• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.508-509
• /
• 2010

본 논문에서는 작곡, 드럼 믹싱, 청음 기능을 제공하는 웹 알고리즘을 제안한다. 이를 위해 시간과 장소에 구애 받지 않고 웹 브라우저를 통해 작곡, 리스닝, 검색을 할 수 있도록 하는 웹 음악저작 시스템을 소개하고, 이후, 리듬을 관리하는 드럼 믹싱 기능을 소개한다. 마지막으로, 음감을 향상시켜주는 게임 알고리즘을 제안한다. 제안하는 알고리즘을 통하여 사용자가 웹 브라우저를 통하여 언제 어디서나 작곡이 가능하도록 지원하며, 드럼 믹싱을 통하여보다 풍부한 작곡 기능을 제공하고, 청음게임을 통하여 음감향상의 효과를 기대할 수 있는 방법론이 될 수 있을 것으로 기대한다.

• Journal of KIISE
• /
• v.43 no.2
• /
• pp.204-211
• /
• 2016

In this paper, we propose an automatic melody composition system that can generate a sophisticated melody by adding non-harmony tone in the given chord progression. An overall procedure consists of two steps, which are the rhythm generation and melody generation parts. In the rhythm generation part, we designed new fitness functions for rhythm that can be controlled by a user setting parameters. In the melody generation part, we designed new fitness functions for melody based on harmony theory. We also designed evolutionary operators that are conducted by considering a musical context to improve computational efficiency. In the experiments, we compared four metaheuristics to optimize the rhythm fitness functions: Simple Genetic Algorithm (SGA), Elitism Genetic Algorithm (EGA), Differential Evolution (DE), and Particle Swarm Optimization (PSO). Furthermore, we compared proposed genetic algorithm for melody with the four algorithms for verifying performance. In addition, composition results are introduced and analyzed with respect to musical correctness.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.261-266
• /
• 2018

This study aimed to provide an overview of artificial intelligence based music composition programs. The artificial intelligence-based composition program has shown remarkable growth as the development of deep neural network theory and the improvement of big data processing technology. Accordingly, artificial intelligence based composition programs for composing classical music and pop music have been proposed variously in academia and industry. But there are several limitations: devaluation in general populations, missing valuable materials, lack of relevant laws, technology-led industries exclusive to the arts, and so on. When effective measures are taken against these limitations, artificial intelligence based technology will play a significant role in fostering national competitiveness.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.869-876
• /
• 2021

In the field of music, various AI composition methods using machine learning have recently been attempted. However, most of this research has been centered on Western music, and little research has been done on Korean traditional music. Therefore, in this paper, we will create a data set of Korean traditional music, create a melody using three algorithms based on the data set, and compare the results. Three models were selected based on the similarity between language and music, LSTM, Music Transformer and Self Attention. Using each of the three models, a melody generator was modeled and trained to generate melodies. As a result of user evaluation, the Self Attention method showed higher preference than the other methods. Data set is very important in AI composition. For this, a Korean traditional music data set was created, and AI composition was attempted with various algorithms, and this is expected to be helpful in future research on AI composition for Korean traditional music.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.988-991
• /
• 2014

일반적으로 인간은 원하는 정보를 얻거나 어려운 계산과정을 더 빠르고 쉽게 처리하기 위해 컴퓨터를 사용한다. 또한 컴퓨터를 이용해 자연 속에서 일어나는 일들을 과학적으로 분석하여 시뮬레이션을 하기도 한다. 본 연구는 인간의 전유물로 여겨졌던 예술적 창작 활동을 컴퓨터로 모방하는 실험이다. 작곡가가 음악을 통해 음악의 특성을 학습하여 새로운 곡을 작곡하는 과정을 컴퓨터로 모방해보았다.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.618-622
• /
• 2008

In this paper, we suggest new music composition algorithm based on fractal theory. User can define and control fractal shape by setting an initial state and production rules in L-System. We generate an asymmetric fractal tree based on L-System and probability. Then a music is generated by the fractal tree image using sonification techniques. We introduce two composition algorithm using the fractal tree. First, monophonic music can be generated by mapping x and y axis to velocity and pitch, respectively Second, harmonic music also can be generated by mapping x and y axis to time and pitch, respectively Using our composition algorithm, user can easily generate a music which has repeated pattern created by recursive feature of fractal, and a music which has structure similar to fractal tree image.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.733-738
• /
• 2008

Serial Music, introduced by A. Sch nberg, is a one of the important composition techniques. This music style has features of pantonality and atonality, so it generates unique atmosphere of modern music. In this paper, we introduce an method of generating serial music using mathematical algorithm. This method generates music that satisfy the requirement that the number of pitches belonged to each pitch class are exactly same, though the requirement is less strict than Sch nberg's definition. To do this, our method uses space-filling curves traversing the twelve tone matrix, which is constructed by the serial series, its inversion and its transpose. Using these curves, we can generate a music that has all notes in the matrix exactly once and adequate repeatness because of the curve's locality. Result music, therefore, can be more suitable for people that are not familiar with modern music, while maintaining the features of pantonality and atonality. This paper also introduces a method of generating extended serial music that uses serialism of duration and dynamic of notes, using multi-dimensional space-filling curves.

• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.449-459
• /
• 2016

This paper proposes a new method to improve the three problems of existing automatic composition method using artificial neural networks. The first problem is that the existing beat post-processing to fit into music theories could not handle all the cases of occurring. The second one is that the pitch space generated by artificial neural networks is distorted because the rest is trained with the pitch on the same neural network with large values. The last problem is caused by the difference between the initial melody and beats given by user and those generated by an artificial neural network in the process of new composition. In order to treat these problems, we propose an enhanced post-processing of beats, initial melody processing, and adoption of artificial neural network for rest. It was found from experiments that the proposed methods totally resolved the three problems.

• Proceedings of the KAIS Fall Conference
• /
• 2000.10a
• /
• pp.339-347
• /
• 2000

본 논문은 디지털 음악 도서관에서 입력된 음성을 인식하여 생성한 음곡선에 의해 임의의 음악정보를 효율적으로 검색하기 위한 알고리즘을 제안한다. 종래의 전형적인 음악정보 검색 항목인 제목이나 작곡자 또는 주제를 입력하는 것이 아니라, 사용자가 음악 데이터베이스로부터 검색하고자 하는 음악의 일부를 마이크를 통해서 노래한다. 그러면 입력된 음성에 대한 음 신호를 처리하여 음표정보를 인식하고, 이를 바탕으로 음정 곡선을 생성하여 이를 탐색 패턴으로 사용한다. 제안한 검색 알고리즘은 일반적으로 근사 탐색을 위해 많이 사용하는 동적 프로그래밍 방법과 함께 실험을 통해 탐색 시간을 비교하여 향상된 탐색 시간을 보인다.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.744-748
• /
• 2008

In this paper, we propose a novel technique that generate a new song with given example songs. Our system use k-th order Markov chain of which each state represents notes in a measure. Because we have to consider very high-dimensional space if we use notes in a measure as a state of Markov chain directly, we exploit a hierarchical clustering technique for given example songs to use each cluster as a state. Each given examples can be represented as sequences of cluster ID, and we use them for training data of the Markov chain. The resulting Markov chain effectively gives new song similar to given examples.