DocumentCode :
2801786
Title :
A missing feature approach to instrument identification in polyphonic music
Author :
Eggink, Jana ; Brown, Gabriel J.
Author_Institution :
Univ. of Sheffield, UK
fYear :
2003
fDate :
19-22 Oct. 2003
Firstpage :
49
Abstract :
Summary form only given. Gaussian mixture model (GMM) classifiers have been shown to give good instrument recognition performance for monophonic music played by a single instrument. However, many applications (such as automatic music transcription) require instrument identification from polyphonic, multi-instrumental recordings. We address this problem by incorporating ideas from missing feature theory into a GMM classifier. Specifically, frequency regions that are dominated by energy from an interfering tone are marked as unreliable and excluded from the classification process. This approach has been evaluated on random two-tone chords and an excerpt from a commercially available compact disc, with promising results.
Keywords :
Gaussian processes; audio signal processing; music; musical instruments; signal classification; GMM classifiers; Gaussian mixture model classifiers; automatic music transcription; instrument identification; instrument recognition; interfering tone; missing feature theory; monophonic music; multi-instrumental recordings; polyphonic music; two-tone chords; Coordinate measuring machines; Filters; Frequency; Instruments; Multiple signal classification; Noise shaping; Phase detection; Psychoacoustic models; Psychology; Streaming media;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Applications of Signal Processing to Audio and Acoustics, 2003 IEEE Workshop on.
Print_ISBN :
0-7803-7850-4
Type :
conf
DOI :
10.1109/ASPAA.2003.1285807
Filename :
1285807
Link To Document :
بازگشت