I hope everyone had a good thanksgiving, filled with family, lots of food (of your choice) and gravy. Unfortunately, I just returned to Montreal only to realize that the official announcement for tomorrow's talks was never sent ! (thanks for the heads up Isabelle). I hope some of you got wind of it by browsing Lisa's Google calendar.
The talks will be given by Philippe Hamel and François Maillet, and are meant to capture material which will be presented at this year's International Society for Music Information Retrieval (ISMIR) conference, held in Kobe, Japan. I apologize for the late notice and hope many of you can attend !
------------- Speaker: Philippe Hamel Title: Automatic identification of instrument classes in polyphonic and poly-instrument audio ------------- We present and compare several models for automatic identification of instrument classes in polyphonic and poly-instrument audio. The goal is to be able to identify which categories of instrument (Strings, Woodwind, Guitar, Piano, etc.) are present in a given audio example. We use a machine learning approach to solve this task. We constructed a system to generate a large database of musically relevant poly-instrument audio. Our database is generated from hundreds of instruments classified in 7 categories. Musical audio examples are generated by mixing multi-track MIDI files with thousands of instrument combinations. We compare three different classifiers: a Support Vector Machine (SVM), a Multilayer Perceptron (MLP) and a Deep Belief Network (DBN). We show that the DBN tends to outperform both the SVM and the MLP in most cases.
------------- Speaker: Francois Maillet Title: Steerable Playlist Generation by Learning Song Similarity from Radio Station Playlists ------------- This paper presents an approach to generating steerable playlists. We first demonstrate a method for learning song transition probabilities from audio features extracted from songs played in professional radio station playlists. We then show that by using this learnt similarity function as a prior, we are able to generate steerable playlists by choosing the next song to play not simply based on that prior, but on a tag cloud that the user is able to manipulate to express the high-level characteristics of the music he wishes to listen to.
-- Guillaume Desjardins