Presentation 2008-11-08
The clustering of midi music using Self-Organizing Map and Hidden Markov Model
Kouhei Tanaka, Hiroshi Dozono,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) As the classification system of musical information, we propose a clustering method of MIDI music data using Self Organizing Maps (SOM) whose nodes are associated to Hidden Markov Model (HMM). MIDI data are converted from scores of music consisting all information for playing the music. In this research, the SOM decide the winner node whose likelihood of a phrase is maximum with onset times HMM and we employ batch learning for process of SOM learning. We examine the ability of the classification according to the genre of music (Rock, Jazz, Blues, Country, Latin. etc.) as the results of learning using SOM with HMM.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Self-Organizing Map / Musical information processing / MIDI / Hidden Markov Model
Paper # NC2008-66
Date of Issue

Conference Information
Committee NC
Conference Date 2008/10/31(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) The clustering of midi music using Self-Organizing Map and Hidden Markov Model
Sub Title (in English)
Keyword(1) Self-Organizing Map
Keyword(2) Musical information processing
Keyword(3) MIDI
Keyword(4) Hidden Markov Model
1st Author's Name Kouhei Tanaka
1st Author's Affiliation The Department of Advanced Systems Control Engineering Graduate School of Science and Engineering, Saga University()
2nd Author's Name Hiroshi Dozono
2nd Author's Affiliation The Department of Advanced Systems Control Engineering Graduate School of Science and Engineering, Saga University
Date 2008-11-08
Paper # NC2008-66
Volume (vol) vol.108
Number (no) 281
Page pp.pp.-
#Pages 6
Date of Issue