关键词: 遗传算法, 智能作曲, 音符序列, 音频文件, 计算机音乐技术

Abstract: In order to compose music intelligently by genetic algorithm，the concrete question that how to create the music note sequences and the audio frequency file by the computer automatically is discussed.The initial groups of music paragraph are produced by the computer in terms of the pre-established parameters，the fitness function values are from the marks to the music paragraphs by manual work.The rules of the selection，crossover and mutation are set respectively.The unstable problem of the duration sum of the music notes in every bar in music during the evolutionary is solved by the duration correction，so the music notes are created by the computer.The audio frequency file is built by the method of modeling and coding.The vibration model expresses the relation among the amplitude，the frequency and the duration.In this model，the frequency value is from the frequency mapped by the pitch component and the duration value is from the time mapped by the duration component in the coding of music notes.So the wave form audio frequency file is built in terms of the vibration model and the digital audio frequency technology，and the transferring from the music notes to the audio frequency file is finished.Compared with the computer music in MIDI form currently，the computer music in WAVE form is abundant，flexible and steady.The experiment shows that the music created by the method of the interactive genetic algorithm can meet the emotional expressing requirements and the aesthetic standards of some people on the whole.And it is of important scientific significance for the development of the computer music technology.

Key words: genetic algorithm, intelligent composition, music note sequences, audio frequency file, computer music technology