• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.693-701
• /
• 2017

In this paper, we propose a new method for music genre classification using spikegram and deep neural network. The human auditory system encodes the input sound in the time and frequency domain in order to maximize the amount of sound information delivered to the brain using minimum energy and resource. Spikegram is a method of analyzing waveform based on the encoding function of auditory system. In the proposed method, we analyze the signal using spikegram and extract a feature vector composed of key information for the genre classification, which is to be used as the input to the neural network. We measure the performance of music genre classification using the GTZAN dataset consisting of 10 music genres, and confirm that the proposed method provides good performance using a low-dimensional feature vector, compared to the current state-of-the-art methods.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.3
• /
• pp.127-139
• /
• 2021

This study selected representative musical song genres and suggested the application of vocal scales to demonstrate the various musical genres that appear in the modern musical style. Various genres of music and singing methods appeared according to the change in musical style throughout the early period (the early 1990s), the Golden Age (1940s to1960s), and the contemporary period (1970s to present) of musical theatre. To this end, this study selected Classic Broadway, Contemporary Broadway, Jazz/Blues, and Pop/Rock as representative musical genres as primary categories. In addition, five musicals and five songs that can represent the musical genres were selected as secondary categories. This study then divided the singing styles into Legit from , Pop from , Rock from , Jazz/Blues from , and Hip Hop/Rap from and suggested vocal scales. The analysis of this study demonstrated how various music was used as a material for musicals responding to the needs of the times in musical history and how important it is to develop various singing styles. While this study selected five representative genres and musicals to limit the scope of analysis, it intends to expand the scope through follow-up research. Based on this, it is anticipated that various further research will be conducted to study the diversity of musical vocal education and vocal techniques.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.27-32
• /
• 2019

Research that implements the classification process through Deep Learning algorithm, one of the outstanding human abilities, includes a unimodal model, a multi-modal model, and a multi-modal method using music videos. In this study, the results were better by suggesting a system to analyze each song's spectrum into short samples and vote for the results. Among Deep Learning algorithms, CNN showed superior performance in the category of music genre compared to RNN, and improved performance when CNN and RNN were applied together. The system of voting for each CNN result by Deep Learning a short sample of music showed better results than the previous model and the model with Softmax layer added to the model performed best. The need for the explosive growth of digital media and the automatic classification of music genres in numerous streaming services is increasing. Future research will need to reduce the proportion of undifferentiated songs and develop algorithms for the last category classification of undivided songs.

• 한국게임학회지
• /
• v.2 no.1
• /
• pp.32-40
• /
• 2002

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.308-320
• /
• 2021

Conventional image quality studies have been focused on 'naturalness' and has relied on memory color. Memory colors are mainly formed for familiar objects with prior experience, and the more faithfully these memories are reflected, the more naturalness of the reproduced image quality increases. In particular, the brightness and saturation of memory colors play an important role in increasing the preference of image quality as well as naturalness. Therefore, in the case of existing image quality studies, image quality characteristics were studied focusing on natural objects and people with memory. We extracted representative images of each genre (sports, documentaries, news, entertainment and music, and movies), adjusted the brightness, contrast, and saturation of each image, and conducted an experiment to evaluate perceived quality. Based on situational context, the results of this classification indicated that genres of television content can be divided into two categories: proximate and indirect experiences. Proximate experience best characterizes outdoor sports, dramas, and nature documentaries, where their image qualities have shown to have a strong correlation with brightness and contrast. On the other hand, indirect experience best characterizes news, music shows and SF/action movies. The image quality perception for indirect experiences was shown to be closely related to and optimized by contrast and saturation.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.3
• /
• pp.55-75
• /
• 2019

This study examines popular entertainers' professionalism with division of genres and cast portions. While genres can be divided into TV drama and variety show, cast portion into leading, supporting, and minor role. Entertainers' thought is categorized into their professional consciousness and their program awareness. By this division and categorization, this study grasps concretely how genres and cast portions affect entertainers' ideas. We conducted a survey on one hundred entertainers in TV dramas and variety shows and have analyzed data by using n-way ANOVA. This study also conducted in-depth interview as a research method by which we intended to enhance validity of the result. The results provide that genres and cast portions affected on entertainers' professional consciousness and their program awareness. In terms of professional consciousness, significant result was drawn on thoughts of discrimination, community, vocation, and satisfaction. In terms of their program awareness, affection, accountability, ownership, and anxiety consciousness were significant. With this result, this study provides implications both theoretical aspect and practical aspect. On theoretical aspect, this study broadens celebrity studies beyond star studies, and attempts to categorize entertainers theoretically. On practical aspect, it provides reconsideration on broadcasting condition, and suggests solving the problem of gap among entertainers.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.145-151
• /
• 2011

This study assumed the competitive structure based on genre classification for Korean online game contents market, and carried out the analysis on the degree and characteristics of the competition that appear differently in each sub market classified according to the genre. First, to analyze the market power of the rank 1 and 2 game contents in each genre, using the play time share ratio and standard deviation statistics values in the genre, ANOVA analysis and Cluster analysis were carried out for each genre. According to ANOVA analysis result, in the rank 1 game share ratio in each genre, there was a relationship of 'FPS/Racing > RST/Sports > Poker > Go-stop > RPG > Arcade > Board', and in the play time total share ratio of rank 1 and 2 games, the relationship of 'RTS > FPS/Racing > Sports > RPG > Go-stop > Poker > Arcade > Board' was verified. And in Cluster analysis, the groups of the genres with the degree of market power tendency and the variability at similar level were classified and stated.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.01a
• /
• pp.27-29
• /
• 2015

최근 IT기술의 발달로 인하여 다양한 분야에서 IT기술을 활용한 융합기술의 시도가 많아지고 있다. 특히 인터넷의 발달과 전자책(e-Book) 시장규모가 커짐에 따라 도서에 대한 정보가 많아지고 있으며, 이러한 정보를 분석하여 활용하는 서비스 시스템에 대한 관심이 높아지고 있다. 하지만 현재 서비스되고 있는 대부분의 온라인 서점에서는 도서의 기본 서지정보와 같이 도서 본문 내용과는 무관한 출판사나 서점에서 도서를 관리하기 위한 정보만을 제공하고 있으며, 도서에 대한 다양한 정보를 활용한 키워드 추출 및 장르 분류를 통한 검색의 효율성 제공이 미흡한 현실이다. 본 논문에서는 도서의 본문 텍스트 정보를 마이닝 처리하여 도서 페이지의 흐름에 따라 포함되어있는 장르를 분류하고 이에 대한 결과를 사용자에게 친화적인 시각화 기법으로 제공되는 시스템을 설계하고 구축하였다. 제안한 서비스 시스템은 의미 분석을 기반으로 도서 정보의 구체적, 실제적, 직관적 정보를 제공하여 도서 추천 서비스에 활용될 것이다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.100-105
• /
• 2009

In this paper, we Propose a browsing system to reduce the contents retrieval time in the personalized broadcasting system. For this purpose, we add a subgenre table between Classification DS and Summarization DS of MPEG-7 MDS. The subgenre includes a subgenre list to shorten the searching time of contents which we want to find. In addition we divide metadata into event and object using Summarization DS of the MPEG-7 MDS. In this way, the hierarchical browsing of broadcasting contents is made possible. This structure may reduce the complexity of search by storing event and object separately. Our simulation results show that the search time of the proposed system is shorter than that of the previous works.

• Cartoon and Animation Studies
• /
• s.38
• /
• pp.195-216
• /
• 2015

'Convention' refers to custom and practice as the dictionary definition; it means genre custom. Readers feel intimate with the pattern and grammar that a genre has, and they participate in the work, predicting and expecting the next in the 'truism.' So, all popular arts targeting the public have genre custom-that is, convention. A cartoon (comics) is one of the popular arts whose convention is developed most to the extent that its law comes across our mind just with the genre's name such as 'sports comics', 'detective comics' and 'romance comics.' However, although the fantasy cartoon is a genre that has been loved for a long time, it is one of the cartoon genres that has rarely been studied on its convention. There are several reasons for the lack of studies on convention of the fantasy cartoon. The most fundamental reason may be that its basic concept has not been properly prescribed. There are some precedent studies prescribing the fantasy cartoon as an extension of the fantastic literature, but it is hard to analyze convention that only fantasy cartoon has, because its range is too wide. So, this study considered J.R.R. Tolkein's 'Lord of the Ring' had made the genre custom of fantasy novel and fantasy comics, and classified concept and type of the fantasy cartoon. And through analysis of various cases, it investigated convention of the fantasy cartoon into 6 types. Genre is not the complete format. It is subdivided and differentiated, and it becomes one with other genres and makes a new one. For that reason, there exist limitations always when we study a genre convention of a certain genre. This study confesses in advance that it also has limitations as it just suggests convention of the general fantasy cartoon.