Presentation 2007-03-16
Instrument Identification Using Line Spectral Pairs
Mizuki IHARA, Shin-ichi MAEDA, Shin ISHII,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To model sound or speech production processes can be applied to audio encoding, talker and instrument identification and their synthesis. In this study, we propose the efficient representation of instrument features by comparing the accuracies of instrument identification using the same classification method with that of existing studies. Although other identification strategies use from double digits to more than 100 features, this proposed method demonstrates almost the same or higher identification rate with lower number of features around 10.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Line Spectral Pairs / Feature Extraction / Instrument Identification / Acoustical Filter / Dimension Reduction
Paper # NC2006-207
Date of Issue

Conference Information
Committee NC
Conference Date 2007/3/9(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Instrument Identification Using Line Spectral Pairs
Sub Title (in English)
Keyword(1) Line Spectral Pairs
Keyword(2) Feature Extraction
Keyword(3) Instrument Identification
Keyword(4) Acoustical Filter
Keyword(5) Dimension Reduction
1st Author's Name Mizuki IHARA
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Shin-ichi MAEDA
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Shin ISHII
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2007-03-16
Paper # NC2006-207
Volume (vol) vol.106
Number (no) 590
Page pp.pp.-
#Pages 4
Date of Issue