Document Type

Conference Proceeding

Language

eng

Format of Original

4 p.

Publication Date

5-14-2006

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Source Publication

2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings (Volume:1 )

Source ISSN

1520-6149

Original Item ID

DOI: 10.1109/ICASSP.2006.1660005

Abstract

This paper introduces the Greenwood function cepstral coefficient (GFCC) and generalized perceptual linear prediction (GPLP) feature extraction models for the analysis of animal vocalizations across arbitrary species. These features are generalizations of the well-known mel-frequency cepstral coefficient (MFCC) and perceptual linear prediction (PLP) approaches, tailored to take optimal advantage of available knowledge of each species' auditory frequency range and/or audiogram data. Illustrative results are presented comparing use of the GFCC and GPLP features versus MFCC features over the same frequency ranges

Comments

Accepted version. Published as part of the proceedings of the conference, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings (Volume:1 ); I-253 - I-256. DOI. © 2019 IEEE. Used with permission.

johnson_4794acc.docx (96 kB)
ADA accessible version

Share

COinS