Title :
Query by humming based on music phrase segmentation and matching
Author :
Menglu Li; Zhijun Zhao; Ping Shi
Author_Institution :
College of Information Engineering, Communication University of China, CUC, Beijing, China
Abstract :
Content-based music retrieval technology has been widely used in modern society. The query by humming method by user´s humming matching music segment is a research hotspot in recent years. This paper puts forward a new method based on music phrase segmentation and matching. Music is segmented into phrases according to the note duration and the note interval, and music fragments match humming fragments in phrases. The accuracy of query is improved effectively by music phrase segmentation and matching method.
Keywords :
"Feature extraction","Databases","Algorithm design and analysis","Correlation","Multiple signal classification","Image segmentation","Multimedia communication"
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2015 12th International Conference on
DOI :
10.1109/FSKD.2015.7382250
