| Paper: | SPTM-P13.3 | ||
| Session: | Detection, Estimation, Classification Theory and Applications | ||
| Time: | Friday, May 19, 14:00 - 16:00 | ||
| Presentation: | Poster | ||
| Topic: | Signal Processing Theory and Methods: Detection, Estimation, Classification Theory and Applications | ||
| Title: | Pitch Based Sound Classification | ||
| Authors: | Andreas Brinch Nielsen, Lars Kai Hansen, Technical University of Denmark, Denmark; Ulrik Kjems, Oticon A/S, Denmark | ||
| Abstract: | A sound classification model is presented that can classify signals into music, noise and speech. The model extracts the pitch of the signal using the harmonic product spectrum. Based on the pitch estimate and a pitch error measure, features are created and used in a linear model with softmax output function. Both linear and quadratic inputs are used. The model is trained on 2 hours of sound and tested on publically available data. A test classification error below 0.05 with 1 s decision horizon is achieved. Further more it is shown that linear input performs as well as a quadratic, and that even though classification gets marginally better, not much is achieved by increasing the decision horizon beyond 1 s. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012