Query by humming: matching humming query to polyphonic audio

Jungmin Song1, So-Young Bae1, Kyoungro Yoon1
1LG Electronics, Seoul, Korea

Tóm tắt

Previously a great attention has been paid to content-based multimedia retrieval that enables users to find and locate audio-visual material according to the intrinsic characteristics of the target. Query by humming (QBH) is also an application that makes retrieval according to major characteristics of music, that is, "melody". Our focus is on the realization of query-by-humming technology for easy-to-use application, which entails full automation of all the processes of the system, including melody information extraction from polyphonic audio. This paper presents developed algorithms for key steps of a QBH system including the melody feature extraction method from polyphonic audio and humming, their representation for matching, and matching method between the represented melody information from polyphonic audio and humming.

Từ khóa

#Data mining #Feature extraction #Music information retrieval #Computer errors #Spatial databases #Concatenated codes #Content based retrieval #Automation #Tiles #Information filtering

Tài liệu tham khảo

liu, 1999, An approximate string matching algorithm for content-based music data retrieval, IEEE Int Conf on Multimedia Computing and Systems, 1, 451, 10.1109/MMCS.1999.779244 kim, 2000, Analysis of a contour-based representation for melody, Proc International Symposium on Music Information Retrieval 10.1145/312624.312675 10.1109/ASPAA.1999.810863 jang, 2001, Hierarchical filtering method for content-based music retrieval via acoustic input, 2001 ACM Multimedia Conf, 401 kosugi, 2000, A practical query-by-humming system for a large music database, ACM Multimedia 2000, 333 10.1023/A:1009606600500 rabiner, 1993, Fundamentals of speech recognition