Presentation 1997/2/21
Note recognition using the statistical information about note transition
Tomoyoshi Kinoshita, Hideya Muraoka, Hidehiko Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Previously, we have proposed a processing model OPTIMA for music scene analysis, and implemented its experimental system. However, its recognition accuracy was not practical. The OPTIMA processing architecture is the framework where multiple sources of information are integrated. Due to this feature, we can improve its accuracy by adding new processing modules. The objective of this paper is improvement of recognition accuracy using statistics of note transition. In this paper, first we analyze the transition of notes and construct a knowledge source for OPTIMA. We then propose a novel process which gives probabilistic information about note ptransition. Experimental results show the effectiveness of this process.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Music scene analysis / Note transition / Auditory scene analysis / Probabilistic information integration
Paper # SP96-116
Date of Issue

Conference Information
Committee SP
Conference Date 1997/2/21(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Note recognition using the statistical information about note transition
Sub Title (in English)
Keyword(1) Music scene analysis
Keyword(2) Note transition
Keyword(3) Auditory scene analysis
Keyword(4) Probabilistic information integration
1st Author's Name Tomoyoshi Kinoshita
1st Author's Affiliation University of Tokyo()
2nd Author's Name Hideya Muraoka
2nd Author's Affiliation University of Tokyo
3rd Author's Name Hidehiko Tanaka
3rd Author's Affiliation University of Tokyo
Date 1997/2/21
Paper # SP96-116
Volume (vol) vol.96
Number (no) 540
Page pp.pp.-
#Pages 6
Date of Issue