Presentation 2010-03-02
Geometrical analysis of linear discriminant analysis algorithms and instrument feature extraction
Mizuki IHARA, Kazushi IKEDA, Shin-ichi MAEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Extracting only the essential sound attributes from sounds is one of the fundamental issues of music information retrieval. This paper shows the efficiency of the use of linear discriminant analysis for instrument feature extraction by analyzing the algorithm geometrically. For monophonic music instrument identification, various feature extraction and selection methods have been proposed. Although raw power spectra have enough information for accurate instrument identification, their dimensionality is too high and redundant. As such a dimensionality reduction method, linear discriminant analysis (LDA) is applied to the preprocessed power spectra by principal component analysis (PCA).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Acoustical feature extraction / Sound source identification / Linear discriminant analysis / Feature projection
Paper # CAS2009-123,SIP2009-168,CS2009-118
Date of Issue

Conference Information
Committee CS
Conference Date 2010/2/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Communication Systems (CS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Geometrical analysis of linear discriminant analysis algorithms and instrument feature extraction
Sub Title (in English)
Keyword(1) Acoustical feature extraction
Keyword(2) Sound source identification
Keyword(3) Linear discriminant analysis
Keyword(4) Feature projection
1st Author's Name Mizuki IHARA
1st Author's Affiliation Graduate School of Information Science, NAIST()
2nd Author's Name Kazushi IKEDA
2nd Author's Affiliation Graduate School of Information Science, NAIST
3rd Author's Name Shin-ichi MAEDA
3rd Author's Affiliation Graduate School of Informatics, Kyoto University
Date 2010-03-02
Paper # CAS2009-123,SIP2009-168,CS2009-118
Volume (vol) vol.109
Number (no) 436
Page pp.pp.-
#Pages 2
Date of Issue