Musical source identification based on frequency component features

KINOSHITA Tomoyoshi, SAKAI Shuichi, TANAKA Hidehiko

Bibliographic Information

Other Title

特徴量に注目した複数楽器の演奏における音源同定処理

Description

We have previously proposed a processing model OPTIMA for music scene analysis and implemented its experimental system. However, the system was not robust to signals with overlapped frequency components. In this paper, we present a new method that improves this problem by using overlap pattern of frequency components. Weighted template-matching method is applied to identify sound sources repeatedly to each frequency component cluster. The weight is evaluated according to the significance of each feature of the signal to a combination of overlapped components. The experimental results show that the system can identify sound sources of 60 to 69% of musical notes. It also showed improvement the accuracy about 5%, compared to the result without the proposed mechanism.

Journal

IPSJ SIG Notes

IPSJ SIG Notes 29 49-54, 1999-02-18

Information Processing Society of Japan (IPSJ)

Keywords

Details 詳細情報について

CRID: 1572824502059292032

NII Article ID: 110002935630

NII Book ID: AN10438388

ISSN: 09196072

Text Lang: ja

Data Source

CiNii Articles

Export

Report a problem