Title :
Radon-based Audio Classification Features
Author_Institution :
Inst. for Integrated & Intell. Syst., Griffith Univ., Gold Coast, QLD, Australia
Abstract :
This paper presents novel features for audio classification based on the Radon transform. These features are evaluated against widely accepted MFCC based features in terms of classification accuracy for a wide range of audio data sets.
Keywords :
Radon transforms; audio signal processing; content-based retrieval; MFCC based features; Radon based audio classification features; Radon transform; audio data sets; content based retrieval; Error analysis; Feature extraction; Instruments; Mel frequency cepstral coefficient; Training; Transforms; Vectors; Audio classification; MFCC; Radon Transform; content-based retrieval; frog calls; indexing; insect sounds; k-NN classification; machine learning; musical instruments; spectral features; speech and music discrimination;
Conference_Titel :
Multimedia and Expo (ICME), 2012 IEEE International Conference on
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4673-1659-0
DOI :
10.1109/ICME.2012.155
