SIGGRAPH 2008 > For Attendees > New Tech Demos > mHashup

Browse Program

By Format




mHashup: Fast Visual Music Discovery Via Locality-Sensitive Hashing

Theme: Complexity and Accessibility
South Lobby

mHashup is a novel visual interface to large music collections, such as today's million-song download services, for discovering musical relationships among tracks. Users engage in direct on-screen query and retrieval of music fragments in an instantaneous feedback flow performed by a locality sensitive hash table in secondary storage.

mHashup facilitates both professional music searches (such as musicologists and copyright lawyers seeking the origins of sampled music with location markers precisely given for each returned track) and end-user music applications (such as discovery of "dark media" by its relationship to known "hot" items). The visual/auditory display of results incorporates summaries of retrieved tracks and facilitates a user-interaction feedback cycle for refining and expanding music discovery processes. mHashup's visual interface uses the core functionality of a content-based search engine as a visual grammar to be explored by direct manipulation.

Enhanced Life
mHashup enables discovery of new music and previously unknown artists, the samples used in mixes, new material for creating original mixes, playlist recommendations, cover songs, and musical influences. It is designed to aid professional and amateur users, including composers and performers.

Goal
To facilitate access to "dark media" stored in vast music libraries where metadata is erratic or unknown. The emphasis here is on starting a search with a chosen "audio shingle" and expanding the search via an audio-search feedback loop.

Innovations
mHashup performs audio retrieval via a highly efficient hashing technique over billions of music fragments and provides visual summaries of retrieved audio fragments and a user interaction feedback cycle for refining and expanding the music discovery process.

Vision
mHashup will be expanded in line with the Elastic Engine family of media interfaces, to enable instinctive "surfing" through "dark media" by direct manipulation with instantaneous results. The application will be adapted for both professional and commercial users and platforms.

Contributors
Michela Magas
Michael Casey
Christophe Rhode
Goldsmiths Digital Studios