Compacting music signatures for efficient music retrieval

Abstract

Music information retrieval is becoming very important with the ever-increasing growth of music content in digital libraries, peer-to-peer systems and the internet. While it is easy to quantize music into a discrete string representation, retrieval by content requires (approximate) sub-string matching, which is hard.In this paper, we present a novel system, called MUSIG, that uses compact MUsic SIGnatures for efficient contentbased music retrieval. The signature is computed as follows: (a) each music file is split into a set of (overlapping) segments; (b) similar segments are clustered together; the number of clusters corresponds to the number of dimensions; (c) for each music file, the number of its segments that fall into a cluster determines the key value in that dimension.Most index structures for multimedia are only able to provide an initial filtering and return a set of candidate answers that must be further examined. For MUSIG, we have also designed a scoring function that permits a ranked answer set to be generated directly based only on the signatures. Our experimental results show that this scheme retains a high degree of accuracy while being very efficient.

A SOM-based multimodal system for musical query-by-content

“…While improving the query time of the SOM is important, the bulk of the computation occurs when comparing the computed path to the stored paths for all songs in the library. One approach to this problem was presented by Cui et al which involves storing signatures in a database for quick elimination of unlikely candidates [27]. Additionally, the system currently does not handle varying tempo in queries.…”