DocumentCode
2081438
Title
An improved feature extraction algorithm of humming music
Author
Wei, Da-chuan
Author_Institution
Sci. & Technol. Ind. Div., Jilin Archit. & Civil Eng. Inst., Changchun, China
fYear
2011
fDate
16-18 Dec. 2011
Firstpage
2500
Lastpage
2503
Abstract
The feature extraction of humming music is one of important factors affecting the accuracy of humming music retrieval, based on this, an improved feature extraction algorithm of humming music was proposed in this study. According to the feature analysis, preprocess the humming signal firstly, and then extract the pitch feature and the rhythm feature of melody. These two features are combined together to be the feature of humming music. By the extracted feature, the musical segments identification was tested, the results showed that, the humming music feature extracted by our algorithm has a good recognizability, and the identification rate of musical notes has reached up to more than 95%.
Keywords
audio signal processing; feature extraction; feature extraction algorithm; humming music; pitch feature; rhythm feature; Accuracy; Feature extraction; Filtering; Frequency domain analysis; Multiple signal classification; Rhythm; Stability analysis; feature extraction; humming music retrieval; pitch feature; rhythm feature of melody;
fLanguage
English
Publisher
ieee
Conference_Titel
Transportation, Mechanical, and Electrical Engineering (TMEE), 2011 International Conference on
Conference_Location
Changchun
Print_ISBN
978-1-4577-1700-0
Type
conf
DOI
10.1109/TMEE.2011.6199729
Filename
6199729
Link To Document