• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1738-1741
• /
• 2019

Music performance techniques have been primarily trained by apprenticeship. The technique transfer, which relies on the imitation of experience and actual performance without scientific evidence, required the pianists more time and effort than necessary. However, if the players in the field discover the principles of universally applicable piano playing techniques in collaboration with scientists, they will avoid errors and prepare a new paradigm in the development of piano playing techniques. This is why music performance science is needed. Little has been studied about it in Korea, but it has been activated abroad since the mid-1990s. The core science of music performance science is expected to be computer science fitting data analysis. In this paper, we introduce music performance science for the pianist and present how computer can help it.

• Journal of the Korean Society for Library and Information Science
• /
• v.26
• /
• pp.75-112
• /
• 1994

The purpose of this study is to investigate the problems concerning 780 music division of DDC. The object is especially arrangement of 780 music in the 20th edition of DDC which is the complete revision. The result is summarized as follows : 1. Although music is an important subject in humanities, especially in arts, it was classified as one division (780) not class. 2. The arrangement of 780 music is severely west-oriented music theory, vocal music and instrumental music. 3. Classification number of 780 music becomes longer because of the limitation of decimal notation. 4. 780 music division of DDC neglects music theory and emphasizes music practicing, especially performance. 5. The assignment of classification number is unbalanced, especially between theory and practice, composition and performance, and among sub-sections of vocal and instrumental music. 6. Many important subject are omitted in DDC music schedule, for example, musicology and branches of musicology, composition and traditional instruments of many countries. 7. Employment of terminology is often improper and inconsistant.

• Journal of Information Technology Applications and Management
• /
• v.23 no.1
• /
• pp.33-43
• /
• 2016

Along with the spread of digital music and recent growth in the digital music industry, the demands for music recommender are increasing. These days, listeners have increasingly preferred to digital real-time streamlining and downloading to listen to music because it is convenient and affordable for the listeners to do that. We use Bayesian learning through weight of listener's prefered music site such as Melon, Billboard, Bugs Music, Soribada, and Gini. We reflect most popular current songs across all genres and styles for music recommender system using user profile. It is necessary for us to make the task of preprocessing of clustering the preference with weight of listener's preferred music site with popular music charts. We evaluated the proposed system on the data set of music sites to measure its performance. We reported some of the experimental result, which is better performance than the previous system.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.229-232
• /
• 2004

In this paper, we propose a robust music retrieval system based on the content analysis of music. New feature extraction method called Multi-Feature Clustering (MFC) is proposed for the robust and optimum performance of the music retrieval system. It is demonstrated that the use of MFC significantly improves the system stability of music retrieval with better classification accuracy.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.18 no.12
• /
• pp.1352-1358
• /
• 2007

This paper address the statistical charateristics of MUSIC algorithm which is suggested as satellite direction finding algorithm. If the MUSIC algorithm is adopted as a satellite direction detection method in mobile TT&C system, then the statistical performance of the MUSIC algorithm will be closely related with the overall performance of the system. So statistical characteristics of the parameter in the respect of SNR and data length are addressed and then analyse the final effects to the satellite direction finding.

• Journal of Korean Library and Information Science Society
• /
• v.38 no.3
• /
• pp.425-454
• /
• 2007

This study is to present a draft for the formulation of uniform title for sound recordings of the Korean traditional music. The draft as the results of this study is summarized as follows: In a musical work of a type of non-composition, the popular name is put into square brackets as a uniform title of court music and folk music in the old Korean traditional music, and the composer's original title is put into square brackets as a uniform title of the new Korean traditional music, but the medium of performance and others are omitted except an identifying element. However, for the formulation of uniform title of a type of composition in an instrumental music, the descriptive form consisted of the order of 'name of one type of composition, medium of performance, serial number, opus number, key, and a descriptive word or phrase' is put into square brackets as a uniform title and the identifying elements. And in the vocal music of the old Korean traditional music, the following medium of performance is used: in vocal choruses, a type of voices; in solo voices, a type of solo voice by sex, but one of the new Korean traditional music follows the descriptive form of the western classical music.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.11 no.2
• /
• pp.124-128
• /
• 2011

Music emotion recognition is currently one of the most attractive research areas in music information retrieval. In order to use emotion as clues when searching for a particular music, several music based emotion recognizing systems are fundamentally utilized. In order to maximize user satisfaction, the recognition accuracy is very important. In this paper, we develop a new music emotion recognition system, which employs a multilabel feature selector and multilabel classifier. The performance of the proposed system is demonstrated using novel musical emotion data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1726-1733
• /
• 2019

Movement is everything in life and music is with our whole lives. Based on movement and sound, art has developed and reflected the times with close ties to technology and is creating new cultural content in the digital age. The absence of experts and research institutes with academic knowledge and experience in various fields compared to the frequency with which music and body movements are interwoven in the intermedia art and education of convergence is a real problem. Introducing the Rhythmik that studied the most basic principles of music and exercise through the precedent of foreign universities, we raise the need to introduce music physiology, musicians' Medicine and music performance science, the areas we studied together. It presents a new direction in the convergence era and education in pioneering research areas in which the only "I myself" systematically recognizes the movement to become the subject through physiology and medicine and scientifically moves and expresses music as a medium.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.11
• /
• pp.880-885
• /
• 2017

In AD-MUSIC algorithm, DOD/DOA can be estimated without computationally expensive two-dimensional search. In this paper, to further reduce the computational complexity, the Newton type method has been applied to one-dimensional search. In this paper, we summarize the formulation of the AD-MUSIC algorithm, and present how to apply Newton-type iteration to AD-MUSIC algorithm for improvement of the accuracy of the DOD/DOA estimates. Numerical results are presented to show that the proposed scheme is efficient in the viewpoints of computational burden and estimation accuracy.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.47-54
• /
• 2023

For Bengali music emotion classification, deep learning models, particularly CNN and RNN are frequently used. But previous researches had the flaws of low accuracy and overfitting problem. In this research, attention-based Conv1D and BiGRU model is designed for music emotion classification and comparative experimentation shows that the proposed model is classifying emotions more accurate. We have proposed a Conv1D and Bi-GRU with the attention-based model for emotion classification of our Bengali music dataset. The model integrates attention-based. Wav preprocessing makes use of MFCCs. To reduce the dimensionality of the feature space, contextual features were extracted from two Conv1D layers. In order to solve the overfitting problems, dropouts are utilized. Two bidirectional GRUs networks are used to update previous and future emotion representation of the output from the Conv1D layers. Two BiGRU layers are conntected to an attention mechanism to give various MFCC feature vectors more attention. Moreover, the attention mechanism has increased the accuracy of the proposed classification model. The vector is finally classified into four emotion classes: Angry, Happy, Relax, Sad; using a dense, fully connected layer with softmax activation. The proposed Conv1D+BiGRU+Attention model is efficient at classifying emotions in the Bengali music dataset than baseline methods. For our Bengali music dataset, the performance of our proposed model is 95%.