Identification of Birds' Kinds from Songs Using DP Matching and SOM

Kengo Yoshida; Masahiro Tanaka

doi:10.5687/sss.2004.35

Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications

Online ISSN : 2188-4749
Print ISSN : 2188-4730

The 35th ISCIE International Symposium on Stochastic Systems Theory and Its Applications (Oct. 2003, Ube)

Identification of Birds' Kinds from Songs Using DP Matching and SOM

Kengo Yoshida, Masahiro Tanaka

Author information

JOURNAL FREE ACCESS

2004 Volume 2004 Pages 35-40

DOI https://doi.org/10.5687/sss.2004.35

Details

Abstract

In this paper, the identification of birds' kinds from their acoustic sound is treated. The short time Fourier Transform will be used as the feature vectors. The standard songs will be registered as the template songs. For the recognition problem, DP matching will be tried, and it will be shown to be useful if the songs are of full length as the templates. Next, for the worse condition of the songs, SOM will be used for the sound abstraction and ordering.

Content from these authors

Favorites & Alerts

Corresponding author

Register with J-STAGE for free!