• The Journal of the Acoustical Society of Korea
• /
• v.27 no.6
• /
• pp.319-324
• /
• 2008

In this paper, we propose a novel approach to improve the performance of speech/music classification for the selectable mode vocoder (SMV) of 3GPP2 using the discriminative weight training which is based on the minimum classification error (MCE) algorithm. We first present an effective analysis of the features and the classification method adopted in the conventional SMV. And then proposed the speech/music decision rule is expressed as the geometric mean of optimally weighted features which are selected from the SMV. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme of the SMV.

• Journal of Music and Human Behavior
• /
• v.16 no.2
• /
• pp.53-77
• /
• 2019

The purpose of this study was to review the literature on music interventions with older adults and to analyze the rationale for the type of intervention and type of music selected. A search of KCI journals for research including older adults and music-based interventions identified 33 published articles, and 23 of these studies met the criteria for inclusion in this analysis. Included studies were analyzed in terms of the contents of the interventions and the appropriateness of the rationale reported for selecting the intervention and music. Each study was analyzed in terms of the relevance of the reported rationale to target goals and the characteristics of the study participants. The results showed that many of the included studies incorporated a variety of activities but failed to include a valid rationale for using those activities to achieve the target goals. Also, many of the studies tended to select music based on participants' preferences or perceived familiarity without thorough consideration of the therapeutic function of music in the given intervention. This study presents how music therapy interventions with older adults have been conducted without sufficient attention to the selection of the intervention and presented music. There remains a need to delineate which intervention and music characteristics should be utilized to obtain particular outcomes with specific populations.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.101-111
• /
• 2021

This paper is a study that analyzes the use and techniques of rap in music that entered Melon Chart, one of the major music sites in Korea, during 2020. Among the songs that entered the chart, reflecting the public's preference, the trend of rap music, an important element of hip-hop music, is analyzed and musical features such as representative artists or frequently used rhythm patterns are analyzed. Through this paper, characteristics of rap music favored by the public and artists in recent popular music have been organized and formalized, and based on this, the elements of etude development for technical polishing are summarized. Through this, it is hoped that just like the long-time analyzed and structured performance techniques such as vocals and instruments, various styles of rap music can develop into a systematic and step-by-step technique system for students who want to learn and practice it.

• Journal of Gifted/Talented Education
• /
• v.24 no.4
• /
• pp.629-655
• /
• 2014

This study aims to explore the characteristics of environmental catalysts which have affected the development of music giftedness of the disadvantaged students. For this purpose, this study deals with nineteen disadvantaged gifted in music and examines their self-evaluation test, personal statement, and interview. Based on Gagn$\acute{e}$'s environmental catalysts of differentiated model of giftedness and talent(DMGT), the analysis of the interviews conveys the milieu of the disadvantaged gifted hardly exerts positive influences on their musical activities and studies. While concerning music and supporting their children financially and emotionally, parents unintentionally tend to exert negative influences on their children for their misapprehension of giftedness and incompetent advice. On the whole, the disadvantaged gifted hardly admit their teachers as experts in music. In relation to provisions, most students participate in extra school and local program and none of them participates in music gifted program. They are not satisfied with the quality in education. Despite the importance of the events such as crystallizing experience, award-winning, and performance, most students don't have enough events for inspiring their giftedness. As a conclusion, this study gives a proposition for a strategy to improve the environmental catalysts for the disadvantaged gifted in many different ways: the improvement of social recognition, the enhancement of parent consulting and teachers training programs, and the development and diffusions of more qualified gifted programs and so on.

• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.365-368
• /
• 2011

본 논문에서 구조 분석 기법을 이용하여 음악을 구간들로 나누고, 그 구간 중 대표 구간들을 자동으로 설정 후 다수의 사용자에게 그 구간들에 대한 분위기 값을 입력받은 후 이 값들을 바탕으로 구간의 대표 분위기를 결정하는 방법을 제안하였다. 또한, 이렇게 결정된 대표 분위기와 그 구간의 음악적 특징들을 이용하여 음악 분위기 판별 실험을 하였다. 이를 위해 음원의 분위기를 211명에게 수집하였고, 음원에서 특징들을 결정계수를 이용하여 특징의 수를 줄인 후 신경망을 이용하여 학습 및 판별을 하였다. 그리고 Leave-one-out 교차 검증을 통하여 성능 분석을 하였다. 실험결과, 3,000번 학습 시 은닉층 17개를 이용하였을 때 66%의 판별율을 보였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.4
• /
• pp.687-692
• /
• 2023

This research began with the intention to create music using the superposition characteristics of quantum computers. Existing music has characteristics that are limited to those composed by composers. However, music using the overlap of quantum computers has musical characteristics that change when executed within a limited range. Using this, you will be able to create music that changes based on specific chords at run time. In this paper, quantum computers and existing computers are connected to generate sound, And it focuses on creating changing sounds by applying the nature of superposition.

• Annual Conference of KIPS
• /
• 2008.05a
• /
• pp.51-53
• /
• 2008

최근 오디오 압축 기술의 발전에 힘입은 디지털 음원과 웹 스트리밍의 보급으로, 사용자가 음악 정보에 손쉽게 접할 수 있게 되었다. 이에 따라 음악을 보다 쉽고 효율적인 방법으로 검색하는 방법뿐 아니라 사용자의 환경에 따라 적절한 음악을 검색할 수 있는 기능의 필요성이 증가하게 되었다. 본 논문에서는 음악의 특징에 따라 분류된 데이터베이스를 사용하고, 사용자의 감정을 분석하여 적절한 음악을 검색하는 시스템을 제안한다. 본 시스템은 사용자의 감정 입력을 효율적으로 처리하기 위한 방법으로 Thayer의 2D emotional space를 적용하여 Valence-Arousal model의 두 가지의 입력을 처리한다. 가장 적합한 음악의 정보를 얻기 위해 사용된 Fuzzy Inference System의 IF-THEN 규칙을 정의하기 위하여 언어적으로 정의된 기존의 음악 감정 연구 결과를 적용하였고, 도출된 결과와 가장 유사도가 깊은 음악을 우선적으로 검색하도록 설계하였다. 이와 같이 구현된 시스템의 타당성을 검증하기 위해 사용자 설문조사를 수행하였다.

• Journal of Broadcast Engineering
• /
• v.9 no.1
• /
• pp.2-7
• /
• 2004

In this paper, we proposed the content-based music information retrieval technique using some MPEG-7 low-level descriptors. Especially, pitch information and timbral features can be applied in music genre classification, music retrieval, or QBH(Query By Humming) because these can be modeling the stochasticpattern or timbral information of music signal. In this work, we restricted the music domain as O.S.T of movie or soap opera to apply broadcasting system. That is, the user can retrievalthe information of the unknown music using only an audio clip with a few seconds extracted from video content when background music sound greeted user's ear. We proposed the audio feature set organized by MPEG-7 descriptors and distance function by vector distance or ratio computation. Thus, we observed that the feature set organized by pitch information is superior to timbral spectral feature set and IFCR(Intra-Feature Component Ratio) is better than ED(Euclidean Distance) as a vector distance function. To evaluate music recognition, k-NN is used as a classifier

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.23-30
• /
• 2010

The 50th anniversary of life as popular a female singer Lee Mi-Ja & Pati Kim in this paper analyzed out their musical characteristics to apply the analysis method of the Sasang constitution. From this, we are applied appearance & manner of speaking's method to classify the constitution through the face and voice features in the Sasang constitution classification method. Therefore, we are quantitatively analyzed out result of the Sasang constitution classification through voice and face of the visual comparison of the same ages by technological application of appearance & manner of speaking 's method. Also, experiment results also are applied to Lee Mi-Ja & Pati Kim and the same experiment to confirm that the result based on the two female singers analyzed their musical characteristics through comparison and analysis to face shape and the features of a tone based on the Sasang constitution about two female singers.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.4
• /
• pp.33-38
• /
• 2009

This paper proposes an automatic equalizer control method in automobile audio system. The proposed method discriminates the music segment from the consecutive real-time audio stream of the radio and the equalizer is controlled automatically according to the classified genre of the music segment. For enhancing the accuracy of the music genre classification in real-time, timbre feature and rhythm feature extracted from the consecutive audio stream is applied to GMM(Gaussian mixture model) classifier. The proposed method evaluates the performance of the music genre classification, which classified various audio segments segmented from the audio signal of the radio broadcast in automobile audio system into one of five music genres.