• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.268-273
• /
• 2007

In this paper, we present effective methods for automatic music recommendation system which automatically recommend music by signal processing technology. Conventional music recommendation system use users’ music downloading pattern, but the method does not consider acoustic characteristics of music. Sometimes, similarities between music are used to find similar music for recommendation in some method. However, the feature used for calculating similarities is not highly related to music characteristics at the system. Thus, our proposed method use high-level music characteristics such as rhythm pattern, timbre characteristics, and the lyrics. In addition, our proposed method store features of music, which individuals queried, to recommend music based on individual taste. Experiments show the proposed method find similar music more effectively than a conventional method. The experimental results also show that the proposed method could be used for real-time application since the processing time for calculating similarities between music, and recommending music are fast enough to be applicable for commercial purpose.

• International Journal of Advanced Culture Technology
• /
• v.10 no.3
• /
• pp.352-359
• /
• 2022

The study examined a sentiment analysis based on Tweeter messages between contemporary pop musicians and classical music composers. Musicians of each genre were carefully selected for the sentiment analysis. Many opinion messages on Tweets that users have discussed were collected, and the messages were evaluated by using Naïve Bayes Classifier. The results demonstrated that users showed high positive sentiments for the two different genres. However, on average, the positive sentiment values for classical music composers are higher than for contemporary pop musicians. In addition, the rankings of the highest positive sentiments among contemporary pop musicians and classical music composers did not coincide with the popularity of the two different genres of musicians. This study will contribute to the study of future sentimental analysis between music and musicians.

• Korean Journal of Applied Biomechanics
• /
• v.23 no.4
• /
• pp.403-407
• /
• 2013

Fouett$\acute{e}$ turns are repeated pirouettes which begin as a normal pirouette en dehors but include a movement that allows the rotational momentum lost to friction to be regained once each revolution. The purpose of this study was to investigate on orientation density of head/trunk to the front with and without music to which dancers perform the Fouette turn in time. 10 female dancers($21.0{\pm}1.4$ years old, height; $165.3{\pm}3.9$ cm, weight: $50.5{\pm}5.7$ kg) who are the students of S University participated in this study. It took shorter time to perform one revolution of fouette turn with music (930 ms) than without music (961 ms), which reason may be the shorter time of phase 2 in which the rotational momentum is not produced but lost to fiction. Orientation density of trunk to the front was smaller with music (.176) than without music (.196), while the one of head had not significant difference between with and without music. And the path length of marker on $2^{nd}$ left metatarsal bone during one revolution was smaller with music (35.7 cm) than without music (40.2 cm) but the difference was not statistically significant (p=.267).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.1195-1198
• /
• 2014

이 논문은 실시간으로 취득되는 뇌파를 기반으로 자동으로 음악을 추천하는 음악추천 기능의 시스템인 MyMusicShuffler 를 소개한다. 이 시스템은 뇌파 분석을 통한 사용자의 감성을 자동으로 분류하는 방식으로 멀티태스킹 환경에 익숙한 사용자들의 음악 청취를 위한 소모적인 상호작용을 없애는 새로운 방식의 인터페이스 환경을 실험하였다. 뇌파의 분석을 통하여 실시간으로 사용자의 감성 관련 반응을 반영하여 음악을 선택하여 제공하는 시스템이다. 이 논문은 개인의 감성적 반응에 의하여 상호작용하는 음악 추천 서비스인 MyMusicShuffler 시스템의 구현 내용을 설명할 것이다.

• 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.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.127-134
• /
• 2009

In spite of controversial debates on aesthetic issues of computer-generated electronic music, rapid advancement of music technologies in the past decade have resulted proliferation of using virtual software synthesizers and samplers in music composition. Computer-based music production platform has become not only a norm among some of contemporary music composers but also vital apparatus for their compositional process. There are two imperative parts of this compositional process involving sampling in computer-based music production, which are commercially available sample libraries that include pre-recorded audio samples, and music production software that processes them. The purpose of this study is to investigate the process and effectiveness of reconstructive compositional process utilizing distinctive features of sampling on computer music production software. This study addresses issues such as: the definition of audio sampling, how sampling is incorporated in compositional process, and what features of music production software are particularly effective in various musical expressions. The result of this study will hopefully accommodate and fulfill the needs of electronic and acoustic musicians' creativeness.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.2E
• /
• pp.51-56
• /
• 2008

In this paper, we propose an effective method for music summarization which automatically extracts a representative part of the music by using signal processing technology. Proposed method uses a vector quantization technique to extract several segments which can be regarded as the most important contents in the music. In general, there is a repetitive pattern in music, and human usually recognizes the most important or catchy tune from the repetitive pattern. Thus the repetition which is extracted using segment similarity is considered to express a music summary. The segments extracted are again combined to generate a complete music summary. Experiments show the proposed method captures the main theme of the music more effectively than conventional methods. The experimental results also show that the proposed method could be used for real-time application since the processing time in generating music summary is much faster than other methods.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.10 no.3
• /
• pp.215-220
• /
• 2016

Music braille is made up of more systematic and various symbols compared with text braille. Therefore, the translation of braille music requires extensive knowledge of the music and the braille symbols. Because currently the computer program for the text braille has already developed, we don't need any help from the braille translator. However, the translation of music braille is hard without the help of a professional music braille translator, because the translation computer program is not perfect. The current situation is that the music braille translator reads the music score and translates it into the braille himself. In this paper, we designed and implemented the "Braille Music Converter", you can implement a person does not understand the braille translation into music braille well. It includes translation into text braille for the lyrics processing and rest, octave, key signature, time signature, tie, slur, repeat mark was confirmed that the successful conversion to the actual music score.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.1
• /
• pp.37-43
• /
• 2022

This study is a sustainability study of K-Music beyond K-Pop through New Media. New media literally means 'new media'. When TV, classified as legacy media, first appeared in the world, it was an innovative new media platform. Of course, it is considered the most traditional legacy media. However, the definition of new media inevitably changes with the times. Most of the media called new media today are based on online and mobile. This thesis focuses on popular music including crossover traditional music genre. And we define popular music exported abroad as K-pop, and propose the possibility of globalization of Korean music using K-pop users and new media, a metaverse based K-pop audition platform, as consumers and suppliers in the global market. Hallyu, the studying of K-Pop through the study of attitudes and economic effects of K-pop, such as reactions to the spread of K-pop and the reactions of fans who like K-pop, are constantly being discussed in various ways. But there has been no case of cultural technology research that linked the sustainability of Gugak as the Korean music through new media to the K-pop business platform. As the overflowing data pours out in the virtual space as an act that gives the meaning of existence, the online is able to become an open market that provides reliable information all over the world. Therefore we would like to propose on the sustainability of Korean music through the 'Korean Traditional Music Broadcasting Metaverse Audition' beyond the K-pop business model as the K-Music content in the cultural technology era.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.1
• /
• pp.18-24
• /
• 2021

The current settlement and distribution used in theme, background and signal music market other than conventional music is being carried out with either the comprehensive settlement method or the measured meter-rate settlement method in the payment process of collected user fees and compensation depending on the use-permission types. In this settlement and distribution process, however, the reliability issues are often being raised because of the difficulty of tracking rights due to changes in music source rights management information, etc, and the opaque settlement and distribution method itself. This paper proposes a new settlement and distribution platform using a blockchain for the reliable collection and distribution of copyright fees among music user group, monitoring organization group, trust organization group and copyright holders, based on the monitoring information of the theme, background and signal music usage. This platform also provides the transparency in settlement and distribution process among stakeholders through smart contract system.