH <span style='color:#808030; '>=</span> <span style='color:#0000e6; '>'"C:\\fpclient\\lastfmfpclient.exe"'</span><br />MAX_RETRIES_URL_OPEN <span style='color:#808030; '>=</span> <span style='color:#008c00; '>5</span><br /><br /><span style='color:#800000; font-weight:bold; '>def</span> getArtistTrack<span style='color:#808030; '>(</span>mp3FileName<span style='color:#808030; '>)</span><span style='color:#808030; '>:</span> <span style='color:#696969; '># ret: (artist, track)</span><br /> command <span style='color:#808030; '>=</span> FP_CLIENT_PATH <span style='color:#808030; '>+</span> <span style='color:#0000e6; '>' '</span> <span style='color:#808030; '>+</span> mp3FileName<br /> pipe <span style='color:#808030; '>=</span> subprocess<span style='color:#808030; '>.</span>Popen<span style='color:#808030; '>(</span>command<span style='color:#808030; '>,</span> \<br /> stdout<span style='color:#808030; '>=</span>subprocess<span style='color:#808030; '>.</span>PIPE<span style='color:#808030; '>)</span><span style='color:#808030; '>.</span>stdout<br /> <span style='color:#800000; font-weight:bold; '>for</span> line <span style='color:#800000; font-weight:bold; '>in</span> pipe<span style='color:#808030; '>:</span><br /> mo <span style='color:#808030; '>=</span> re<span style='color:#808030; '>.</span>search<span style='color:#808030; '>(</span><span style='color:#0000e6; '>'<url>.*/([^/]+)/_/(.+)<'</span><span style='color:#808030; '>,</span>line<span style='color:#808030; '>)</span><br /> <span style='color:#800000; font-weight:bold; '>if</span> mo<span style='color:#808030; '>:</span><br /> <span style='color:#800000; font-weight:bold; '>return</span> urllib<span style='color:#808030; '>.</span>quote<span style='color:#808030; '>(</span>mo<span style='color:#808030; '>.</span>group<span style='color:#808030; '>(</span><span style='color:#008c00; '>1</span><span style='color:#808030; '>)</span><span style='color:#808030; '>)</span><span style='color:#808030; '>,</span> \<br /> urllib<span style='color:#808030; '>.</span>quote<span style='color:#808030; '>(</span>mo<span style='color:#808030; '>.</span>group<span style='color:#808030; '>(</span><span style='color:#008c00; '>2</span><span style='color:#808030; '>)</span><span style='color:#808030; '>)</span><br /> <span style='color:#800000; font-weight:bold; '>print</span> <span style='color:#0000e6; '>"ERROR: failed to get artist/track for: "</span> <span style='color:#808030; '>+</span> \<br /> mp3FileName<br /><br /><span style='color:#800000; font-weight:bold; '>def</span> crawlTags<span style='color:#808030; '>(</span>url<span style='color:#808030; '>)</span><span style='color:#808030; '>:</span> <span style='color:#696969; '># ret: [(tag, count), ...]</span><br /> <span style='color:#800000; font-weight:bold; '>for</span> i <span style='color:#800000; font-weight:bold; '>in</span> <span style='color:#e34adc; '>xrange</span><span style='color:#808030; '>(</span>MAX_RETRIES_URL_OPEN<span style='color:#808030; '>)</span><span style='color:#808030; '>:</span><br /> tagCounts <span style='color:#808030; '>=</span> <span style='color:#808030; '>[</span><span style='color:#808030; '>]</span><br /> time<span style='color:#808030; '>.</span>sleep<span style='color:#808030; '>(</span><span style='color:#008c00; '>1</span><span style='color:#808030; '>)</span> <span style='color:#696969; '># be nice!</span><br /> <span style='color:#800000; font-weight:bold; '>try</span><span style='color:#808030; '>:</span><br /> root <span style='color:#808030; '>=</span> etree<span style='color:#808030; '>.</span>parse<span style='color:#808030; '>(</span><br /> urllib<span style='color:#808030; '>.</span>urlopen<span style='color:#808030; '>(</span>url<span style='color:#808030; '>)</span><span style='color:#808030; '>)</span><span style='color:#808030; '>.</span>getroot<span style='color:#808030; '>(</span><span style='color:#808030; '>)</span><br /> <span style='color:#800000; font-weight:bold; '>except</span> <span style='color:#e34adc; '>IOError</span><span style='color:#808030; '>:</span><br /> <span style='color:#800000; font-weight:bold; '>print</span> <span style='color:#0000e6; '>"(%d/%d) Failed trying to get: %s."</span> <span style='color:#808030; '>%</span> \<br /> <span style='color:#808030; '>(</span>i<span style='color:#808030; '>,</span> MAX_RETRIES_URL_OPEN<span style='color:#808030; '>,</span> url<span style='color:#808030; '>)</span><br /> <span style='color:#800000; font-weight:bold; '>else</span><span style='color:#808030; '>:</span><br /> <span style='color:#800000; font-weight:bold; '>for</span> tag <span style='color:#800000; font-weight:bold; '>in</span> root<span style='color:#808030; '>.</span><span style='color:#e34adc; '>iter</span><span style='color:#808030; '>(</span><span style='color:#0000e6; '>'tag'</span><span style='color:#808030; '>)</span><span style='color:#808030; '>:</span><br /> tagCounts<span style='color:#808030; '>.</span>append<span style='color:#808030; '>(</span><br /> <span style='color:#808030; '>(</span>tag<span style='color:#808030; '>.</span>find<span style='color:#808030; '>(</span><span style='color:#0000e6; '>'name'</span><span style='color:#808030; '>)</span><span style='color:#808030; '>.</span>text<span style='color:#808030; '>,</span> \<br /> tag<span style='color:#808030; '>.</span>find<span style='color:#808030; '>(</span><span style='color:#0000e6; '>'count'</span><span style='color:#808030; '>)</span><span style='color:#808030; '>.</span>text<span style='color:#808030; '>)</span><span style='color:#808030; '>)</span><br /> <span style='color:#800000; font-weight:bold; '>return</span> tagCounts<br /><br /><span style='color:#800000; font-weight:bold; '>def</span> tags<span style='color:#808030; '>(</span>prefix<span style='color:#808030; '>,</span> items<span style='color:#808030; '>,</span> outStream<span style='color:#808030; '>)</span><span style='color:#808030; '>:</span> <span style='color:#696969; '># crawl and write</span><br /> <span style='color:#800000; font-weight:bold; '>for</span> mp3FileName<span style='color:#808030; '>,</span> item <span style='color:#800000; font-weight:bold; '>in</span> items<span style='color:#808030; '>:</span><br /> url <span style='color:#808030; '>=</span> prefix <span style='color:#808030; '>+</span> item <span style='color:#808030; '>+</span> <span style='color:#0000e6; '>'/toptags.xml'</span><br /> <span style='color:#800000; font-weight:bold; '>print</span> url<br /> tagCounts <span style='color:#808030; '>=</span> crawlTags<span style='color:#808030; '>(</span>url<span style='color:#808030; '>)</span><br /> outStream<span style='color:#808030; '>.</span>write<span style='color:#808030; '>(</span><span style='color:#0000e6; '>'%s\t%s\t%s\n'</span> <span style='color:#808030; '>%</span><br /> <span style='color:#808030; '>(</span>mp3FileName<span style='color:#808030; '>,</span> item<span style='color:#808030; '>,</span> <span style='color:#0000e6; '>'\t'</span><span style='color:#808030; '>.</span>join<span style='color:#808030; '>(</span><br /> tag <span style='color:#808030; '>+</span> <span style='color:#0000e6; '>'\t'</span> <span style='color:#808030; '>+</span> <span style='color:#e34adc; '>str</span><span style='color:#808030; '>(</span>count<span style='color:#808030; '>)</span><br /> <span style='color:#800000; font-weight:bold; '>for</span> tag<span style='color:#808030; '>,</span> count <span style='color:#800000; font-weight:bold; '>in</span> tagCounts<span style='color:#808030; '>)</span><span style='color:#808030; '>)</span><span style='color:#808030; '>)</span> <br /><br /><span style='color:#800000; font-weight:bold; '>def</span> main<span style='color:#808030; '>(</span><span style='color:#808030; '>)</span><span style='color:#808030; '>:</span><br /> <span style='color:#800000; font-weight:bold; '>if</span> <span style='color:#e34adc; '>len</span><span style='color:#808030; '>(</span>sys<span style='color:#808030; '>.</span>argv<span style='color:#808030; '>)</span><span style='color:#808030; '><</span><span style='color:#008c00; '>3</span><span style='color:#808030; '>:</span><br /> <span style='color:#800000; font-weight:bold; '>print</span> <span style='color:#0000e6; '>'USAGE: python getTags.py '</span> <span style='color:#808030; '>+</span> \<br /> <span style='color:#0000e6; '>'<outFile> <f1.mp3> [<f2.mp3> ...]'</span><br /> sys<span style='color:#808030; '>.</span><span style='color:#e34adc; '>exit</span><span style='color:#808030; '>(</span><span style='color:#008c00; '>2</span><span style='color:#808030; '>)</span><br /> outFile <span style='color:#808030; '>=</span> sys<span style='color:#808030; '>.</span>argv<span style='color:#808030; '>[</span><span style='color:#008c00; '>1</span><span style='color:#808030; '>]</span><br /> mp3FileNames <span style='color:#808030; '>=</span> sys<span style='color:#808030; '>.</span>argv<span style='color:#808030; '>[</span><span style='color:#008c00; '>2</span><span style='color:#808030; '>:</span><span style='color:#808030; '>]</span><br /> artists <span style='color:#808030; '>=</span> set<span style='color:#808030; '>(</span><span style='color:#808030; '>)</span><br /> artistTracks <span style='color:#808030; '>=</span> set<span style='color:#808030; '>(</span><span style='color:#808030; '>)</span><br /> <span style='color:#800000; font-weight:bold; '>for</span> mp3FileName <span style='color:#800000; font-weight:bold; '>in</span> mp3FileNames<span style='color:#808030; '>:</span><br /> <span style='color:#800000; font-weight:bold; '>print</span> <span style='color:#0000e6; '>'Fingerprinting: '</span> <span style='color:#808030; '>+</span> mp3FileName<br /> artist<span style='color:#808030; '>,</span>track <span style='color:#808030; '>=</span> getArtistTrack<span style='color:#808030; '>(</span>mp3FileName<span style='color:#808030; '>)</span><br /> artists<span style='color:#808030; '>.</span>add<span style='color:#808030; '>(</span><span style='color:#808030; '>(</span>mp3FileName<span style='color:#808030; '>,</span> artist<span style='color:#808030; '>)</span><span style='color:#808030; '>)</span><br /> artistTracks<span style='color:#808030; '>.</span>add<span style='color:#808030; '>(</span><span style='color:#808030; '>(</span>mp3FileName<span style='color:#808030; '>,</span><br /> artist <span style='color:#808030; '>+</span> <span style='color:#0000e6; '>'/'</span> <span style='color:#808030; '>+</span> track<span style='color:#808030; '>)</span><span style='color:#808030; '>)</span><br /><br /> <span style='color:#800000; font-weight:bold; '>print</span> <span style='color:#0000e6; '>'start crawling tags'</span><br /> o <span style='color:#808030; '>=</span> <span style='color:#e34adc; '>open</span><span style='color:#808030; '>(</span>outFile<span style='color:#808030; '>,</span><span style='color:#0000e6; '>'w'</span><span style='color:#808030; '>)</span><span style='color:#808030; '>;</span><br /> tags<span style='color:#808030; '>(</span><span style='color:#0000e6; '>'http://ws.audioscrobbler.com/1.0/artist/'</span><span style='color:#808030; '>,</span> \<br /> artists<span style='color:#808030; '>,</span> o<span style='color:#808030; '>)</span><br /> tags<span style='color:#808030; '>(</span><span style='color:#0000e6; '>'http://ws.audioscrobbler.com/1.0/track/'</span><span style='color:#808030; '>,</span> \<br /> artistTracks<span style='color:#808030; '>,</span> o<span style='color:#808030; '>)</span> <br /> o<span style='color:#808030; '>.</span>close<span style='color:#808030; '>(</span><span style='color:#808030; '>)</span> <br /><br /><span style='color:#800000; font-weight:bold; '>if</span> <span style='color:#e34adc; '>__name__</span> <span style='color:#808030; '>=</span><span style='color:#808030; '>=</span> <span style='color:#0000e6; '>"__main__"</span><span style='color:#808030; '>:</span><br /> main<span style='color:#808030; '>(</span><span style='color:#808030; '>)</span><br /></pre>Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-80227882388375475602008-08-24T11:16:00.007+01:002008-08-24T12:11:06.944+01:00Tagging CriticsI was doing some research for the ISMIR tag tutorial when I stumbled upon (via this interesting paper <a href="http://etd.ils.unc.edu/dspace/bitstream/1901/535/1/abbeythompson.pdf">Playing Tag: An Analysis of Vocabulary Patterns and Relationships Within a Popular Music Folksonomy</a> by Abbey E. Thompson):<br /><br />The following expert from <a href="http://www.dlib.org/dlib/january06/guy/01guy.html">this paper</a>:<br /><br /><i>[...] "tags are often ambiguous, overly personalised and inexact" [...] "The result is an uncontrolled and chaotic set of tagging terms that do not support searching as effectively as more controlled vocabularies do." [...]</i><br /><br />This was published in the D-Lib magazine in early 2006. I wouldn't be surprised if by now the authors realized they were wrong. <br /><br />But why would anyone ever want to control the vocabulary people use when describing something so extremely multifaceted and something that evolves so fast like the content on the web (delicious), or snapshots of life (flickr), or music (Last.fm)? I guess I'd need to think more like an old-skool librarian to understand that.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com8tag:blogger.com,1999:blog-2889894315257595136.post-27637245999067717352008-08-23T01:49:00.004+01:002008-09-13T22:51:38.330+01:00Tagging Games (Callabio on Facebook)Did Microsoft researchers <a href="http://research.microsoft.com/displayArticle.aspx?0rc=n&id=2075">clone</a> the scoring system <a href="http://majorminer.org/info/intro">MajorMiner</a> uses for a tagging game on Facebook? Well, maybe it's not identical, but it seems kind of similar. And I guess it could be lots of fun. <br /><br />Btw, if scoring points is what drives people to play that game, what would stop them from entering a whole dictionary?Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-28833080857382953682008-08-23T00:05:00.007+01:002008-08-23T00:46:42.236+01:00UK Hadoop User Group Meeting<img id="noborder" style="float:right; margin:0 0 10px 10px;cursor:pointer; cursor:hand;" src="http://bp1.blogger.com/_ccNNXQ8yqZQ/SDQ3MUGW47I/AAAAAAAAANs/q1RnQEPlTc8/s400/hadoop-logo.jpg" border="0" alt=""id="BLOGGER_PHOTO_ID_5202844154213098418" /><br />Last Tuesday the first UK <a href="http://hadoop.apache.org/<br />">Hadoop</a> user group <a href="http://upcoming.yahoo.com/event/506444/">meeting</a> took place in London. <a href="http://www.last.fm/user/skr">Johan</a> did a great job in organizing it and speakers included <a href="http://en.wikipedia.org/wiki/Doug_Cutting">Doug Cutting</a> from Yahoo! (who leads the Hadoop project).<br /><br />Here's are some links:<ul><li>Yahoo! developer network <a href="http://developer.yahoo.net/blog/archives/2008/08/uk_hadoop_user.html">blog</a> mentioning the event. (Includes a video of interviews with some of the presenters.)<br /><li><a href="http://skillsmatter.com/podcast/cloud-grid/hadoop-overview">Doug Cutting: Hadoop overview</a> <br /><li><a href="http://skillsmatter.com/podcast/cloud-grid/hadoop-on-amazon-s3ec2">Tom White: Hadoop Web Services on Amazon S3/EC2</a> <br /><li><a href="http://skillsmatter.com/podcast/cloud-grid/smartfrog-and-hadoop">Steve Loughran: Deploying Apache Hadoop with Smartfrog</a><br /><li><a href="http://skillsmatter.com/podcast/cloud-grid/distributed-lucene-for-hadoop">Mark Butler: Distributed Lucene for Hadoop</a><br /><li>Last.fm related talks:<ul><li><a href="http://skillsmatter.com/podcast/cloud-grid/hadoop-usage-at-last-fm">Martin Dittus: Hadoop usage at Last.fm</a><br /><li><a href="http://skillsmatter.com/podcast/cloud-grid/hadoop-at-last-fm-radio-log-analysis-for-ab-tests">Elias Pampalk: Radio Log Analysis for A/B Tests</a><br /><li><a href="http://skillsmatter.com/podcast/cloud-grid/hadoop-lessons-learned-at-last-fm">Johan Oskarsson: Hadoop: Lessons learned at Last.fm</a><br /><li><a href="http://skillsmatter.com/podcast/cloud-grid/dumbo-hadoop-streaming-made-elegant-and-easy">Klaas Bosteels: Dumbo: Hadoop streaming made elegant and easy</a><br /><li><a href="http://skillsmatter.com/podcast/cloud-grid/postgresql-to-hbase-replication">Tim Sell: PostgreSQL to HBase Replication</a><br /></ul><br /></ul><br /><br />Seems like the interesting talk by Miles Osborne on "Using Nutch and Hadoop for Natural Language Processing" is still missing on skills matter's website. I'll update this blog post when the talk is added.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0tag:blogger.com,1999:blog-2889894315257595136.post-59864566544584691892008-08-02T20:39:00.009+01:002008-08-02T23:53:19.521+01:00More MIR related PhDsI've added 5 dissertations to the incomplete <a href="http://pampalk.at/mir-phds">list of MIR related PhDs</a>. I'm particularly happy that Markus, Tomoyasu, and Kazuyoshi (all of them are former colleagues of mine) finished their thesis so successfully.<br /><br /><img style="margin: 0pt 0pt 10px 10px; float: right; cursor: pointer;" src="http://bp3.blogger.com/_ccNNXQ8yqZQ/SJTUkelM--I/AAAAAAAAAOc/GF0snruxUBE/s400/nakano.gif" alt="" id="BLOGGER_PHOTO_ID_5230038790433471458" border="0" />Tomoyasu Nakano recently finished his thesis on <a href="http://www.pampalk.at/mir-phds/abstract/Nakano2008.html">"A Study on Developing Applications Systems Based on Singing Understanding and Singing Expression" (in Japanese)</a>. He has now joined Masataka Goto's research group as a postdoc and is working on the <a href="http://www.crestmuse.jp/crestmuse_lab_goto_e.html">CrestMuse project</a>. He recently received a lot of <a href="http://mir-research.blogspot.com/2008/07/vocalistener.html">attention</a> for his work on optimizing Vocaloid parameters.<br /><br /><img style="margin: 0pt 0pt 10px 10px; float: right; cursor: pointer;" src="http://bp3.blogger.com/_ccNNXQ8yqZQ/SJTUkstjMAI/AAAAAAAAAOs/abSbNXRz3GI/s400/yoshii.gif" alt="" id="BLOGGER_PHOTO_ID_5230038794226577410" border="0" />Kazuyoshi Yoshii recently finished his thesis on <a href="http://winnie.kuis.kyoto-u.ac.jp/members/yoshii/d-thesis-yoshii.pdf">"Studies on Hybrid Music Recommendation Using Timbral and Rhythmic Features"</a>. Kazuyoshi was awarded a tenure position at the <a href="http://www.aist.go.jp/index_en.html">AIST</a> which is pretty impressive. He joined Masataka's group and is working on CrestMuse.<br /><br /><img style="margin: 0pt 0pt 10px 10px; float: right; cursor: pointer;" src="http://bp2.blogger.com/_ccNNXQ8yqZQ/SJTVd0KZ_uI/AAAAAAAAAO0/-jyLOSIYs1c/s400/markus.jpg" alt="" id="BLOGGER_PHOTO_ID_5230039775479201506" border="0" />Markus Schedl recently finished his thesis on <a href="http://www.cp.jku.at/research/papers/schedl_phd_2008.pdf">"Automatically Extracting, Analyzing, and Visualizing Information on Music Artists from the World Wide Web"</a>. As part of his thesis he crawled a very impressive number of web pages to build a retrieval system for 600,000 artists. In the next months he'll be finishing his business studies.<br /><br /><img style="margin: 0pt 0pt 10px 10px; float: right; cursor: pointer;" src="http://bp0.blogger.com/_ccNNXQ8yqZQ/SJTUkrb0FuI/AAAAAAAAAOk/TINdqKsNBh8/s400/STP-July05-tiny2.jpg.gif" alt="" id="BLOGGER_PHOTO_ID_5230038793883752162" border="0" />Steven Travis Pope's thesis is already a bit older (2005) and serves as perfect example of how incomplete the list of PhDs is which I maintain. His work was on <a href="http://heaveneverywhere.com/STPope_Dissertation.pdf">"Software Models and Frameworks for Sound Composition, Synthesis, and Analysis: The Siren, CSL, and MAK Music Languages"</a>.<br /><br />The 5th PhD thesis I added to the list is Matt Wright's work on <a href="http://ccrma.stanford.edu/%7Ematt/diss/Matthew-Wright-Dissertation.pdf">"Computer-Based Music Theory and Acoustics"</a> which he completed at CCRMA, Stanford University.Eliashttp://www.blogger.com/profile/06133166115774380054noreply@blogger.com0