“mHashup: Fast Visual Music Discovery via Locality Sensitive Hashing” by Magas, Casey and Rhodes

  • ©Michela Magas, Michael Casey, and Christophe Rhodes

Title:


    mHashup: Fast Visual Music Discovery via Locality Sensitive Hashing

Presenter(s):


Entry Number: 27


Description:


    Millions of tracks in music download services pose a problem: how to find “dark media” – those items for which little is known but that users may want to find. The problem is similar for music lawyers and musicologists: how to identify closely matching music fragments in large recorded music collections.

    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.


Other Information:


    References

    CASEY, M., RHODES, C. and SLANEY, M. Analysis of Minimum Distances in High Dimensional Musical Spaces, IEEE Transactions on Speech, Audio and Language Processing, accepted for publication.

    SLANEY, M. and CASEY, M. 2008. Locality Sensitive Hashing for Music Audio, IEEE Signal Processing Magazine.


PDF:



Conference:


Type: