• Title/Summary/Keyword: 자동작곡

Search Result 13, Processing Time 0.193 seconds

Postprocessing for Tonality and Repeatability, and Average Neural Networks for Training Multiple Songs in Automatic Composition (자동작곡에서 조성과 반복구성을 위한 후처리 방법 및 다수 곡 학습을 위한 평균 신경망 방법)

  • Kim, Kyunghwan;Jung, Sung Hoon
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.26 no.6
    • /
    • pp.445-451
    • /
    • 2016
  • This paper introduces a postprocessing method, an iteration method for melody, and an average neural network method for learning a large number of songs in order to improve musically insufficient parts in automatic composition using existing artificial neural network. The melody of songs composed by artificial neural networks is produced according to the melodies of trained songs, so it can not be a specific tonality and it is difficult to have a repetitive composition. In order to solve these problems, we propose a postprocessing method that converts the melody composed by artificial neural networks into a melody having a specific tonality according to music theory and an iteration method for melody by iteratively composing measure divisions of artificial neural networks. In addition, the existing training method of many songs has some disadvantages. To solve this problem, we adopt an average neural network that is made by averaging the weights of artificial neural networks trained each song. From some experiments, it was confirmed that the proposed method solves the existing problems.

Adoption of Artificial Neural Network for Rest, Enhanced Postprocessing of Beats, and Initial Melody Processing for Automatic Composition System (자동작곡시스템에서 쉼표용 인공신경망 도입 및 개선된 박자후처리와 초기멜로디 처리)

  • Kim, Kyunghwan;Jung, Sung Hoon
    • 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.

Automatic Composition using Time Series Embedding of RNN Auto-Encoder (RNN Auto-Encoder의 시계열 임베딩을 이용한 자동작곡)

  • Kim, Kyung Hwan;Jung, Sung Hoon
    • Journal of Korea Multimedia Society
    • /
    • v.21 no.8
    • /
    • pp.849-857
    • /
    • 2018
  • In this paper, we propose an automatic composition method using time series embedding of RNN Auto-Encoder. RNN Auto-Encoder can learn existing songs and can compose new songs from the trained RNN decoder. If one song is fully trained in the RNN Auto-Encoder, the song is embedded into the vector values of RNN nodes in the Auto-Encoder. If we train a lot of songs and apply a specific vector to the decoder of Auto-Encoder, then we can obtain a new song that combines the features of trained multiple songs according to the given vector. From extensive experiments we could find that our method worked well and generated various songs by selecting of the composition vectors.

Automatic Generation of a Configured Song with Hierarchical Artificial Neural Networks (계층적 인공신경망을 이용한 구성을 갖춘 곡의 자동생성)

  • Kim, Kyung-Hwan;Jung, Sung Hoon
    • Journal of Digital Contents Society
    • /
    • v.18 no.4
    • /
    • pp.641-647
    • /
    • 2017
  • In this paper, we propose a method to automatically generate a configured song with melodies composed of front/middle/last parts by using hierarchical artificial neural networks in automatic composition. In the first layer, an artificial neural network is used to learn an existing song or a random melody and outputs a song after performing rhythm post-processing. In the second layer, the melody created by the artificial neural network in the first layer is learned by three artificial neural networks of front/middle/last parts in the second layer in order to make a configured song. In the artificial neural network of the second layer, we applied a method to generate repeatability using measure identity in order to make song with repeatability and after that the song is completed after rhythm, chord, tonality post-processing. It was confirmed from experiments that our proposed method produced configured songs well.

Training Method of Artificial Neural Networks for Implementation of Automatic Composition Systems (자동작곡시스템 구현을 위한 인공신경망의 학습방법)

  • Cho, Jae-Min;Ryu, Eun Mi;Oh, Jin-Woo;Jung, Sung Hoon
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.3 no.8
    • /
    • pp.315-320
    • /
    • 2014
  • Composition is a creative activity of a composer in order to express his or her emotion into melody based on their experience. However, it is very hard to implement an automatic composition program whose composition process is the same as the composer. On the basis that the creative activity is possible from the imitation we propose a method to implement an automatic composition system using the learning capability of ANN(Artificial Neural Networks). First, we devise a method to convert a melody into time series that ANN can train and then another method to learn the repeated melody with melody bar for correct training of ANN. After training of the time series to ANN, we feed a new time series into the ANN, then the ANN produces a full new time series which is converted a new melody. But post processing is necessary because the produced melody does not fit to the tempo and harmony of music theory. In this paper, we applied a tempo post processing using tempo post processing program, but the harmony post processing is done by human because it is difficult to implement. We will realize the harmony post processing program as a further work.

Automatic Composition Algorithm based on Fractal Tree (프랙탈 트리를 이용한 자동 작곡 방법)

  • Kwak, Sung-Ho;Yoo, Min-Joon;Lee, In-Kwon
    • 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.

  • PDF

Automatic Composition Using Training Capability of Artificial Neural Networks and Chord Progression (인공신경망의 학습기능과 화성진행을 이용한 자동작곡)

  • Oh, Jin-Woo;Song, Jung-Hyun;Kim, Kyung-Hwan;Jung, Sung Hoon
    • Journal of Korea Multimedia Society
    • /
    • v.18 no.11
    • /
    • pp.1358-1366
    • /
    • 2015
  • This paper proposes an automatic composition method using the training capability of artificial neural networks and chord progression rules that are widely used by human composers. After training a given song, the new melody is generated by the trained artificial neural networks through applying a different initial melody to the neural networks. The generated melody should be modified to fit the rhythm and chord progression rules for generating natural melody. In order to achieve this object, we devised a post-processing method such as chord candidate generation, chord progression, and melody correction. From some tests we could find that the melody after the post-processing was very improved from the melody generated by artificial neural networks. This enables our composition system to generate a melody which is similar to those generated by human composers.

Western Music as an Abstract Art Form (추상 예술로서의 서양 음악)

  • 윤중선;황성호;주동욱;하영명
    • Proceedings of the Korean Society of Precision Engineering Conference
    • /
    • 1996.11a
    • /
    • pp.450-455
    • /
    • 1996
  • Emotional intelligence is investigated in terms of a composing machine as a modern abstract art form. Music has the longest tradition of being an art form which has an explicit formal foundation. Formal aspects of traditional and modern music theory are explained in terms of simple numerical relationship and illustrated with examples. The exploration of art in the view of intelligence, information and structure will restore the balanced sense of art and science which seeks happiness in life.

  • PDF

Implementation of Auto Composition by using Neural Network (신경망을 이용한 자동 작곡 시스템 구현)

  • Kim, Yoon-Ho;Lee, Ju-Shin
    • The Journal of Korea Institute of Information, Electronics, and Communication Technology
    • /
    • v.6 no.3
    • /
    • pp.189-194
    • /
    • 2013
  • In this paper, chord progress pattern of popular music is analyzed, and based on this optimal chord pattern, bit matrix of melody information is used for the input vector of neural network. Experimental result showed that possibility of computer composition based on neural network is verified. With regard to some given melody, by making use of proposed method, it is also possible to reconstruct the various melody.

Automatic Generation of Serial Music Using Space-Filling Curves (공간 채움 곡선을 이용한 자동 음열 음악 작곡 방법)

  • Yoo, Min-Joon;Lee, In-Kwon
    • 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.

  • PDF