DocumentCode :
2955622
Title :
Musical Signal Type Discrimination based on Large Open Feature Sets
Author :
Schuller, Björn ; Wallhoff, Frank ; Arsi, Dejan ; Rigoll, Gerhard
Author_Institution :
Inst. fur Human-Machine Commun., Technische Univ. Munchen
fYear :
2006
fDate :
9-12 July 2006
Firstpage :
1089
Lastpage :
1092
Abstract :
Automatic discrimination of musical signal types as speech, singing, music, genres or drumbeats within audio streams is of great importance, e.g. for radio broadcast stream segmentation. Yet, feature sets are largely discussed. We therefore suggest a large open feature set approach starting with systematical generation of 7k hi-level features based on MPEG-7 low-level-descriptors and further feature contours. A subsequent fast gain ratio reduction followed by wrapper-based floating search leads to a strong basis of relevant features. Next, features are added by alteration and combination within genetic search. For classification we use support-vector-machines proven reliable for this task. Test-runs are carried out on two task-specific databases and the public Columbia SMD database and show significant improvements for each step of the suggested novel concept
Keywords :
audio databases; audio signal processing; feature extraction; genetic algorithms; music; signal classification; speech processing; support vector machines; MPEG-7 low-level-descriptor; SVM classification; audio streaming; genetic search; musical signal type discrimination; open feature set approach; public Columbia SMD database; speech music discrimination; support-vector-machine; wrapper-based floating search; Genetics; MPEG 7 Standard; Man machine systems; Multiple signal classification; Music information retrieval; Radio broadcasting; Spatial databases; Speech analysis; Streaming media; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo, 2006 IEEE International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
1-4244-0366-7
Electronic_ISBN :
1-4244-0367-7
Type :
conf
DOI :
10.1109/ICME.2006.262724
Filename :
4036793
Link To Document :
بازگشت