Talk by Prof. Michael Casey
To be presented Friday December 5th, 2008
New York University, NYC
Abstract
Soundspotting is a new approach to creating musical streams by
selecting and concatenating source segments from a large audio
database using methods from music information retrieval. Sometimes
called plundermatics, audio mosaics or concatenative synthesis,
soundspotting computes a similarity score between a target audio
segment and all the [...]
This talk describes new approximate nearest-neighbor methods employed in a scalable audio-feature database system called “AudioDB.” This open-source system is designed to scale to storing and searching hundreds of millions of feature vectors on standard UNIX workstation platforms. A radius-bounded nearest-neighbor vector-sequence search algorithm, based on locality sensitive hashing LSH , achieves sublinear retrieval times at this scale. The performance of the LSH-based algorithm depends critically on the choice of radius bound supplied—the wrong value impacts retrieval accuracy or retrieval time. An optimal radius estimator is derived by modeling the minimum value distribution of a random sample of a data set’s pairwise distance distribution
Social Playlists and Bottleneck Measurements: Exploiting Musician Social Graphs Using Content-Based Dissimilarity and Pairwise Maximum Flow Values
Ben Fields, Kurt Jacobson, Christophe Rhodes and Michael Casey
International Conference on Music Information Retrieval (ISMIR), Philadelphia, Sep., 2008
Paper 209 [PDF]
We have sampled the artist social network of Myspace and to it applied the pairwise relational connectivity measure Minimum [...]
Michael Casey, Michela Magas, Christophe Rhodes
ACM SIGGRAPH, Los Angeles, CA, 2008
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 [...]
