Automatic musical instrument recognition using modulation spectral analysis

CHUR > College Computer Science and Informatics > Department of Computer Science and Information Engineering > Journal Articles > Item 987654321/31386

Please use this identifier to cite or link to this item: http://chur.chu.edu.tw/handle/987654321/31386

Title:	Automatic musical instrument recognition using modulation spectral analysis
Authors:	李建興 Lee, Chang-Hsing
Contributors:	資訊工程學系 Computer Science & Information Engineering
Keywords:	調變頻譜分析;樂器辨識 modulation spectral analysis;musical instrument recognition
Date:	2013
Issue Date:	2014-06-27 01:26:51 (UTC+8)
Abstract:	本論文應用調變頻譜分析於音樂樂器自動辨識，首先我們自樂器音符中擷取頻帶能量調變頻譜特徵、頻帶平均能量調變頻譜特徵、頻帶能量標準差調變頻譜特徵、擴充頻帶能量調變頻譜特徵、擴充頻帶平均能量調變頻譜特徵和擴充頻帶能量標準差調變頻譜特徵作為音符之特徵，然後將測詴音符與訓練音符用歐基里德距離來計算兩個音符之間的距離，我們取音符距離最小者的樂器類別作為辨識之類別。我們實驗的樂器種類為8 種包含:中音薩克斯風、低音提琴、大提琴、長笛、雙簧管、小號、中提琴和小提琴，經由對這8 種樂器進行自動辨識之實驗後，其中發 In this paper, modulation spectral analysis is employed to extract discriminated features for musical instruments recognition. First we apply modulation spectral analysis on subband energy, to extract variant modulation spectral features, including subban
Appears in Collections:	[Department of Computer Science and Information Engineering] Journal Articles

Files in This Item:

File	Description	Size	Format
p_e331_0099.pdf		26Kb	Adobe PDF	193	View/Open