Presentation 2000/2/18
Hidden Markov Model Applied to Automatic Harmonization of Given Melodies
Takashi Kawakami, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes the use of Hidden Markov Model(HMM) for automatic music harmonization of given molodies and describes experimental results. The process of producing a melody is modeled by a hidden Markov model consisting of harmony transitions and emission of musical notes from harmonies. The underlying harmony is estimated as an inverse problem solved by a maximum like-lihood estimation from the given melody. Harmony transition models, melody emission models, N-best candidate generation, tonality estimation and detection are also discussed. Experimental studies were made based on statistical analysis of harmony transitions in tunes and songs as well as in more than 300 chorales by J. S. Bach.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hidden Markov Model / automatic harmonization / tonality estimation
Paper # SP99-156
Date of Issue

Conference Information
Committee SP
Conference Date 2000/2/18(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) Hidden Markov Model Applied to Automatic Harmonization of Given Melodies
Sub Title (in English)
Keyword(1) Hidden Markov Model
Keyword(2) automatic harmonization
Keyword(3) tonality estimation
1st Author's Name Takashi Kawakami
1st Author's Affiliation Japan Advanced Institute of Science and Technology()
2nd Author's Name Mitsuru Nakai
2nd Author's Affiliation Japan Advanced Institute of Science and Technology
3rd Author's Name Hiroshi Shimodaira
3rd Author's Affiliation Japan Advanced Institute of Science and Technology
4th Author's Name Shigeki Sagayama
4th Author's Affiliation Japan Advanced Institute of Science and Technology
Date 2000/2/18
Paper # SP99-156
Volume (vol) vol.99
Number (no) 627
Page pp.pp.-
#Pages 8
Date of Issue