http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
조재영(JaeYoung Jo),김윤호(YoonHo Kim) 한국정보기술학회 2008 한국정보기술학회논문지 Vol.6 No.6
In this paper, we proposed a new algorithm of creating melody pattern. Firstly, back propagation neural network for melody pattern learning is reviewed in the process of progressing popular music. Secondly, a methodology for transforming chord-based melody into bit pattern which is to be used for neural network input is addressed. In order to insert the melody, composition pattern is learned by using back propagation neural network, and based on these trained data, a new melody is to be generated. Experimental results verified the possibility of neural network based computer composition and melody creating method as well.
조재영(JaeYoung Jo),김윤호(YoonHo Kim) 한국정보기술학회 2009 한국정보기술학회논문지 Vol.7 No.1
In this paper, we proposed a new method to analyze a melody pattern of each music chord by using back propagation neural network. In the first step, so as to analyze the melody pattern, each change of melody pattern with respect to the chord progress is trained using neural network. And based on these trained data, new melody is to be generated. Therefore, with trained weighted-data for a basis, if first melody is given, new types of melody could be formed. In the experiment, specific composer's music is transform into bit pattern, and these could be used for neural input vectors. Newly generated bit patterns are reconverted into melody chord and analyzed each pattern, consequently, we have demonstrated the validity of our proposed method.
조재영(Jo, JaeYoung),김윤호(Kim, YoonHo) 한국정보전자통신기술학회 2008 한국정보전자통신기술학회논문지 Vol.1 No.3
본 논문에서는 대중음악 코드진행 과정에 있어서 패턴 분석을 이용하여 멜로디를 추가하는 방법을 소개한다. 먼저, 멜로디를 신경망의 입력으로 사용되는 비트패턴으로 변환하는 방법을 기술한다. 멜로디 추가 방법은 역전파 신경망 학습을 통해 멜로디 작곡 패턴을 학습시키고 학습 된 데이터를 바탕으로 멜로디를 생성하도록 설계하였다. 실험결과 신경망 학습을 이용한 컴퓨터의 작곡 가능성을 확인하였다. In this paper, in the middle of progressing popular music chord, a method of inserting melody is addressed, which utilized by analyzing chord progress pattern. Firstly, a method for transforming melody into bit pattern which is to be used for neural network input is described. In order to insert the melody, composition pattern is learned from back propagation neural network, and based on these data new melody is to be generated. Experimental results verified the possibility of neural network based computer composition.