• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06b
• /
• pp.135-140
• /
• 2008

최근 주변에서 다양한 음악분수를 찾아볼 수 있다. 음악분수의 연출을 위해서는 음악과 동기화되는 물의 움직임을 정의하는 음악분수 시나리오가 요구된다. 하지만 일반적으로 이러한 시나리오는 전문가들에 의하여 생성되기 때문에, 비용적인 문제로 인하여 다양한 음악에 대한 시나리오가 생성되지 못하고 있는 현실이다. 본 논문에서는 예제 기반 방식을 이용하여 자동으로 음악 분수의 시나리오를 생성하는 방법을 제안한다. 즉 기존에 전문가들에 의하여 생성되었던 음악분수의 시나리오를 분석하여 데이터베이스화 시킨 후, 이를 새롭게 합성하여 시나리오를 생성한다. 또한 음악분수 시나리오 생성에서 중요하게 요구되는 음악과 물 모양의 동기화를 위하여 본 논문에서는 임의의 음악이 들어왔을 때, 이 음악의 비트를 추출한 후 비트를 단위로 시나리오를 합성하게 된다. 사용자 실험결과 본 기술에 의하여 자동 생성된 시나리오는 전문가가 생성한 시나리오와 큰 차이가 나지 않음을 알 수 있었다. 본 기술을 이용하면 음악분수 시나리오를 생성할 때 요구되는 시간을 크게 줄일 수 있으며, 이로 인해 음악분수의 유지비용을 크게 절감할 수 있다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.5
• /
• pp.80-86
• /
• 2010

This paper presents automated music story video generation technique as one of entertainment features that is equipped in multimedia system of the vehicle. The automated music story video generation is a system that automatically creates stories to accompany musics with photos stored in user's mobile phone by connecting user's mobile phone with multimedia systems in vehicles. Users watch the generated music story video at the same time. while they hear the music according to mood. The performance of the automated music story video generation is measured by accuracies of music classification, photo classification, and text-keyword extraction, and results of user's MOS-test.

• 한국HCI학회:학술대회논문집
• /
• 2007.02c
• /
• pp.176-182
• /
• 2007

본 연구에서는 사용자가 즉석에서 연주한 곡에 대응하는 춤 동작을 자동으로 생성하는 기술을 제안한다. 본 기법은 먼저 댄서로부터 모션 캡쳐 받은 춤 시퀀스를 분절화한 후 사용자가 신디사이저를 통해 직접 연주하여 얻은 MIDI 데이터를 분석해 음악에서의 특징점을 추출한다. 그리고 분절화 한 모션의 세그먼트들을 음악에 맞춰 다시 배열하여 새로운 춤 시퀀스를 생성함으로써 사용자가 연주한 음악과 어울리는 춤 동작을 자동으로 생성한다. 이를 위해 세 단계의 작업을 수행하게 되는데, 첫 번째 단계에서 모션 캡쳐를 통해 얻게 된 데이터에서 캐릭터의 위치와 자세를 기준으로 하여 긴 시퀀스를 의미 있는 작은 춤 동작으로 분절화한다. 두 번째 단계에서는 사용자의 연주를 통해 획득한 MIDI를 분석하여 특징점을 추출하고, 마지막 단계에서는 이를 바탕으로 음악에 기반한 음악과 동작을 합성한다. 본 연구는 음악과 댄스의 리듬감이 파괴되지 않도록 합성함으로써 우리의 연구는 기존 연구에 비해서 훨씬 자연스러운 춤 시퀀스를 결과물로 만들어 낸다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.337-342
• /
• 2010

The rise of music resources has led to a parallel rise in the need to manage thousands of songs on user devices. So users are tend to build play-list for manage songs. However the manual selection of songs for creating play-list is bothersome task. This paper proposes an auto play-list recommendation system considering user's context of use and preference. This system has two separate systems: mood and emotion classification system and music recommendation system. Users need to choose just one seed song for reflection their context of use and preference. The system recommends songs before the current song ends in order to fill up user play-list. User also can remove unsatisfied songs from recommended song list to adapt user preferences of the system for the next recommendation precess. The generated play-lists show well defined mood and emotion of music and provide songs that user preferences are reflected.

• 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.

• 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.

• 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 Korea Game Society
• /
• v.1 no.1
• /
• pp.88-93
• /
• 2001

It is getting easier to make copy of Digital Media. And, illegal copy of digital media causes an infringement of copyright. As a result, it is getting hard to find good game background music. In this study, Auto music generation method by DNA is proposed. Through this method, the game background music can be provided very easily. Since thousands forms of DNA have been found already, we can have thousands of game background music through this method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.7
• /
• pp.842-848
• /
• 2020

Music markets have entered the era of streaming. In order to select and propose music that suits the taste of music consumers, there is an active demand and research on an automatic music genre classification system. We propose a method to improve the accuracy of genre unclassified songs, which was a lack of the previous system, by using a generative adversarial network (GAN) to further develop the automatic voting system for deep learning music genre using Softmax proposed in the previous paper. In the previous study, if the spectrogram of the song was ambiguous to grasp the genre of the song, it was forced to leave it as an unclassified song. In this paper, we proposed a system that increases the accuracy of genre classification of unclassified songs by converting the spectrogram of unclassified songs into an easy-to-read spectrogram using GAN. And the result of the experiment was able to derive an excellent result compared to the existing method.

• The Journal of the Korea Contents Association
• /
• v.15 no.3
• /
• pp.1-10
• /
• 2015

Generating chord score based on melody is essential for composition and arrangement, while it is picky for amateurs who do not have harmonics knowledges. To solve this problem, we developed automatic chord score generating program, ACGP. Based on genetic algorithm, it successfully reflects diverse hormonic factors and the mood of the music. User interface was also implemented so that anyone can use the program conveniently. Additional analysis was conducted to prove the utility of ACGP.