Archive for the ‘playlists’ Category


Using Visualizations for Music Discovery

October 22, 2009

Hot of the presses, here are the sides for the tutorial that Justin and Paul are presenting at ISMIR 2009 on October 26.

Note that the live presentation will include many demonstrations and videos of visualizations that just are not practical to include in a PDF.  If you have the chance, be sure to check out the tutorial at ISMIR in Kobe on the 26th.


Fidgt: Visualize

September 7, 2009



The Fidg’t Visualizer allows you to play around with your network. You interface with the Visualizer through Flickr and LastFM tags, using any tag to create a Magnet. Once a Tag Magnet is created, members of the network will gravitate towards it if they have photos or music with that same Tag.

This simple mechanic lets you visualize your Network in a unique way, demonstrating its Predisposition towards certain things. What is more popular amongst people in your Network – rock or electronic music? Are photos of buildings more popular than photos of sunsets? Based on how your network reacts to those Tags, you might get an answer. The Visualizer also shows how your Network compares to a random sampling of the networks of other Fidg’t users, letting you see how your network stacks up to others?

For good measure, you can also search through the network for certain users, and check out their recent photos and music. This visualizer is just one example of some of the cool Address Book applications you could build on top of our web services.

More Info


MusicBox:Mapping and visualizing music

September 7, 2009

screenshot june 2008

path selection done

Navigating increasingly large personal music libraries is commonplace.  Yet most music browsers do not enable their users to explore their collections in a guided and manipulable fashion, often requiring them to have a specific target in mind.  MusicBox is a new music browser that provides this interactive control by mapping a music collection into a two-dimensional space, applying principal components analysis (PCA) to a combination of contextual and content-based features of each of the musical tracks. The resulting map shows similar songs close together and dissimilar songs farther apart.  MusicBox is fully interactive and highly flexible: users can add and remove features from the included feature list, with PCA recomputed on the fly to remap the data.  MusicBox is also extensible; we invite other MIR researchers to contribute features to its PCA engine.  MusicBox has been shown to help users find music in their libraries, discover new music, and challenge their assumptions about relationships between types of music.


Anita Lillie

More Info


Mr. Emo: Music Retrieval in the emotion plane

September 7, 2009


This technical demo presents a novel emotion-based music retrieval platform, called Mr. Emo, for organizing and browsing music collections. Unlike conventional approaches which quantize emotions into classes, Mr. Emo defines emotions by two continuous variables arousal and valence and employs regression algorithms to predict them. Associated with arousal and valence values (AV values), each music sample becomes a point in the arousal-valence emotion plane, so a user can easily retrieve music samples of certain emotion(s) by specifying a point or a trajectory in the emotion plane. Being content centric and functionally powerful, such emotion-based retrieval complements traditional keyword- or artist-based retrieval. The demo shows the
effectiveness and novelty of music retrieval in the emotion plane.


Yi-Hsuan Yang, Yu-Ching Lin, Heng-Tze Cheng, and Homer Chen
National Taiwan University

More Info