Intelligent Query by Humming System

Author

Nam, Gi Pyo ; Park, Kang Ryoung ; Lee, Soek-Pil ; Lee, Eui Chul ; Kim, Moo-Young ; Kim, Kichul

Author_Institution

Dept. of Electron. Eng., Dongguk Univ., Seoul, South Korea

fYear

2009

fDate

20-22 Dec. 2009

Firstpage

1

Lastpage

6

Abstract

This research proposes new system which finds the music by using Query-by-humming (QBH). For finding a stored music, the features of humming data are selected by using G.729 feature extractor. We normalize the extracted features by using mean-shifting, median filtering, average filtering and min-max scaling methods. Then the corresponding music is matched based on dynamic time warping (DTW) algorithm. As experiment, we compared the matching performance by using the database of Roger Jang´s Corpus in MIREX.

Keywords

feature extraction; information filtering; median filters; minimax techniques; music; query processing; G.729 feature extractor; Humming system; MIREX; QBH; average filtering; dynamic time warping algorithm; feature extraction; intelligent query; mean-shifting; median filtering; min-max scaling methods; music; Computer science; Content based retrieval; Data mining; Feature extraction; Filtering; Flowcharts; Matched filters; Music information retrieval; Spatial databases; Speech;

fLanguage

English

Publisher

ieee

Conference_Titel

Ubiquitous Information Technologies & Applications, 2009. ICUT '09. Proceedings of the 4th International Conference on

Conference_Location

Fukuoka

ISSN

1976-0035

Print_ISBN

978-1-4244-5131-9

Type

conf

DOI

10.1109/ICUT.2009.5405705

Filename

5405705