Title :
A technique towards automatic audio classification and retrieval
Author :
Lu, Guojun ; Hankinson, Templar
Author_Institution :
Gippsland Sch. of Comput. & Inf. Technol., Monash Univ., Churchill, Vic., Australia
Abstract :
Audio classification is very important in many audio applications so that different audio signals can be processed appropriately. We propose an audio classification scheme which will categorise audio signals based on a number of audio features. These features include silence ratio, spectral centroid, harmonicity and pitch
Keywords :
audio signal processing; feature extraction; signal classification; audio features; automatic audio classification; automatic audio retrieval; harmonicity; pitch; silence ratio; spectral centroid; Acoustic noise; Australia; Indexing; Information technology; Multimedia databases; Music information retrieval; Research and development; Signal processing; Speech recognition; Statistics;
Conference_Titel :
Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-4325-5
DOI :
10.1109/ICOSP.1998.770818
