{"title":"Automatic melody generation considering chord progression by genetic algorithm","authors":"Motoki Kikuchi, Y. Osana","doi":"10.1109/NaBIC.2014.6921876","DOIUrl":null,"url":null,"abstract":"In this research, an automatic melody generation system considering chord progression by genetic algorithm is proposed. In the proposed automatic melody generation system, initial population are generated based on features on rhythm, pitch and chord progression of trained melody. In this system, the trained sample melody is divided into some melody blocks. Here, melody blocks mean verse, bridge, chorus and so on. And some new melodies are generated considering melody features in each block. The features on rhythm and pitch in each melody block of the sample melody are trained in some N-gram models, and they are used in order to calculate fitness in the melody generation by genetic algorithm. Some melodies are generated using the proposed system and confirmed that the proposed system can generate melodies considering features in each melody block of the trained sample melody.","PeriodicalId":209716,"journal":{"name":"2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NaBIC.2014.6921876","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10
Abstract
In this research, an automatic melody generation system considering chord progression by genetic algorithm is proposed. In the proposed automatic melody generation system, initial population are generated based on features on rhythm, pitch and chord progression of trained melody. In this system, the trained sample melody is divided into some melody blocks. Here, melody blocks mean verse, bridge, chorus and so on. And some new melodies are generated considering melody features in each block. The features on rhythm and pitch in each melody block of the sample melody are trained in some N-gram models, and they are used in order to calculate fitness in the melody generation by genetic algorithm. Some melodies are generated using the proposed system and confirmed that the proposed system can generate melodies considering features in each melody block of the trained sample melody.