• Smart Media Journal
• /
• v.7 no.2
• /
• pp.23-33
• /
• 2018

A musical sheet is read by optical music recognition (OMR) systems that automatically recognize and reconstruct the read data to convert them into a machine-readable format such as XML so that the music can be played. This process, however, is very challenging due to the large variety of musical styles, symbol notation, and other distortions. In this paper, we present a model for the recognition of musical symbols through the use of a mobile application, whereby a camera is used to capture the input image; therefore, additional difficulties arise due to variations of the illumination and distortions. For our proposed model, we first generate a line adjacency graph (LAG) to remove the staff lines and to perform primitive detection. After symbol segmentation using the primitive information, we use a covariance-matching method to estimate the similarity between every symbol and pre-defined templates. This method generates the three hypotheses with the highest scores for likelihood measurement. We also add a global consistency (time measurements) to verify the three hypotheses in accordance with the structure of the musical sheets; one of the three hypotheses is chosen through a final decision. The results of the experiment show that our proposed method leads to promising results.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.518-524
• /
• 2018

The cover song refers to live recordings or reproduced albums. This paper studies two-dimensional Fourier transform as a feature-dimension reduction method to search cover song fast. The two-dimensional Fourier transform is conducive in feature-dimension reduction for cover song search due to musical-key invariance. This paper extends the previous work, which only utilize the magnitude of the Fourier transform, by introducing an invariant from phase based on the assumption that adjacent frames have the same musical-key change. We compare the cover song retrieval accuracy of the Fourier-transform based methods over two datasets. The experimental results show that the addition of the invariant from phase improves the cover song retrieval accuracy over the previous magnitude-only method.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.90-97
• /
• 2020

With the development of the Internet and smartphones, digital sound sources are easily accessible, and accordingly, interest in music search and recommendation is increasing. As a method of recommending music, research using melodies such as pitch, tempo, and beat to classify genres or emotions is being conducted. However, since lyrics are becoming one of the means of expressing human emotions in music, the role of the lyrics is increasing, so a study of emotion classification based on lyrics is needed. Therefore, in this thesis, we analyze the emotions of the farewell lyrics in order to subdivide the farewell emotions based on the lyrics. After constructing an emotion dictionary by vectoriziong the similarity between words appearing in the parting lyrics through Word2Vec learning, we propose a method of classifying parting lyrics emotions using Word2Vec and LSTM, which classify lyrics by similar emotions by learning lyrics using LSTM.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.4
• /
• pp.151-160
• /
• 2018

The development of digital technology and the Internet has brought about a great change in the content industry. In order to keep pace with these changes, the copyright law has undergone several revisions, and the concept of "digital sound transmission" was introduced in the 2006 revision. However, in the current law, digital audio transmission is problematic in that the criteria for distinguishing between broadcasting and transmission is abstract and unclear. This ambiguity makes it difficult to judge the legal status of new music webcasting service such as "Free Litsen". Although these services are positioned as digital audion transmission, they have created a new concept of pseudo transmission because of its similarity to the audio transmission in its convenience and utility. These problems stem from the imbalance of between the development of technology and the legal system, so the change of the legal system is inevitable. Thus, this study discusses US copyright law and related cases, and then suggests solutions for pseudo transmission problems. This study suggests legislative criteria for pseudo transmission problems and legislative measures that can reduce the actual damage to the music market.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.4
• /
• pp.151-158
• /
• 2006

In this paper, we proposed a new audio fingerprint extraction method, based on Philips' music retrieval algorithm, which uses the energy difference of neighboring filter-bank and probabilistic characteristics of music. Since Philips method uses too many filter-banks in limited frequency band, it may cause audio fingerprints to be highly sensitive to additive noises and to have too high correlation between neighboring bands. The proposed method improves robustness to noises by reducing the number of filter-banks while it maintains the discriminative power by representing the energy difference of bands with 2 bits where the quantization levels are determined by probabilistic characteristics. The correlation which exists among 4 different levels in 2 bits is not only utilized in similarity measurement. but also in efficient reduction of searching area. Experiments show that the proposed method is not only more robust to various environmental noises (street, department, car, office, and restaurant), but also takes less time for database search than Philips in the case where music is highly degraded.

• The Research Journal of the Costume Culture
• /
• v.26 no.5
• /
• pp.777-792
• /
• 2018

As social media has become a part of daily life, new types of online opinion leaders are emerging, and in turn, changes in traditional fashion leaders and leadership are expected. Considering such changes, this study attempted to reexamine fashion leader types and influence characteristics from the perspective of college students as fashion followers. Students were asked to write an essay identifying their fashion leader and how and why they were influenced by him or her. Sixty essays entitled "My Fashion Leader" were collected and content-analyzed. A total of 78 fashion leaders were identified and categorized into four types including celebrities, social media influencers, friends/family/acquaintances, and people seen on the street in order of frequency. Influence characteristics of the identified fashion leaders included superiority, role model, similarity, and familiarity. Similarity was observed across all types of fashion leaders, while superiority and familiarity were identified for celebrities and friends/family/acquaintances, respectively. The results imply that celebrities, mostly those from the TV, movie, and music industries, are still important as fashion leaders in society regardless of their communication style, while friends/family/acquaintances as opinion leaders within a consumer group are important to provide information, advice, and help. However, social media influencers between the two groups are expanding the influence.

• Journal of the Korean Society of Costume
• /
• v.50 no.5
• /
• pp.41-52
• /
• 2000

During the 3C(B.C.) and 2C(A.D.), there were large influx of variety of arts to Jin and Han dynasty such as music, dancing, and at performing from neighboring countries. It made a tremendous impact on the development of dancing an in Han dynasty. On the other hand, Kokurye people had also enjoyed their own singing and dancing culture (styles) for a long time. Han and Kokurye's dancing costumes were studied based on artifacts (data) such as wall paintings, clay doll, and other small paintings all from tombs in Han and Kokurye. A similarity was found between two dynasties' dancing costume, since both had tong sleeve dresses. However, the further detailed study showed that one can't simply say both are in the same style. For example, the dress in Han dynasty had a long length style of coat(深衣) covering all the way to feet, and there were round neckline coat(團領) and long Jacket(장유). In contrast, that of Kokurye had a shorter length in coat(直領) covering only up to calf of the leg or long jacket(장유).

• Journal of The Korean Digital Architecture Interior Association
• /
• v.9 no.3
• /
• pp.15-23
• /
• 2009

Chaos theory, qualitative study of unstable aperiodic behavior in deterministic nonlinear dynamical systems, is dominant paradigm in the twenty first century. Fractal geometry, as an expressed form of chaos, now influences many areas such as architecture, art, music, economics, literature, etc. The purpose of this study is to analyze fractal geometry and fractal formative elements in architectural design. There are scaling, superimposition, distortion, deformation and repetition in the fractal form generator that can be applied to design concept and process in architecture. This study shows fractal geometry can be the architectural form creation method. Fractal geometry similar to nature's patterned order can be provided endless possibilities for design analysis and methodology in architecture. Therefore the further study of fractal geometry should progress synthetically through the basis of the study.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.1603-1606
• /
• 2003

음악에서 동기는 독립성을 지니는 최소 단위이며, 저작권 검사의 단위로 이용된다 따라서, 한 음악에서 약간의 변화를 가지고 반복되는 주제선율을 추출하거나, 다른 음악간의 유사도를 측정하는데 유사도 계산은 필요하다. 본 논문에서는 비교되는 동기의 선율정보를 음 길이와 음높이가 함께 고려되는 시계열 데이타로 변환하고, cosine measure를 이용하여 동기간의 유사도를 계산한다. 시계열 데이타에서 유사도 계산으로 사용되는 유클리드 거리함수 대신 cosine measure를 이용한 경우, 공간상의 거리 합대신 변화 방향이 반영됨으로써 비교되는 동기간의 유사도를 정확하게 계산한다. 본 논문에서 제안된 동기간의 유사도 계산은 내용 기반 음악 검색에서 색인으로 사용되는 주제선율을 추출하거나, 다른 음악의 동기간의 유사성을 비교하는데 이용될 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.1027-1030
• /
• 2014

대중음악과 스마트폰 기술이 발달하면서 사용자가 직접 음악을 검색할 수 있는 내용 기반 음악 검색 기술이 연구되었다. 그 결과 허밍을 사용하여 음악을 검색할 수 있는 음악 검색 시스템이 개발되었지만, 검색 속도가 느리고 검색 결과가 부정확한 시스템이 많다. 본 논문에서는 음원의 주파수 변화율을 측정하고 이를 코사인 유사도 알고리즘을 이용하여 유사도를 측정하는 음악 검색 시스템을 설계하였고, 각 설계요소를 설명한다. 새로 설계한 음악 검색 시스템을 기반으로 한 실험을 통하여 기존의 음악 검색 시스템과 유사한 성능이 나오는 것을 확인하였으며 본 논문에서 제시한 새로운 음악 검색 시스템은 기존 음악 검색 시스템보다 구조가 단순하면서도 유사한 결과를 내고 있다.