An LZ78 Based String Kernel

We develop the notion of normalized information distance (NID) [7] into a kernel distance suitable for use with a Support Vector Machine classifier, and demonstrate its use for an audio genre classification task. Our classification scheme involves a relatively small number of low-level audio features, is efficient to compute, yet generates an accuracy which compares well with recent works.

• Type: Conference
• Year: 2005
• Where: ADMA
• Authors: Ming Li, Ronan Sleep
• Keywords: ADMA 2005, Audio Genre Classification, Data Mining, Normalized Information Distance, Vector Machine Classifier