• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.1 no.3
• /
• pp.77-82
• /
• 2008

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.

• 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.

• 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 KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.495-508
• /
• 2004

Recently, in content-based music information retrieval systems, to enhance the response time of retrieving music data from large music database, some researches have adopted the indexing mechanism that extracts and indexes the representative melodies. The representative melody of music data must stand for the music itself and have strong possibility to use as users' input queries. However, since the previous researches have not considered the musical composition forms, they are not able to correctly catch the contrast, repetition and variation of motif in musical forms. In this paper, we use an index automatically constructed from representative melodies such like first melody, climax melodies and similarly repeated theme melodies. At first, we expand the clustering algorithm in order to extract similarly repeated theme melodies based on the musical composition forms. If the first melody and climax melodies are not included into the representative melodies of music by the clustering algorithm, we add them into representative melodies. We implemented a prototype system and did experiments on comparison the representative melody index with other melody indexes. Since, we are able to construct the representative melody index with the lower storage by 34％ than whole melody index, the response time can be decreased. Also, since we include first melody and climax melody which have the strong possibility to use as users' input query into representative melodies, we are able to get the more correct results against the various users' input queries than theme melody index with the cost of storage overhead of 20％.

• 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.

• 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.

• 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.

• 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.

• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.12
• /
• pp.8830-8835
• /
• 2015

As the smallest unit in the composition of any melody, motive forms the basis for melodic tunes and establishes a starting point for any creation. Among other melody composition methods, how to form a motive, change it, and refine it to develop a solo is important in playing solos, and in an impromptu jazz solo, analyzing how motive is changed and developed and using it can be a method or idea to approach a more melodic solo. This thesis consists of a thorough analysis of the kinds of developmental methods that were used to change and advance motives in three solos by Larry Grenadier, a musician who is active with creative ideas in many genres of contemporary jazz music. After such analysis, these motive development methods were applied to a rendition. Since judgment was used in the motive development methods mentioned in the introduction, elements in the methods that appeared to be motives but were impossible to analyze were excluded from the analysis, therefore making it one limitation of this study. There will be a need for future studies to overcome this limitation.