CNMAT Flashback

A look back at some items in our archives.

Archive Browser

Browse CNMAT content by type
Publication

Mapping Spectral Frames to Pitch with the Support Vector Machine

Posted by Yotam Mann on December 31, 2004
A. W. Schmeder, Mapping Spectral Frames to Pitch with the Support Vector Machine, in International Computer Music Conference, Miami, FL, 2004, pp. 664-667.

The Support Vector Machine algorithm is studied in the con-text of pitch estimation. Its learning capacity is analyzed using an artificial dataset of harmonic spectra. We propose an architecture for learning pitch in difficult real-world scen-arios, and demonstrate its application with a database of gui-tar sounds. Domain-specific aspects of kernel methods are discussed, and a method for extracting structural knowledge via visualization is examined.

Pages