• Journal of KIISE:Databases
• /
• v.34 no.4
• /
• pp.283-303
• /
• 2007

Recently, the study of efficient way to store and retrieve enormous music data is becoming the one of important issues in the multimedia database. Most general method of MIR (Music Information Retrieval) includes a text-based approach using text information to search a desired music. However, if users did not remember the keyword about the music, it can not give them correct answers. Moreover, since these types of systems are implemented only for exact matching between the query and music data, it can not mine any information on similar music data. Thus, these systems are inappropriate to achieve similarity matching of music data. In order to solve the problem, we propose an Efficient Query-By-Humming System (EQBHS) with a content-based indexing method that efficiently retrieve and store music when a user inquires with his incorrect humming. For the purpose of accelerating query processing in EQBHS, we design indices for significant melodies, which are 1) frequent melodies occurring many times in a single music, on the assumption that users are to hum what they can easily remember and 2) melodies partitioned by rests. In addition, we propose an error tolerated mapping method from a note to a character to make searching efficient, and the frequent melody extraction algorithm. We verified the assumption for frequent melodies by making up questions and compared the performance of the proposed EQBHS with N-gram by executing various experiments with a number of music data.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.6
• /
• pp.488-496
• /
• 2004

This paper describes a music information retrieval system which uses humming as the key for retrieval Humming is an easy way for the user to input a melody. However, there are several problems with humming that degrade the retrieval of information. One problem is a human factor. Sometimes people do not sing accurately, especially if they are inexperienced or unaccompanied. Another problem arises from signal processing. Therefore, a music information retrieval method should be sufficiently robust to surmount various humming errors and signal processing problems. A retrieval system has to extract pitch from the user's humming. However pitch extraction is not perfect. It often captures half or double pitches. even if the extraction algorithms take the continuity of the pitch into account. Considering these problems. we propose a system that takes multiple pitch candidates into account. In addition to the frequencies of the pitch candidates. the confidence measures obtained from their powers are taken into consideration as well. We also propose the use of an algorithm with three dimensions that is an extension of the conventional DP algorithm, so that multiple pitch candidates can be treated. Moreover in the proposed algorithm. DP paths are changed dynamically to take deltaPitches and IOIratios of input and reference notes into account in order to treat notes being split or unified. We carried out an evaluation experiment to compare the proposed system with a conventional system. From the experiment. the proposed method gave better retrieval performance than the conventional system.

• Cartoon and Animation Studies
• /
• s.49
• /
• pp.589-610
• /
• 2017

This study aimed at examining the music world of the composer Muczynski, who played an important and meaningful role in the various experimental trends of music which began to appear in the early $20^{th}$ century, and his works, thereby understanding his relationship with the development of music of various genres today. In the study, his pieces of piano music among his works, which formed the basis for his music, were analyzed. The study examined stylistic characteristics, that is techniques of various types including form, melody, harmony, tonality, rhythm and structure, and introduced the composer's growth in terms of music and philosophical background. Muczynski, the composer who showed the characteristics of neoclassicism, neoromanticism and neobaroque in contrast to the various forms of the $20^{th}$ music, namely music of free styles including atonal music, twelve-tone technique, avant-garde music and electronic music, used traditional forms. However, the characteristics of his works are very free. In addition, in the 1960s, he participated in the production of documentary movie music, creating very creative and sensational music. Muczynski's music has the features of tonality and shows neoclassic and neoromantic features including economical idea, lyrical melody, bitonality and nine-note scale. His music, therefore, is being evaluated as very creative and valuable and is largely significant in that it has provided a good basis for the development of modern movie music and jazz music today.

• Sijohaknonchong
• /
• v.30
• /
• pp.219-240
• /
• 2009

Jasan An Whak did research on the essence of Sijo to show that Sijo has some features as a literature. I tried to show the formation process of Sijo theory in 1930s through Jasan's Sijo theory. As a preparatory step for it, I introduced Jasan's Sijo theory released in early 1930s and examined the characteristic aspects of it. Jasan recognized a literature as a directing post that reveals the history of our national spirit. He thought a literature as a foundation for satisfying new age. Also, he recognized the essence of a literature as a emotional expression. He emphasized that a new literature in Joseon age should have not only particularity of Joseon literature but also universality of modern literature. Jasan studied style of Sijo. Because he was at the time of modernization, he used the term, 'style', instead of 'poongkyeok', which had used before modern time. He tried to show linguistic artistry of Sijo through the series of his works about the style of Sijo. Jasan tried to find formal beauty of Sijo in the aspect of rhythm instead of rhyme. And he claimed that poetic words can be lengthened or shortened to be harmonious with the melody of Sijo. In other words, it is possible to change the words of Sijo for harmonizing with a tune. Jasan recognized that the words of Sijo have a musical function as well as a semantic function.

• (The) Research of the performance art and culture
• /
• no.33
• /
• pp.9-31
• /
• 2016

Shin Gwang-su (申光洙, 1712~1775), also known as Seokbuk (石北), is a well-known poet and author of the song poetry (詩唱) "Gwanseo-akbu (Poems of the Gwanseo Region, 關西樂府)" in the late Joseon Dynasty. "Gwanseo-akbu" was popular among the Joseon Dynasty musicians. This fact confirms that the tradition of adding a melody to Shin Gwang-su's "hansi (Korean poetry recorded in Chinese characters, 漢詩)" already existed in the Joseon Dynasty. It is also a proof that the hansi poem was used in songs. Besides Seokbuk, other literary figures in the Joseon Dynasty wrote and sang hansi. In that case, the place of communication for songs was a poet's personal study, or "sarangbang." But when, like the works by Seokbuk, poems were sung by musicians, they became available to the public to communicate through music. This study is one of the attempts to re-make Seokbuk Shin Gwang-su's poems and songs, once popular among the Joseon Dynasty people, into the contemporary music that can be performed on stage. By adding a certain melody to his poems, this study introduces a case of musical work and offers an opportunity to consider hansi as performance art. There is a number of hansi works by Shin Gwang-su, and each poem includes material which can help survey Shin Gwang-su's musical life. And, working on his hansi works makes it possible to narrate major events that took place in Shin's life. Thus, this study attempts to focus Shin Gwang-su's musical life and introduces methods and contents to stage his hansi poems as performance art.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.4
• /
• pp.193-202
• /
• 2017

With the growth of Chinese manufacturing industry and strengthening of manufacturing industry in advanced countries, the competitiveness of Korean manufacturing industry has become weak. Accordingly, it is time when energy for new growth is required very strongly. This research is the basic research to construct a cognitive and emotional information system to support sound design in manufacturing industry, and aims to develop AUI (Auditory User Interface) guideline. To fulfill research aims, this research conducted interviews to persons belonging to the manufacturing industry, and analyzed contexts and major characteristics related with AUI design. In addition, this research conducted survey on 269 persons on user preference on representative function of products. By analyzing survey data, this research examined the most suitable melody method for each sound, and difference in user preference between men and women. Based on beep sound, it performed analysis focusing on the number of sounds, melody types, and code. It also extracted AUI guidelines usable when users of the product into male and female. This research has significance in the sense that it built the basic guide data which can support AUI design in manufacturing industry.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1869-1886
• /
• 2018

This paper proposes a MIDI- and audio-based music genre classification method for Korean traditional music. There are many traditional instruments in Korea, and most of the traditional songs played using the instruments have similar patterns and rhythms. Although music information processing such as music genre classification and audio melody extraction have been studied, most studies have focused on pop, jazz, rock, and other universal genres. There are few studies on Korean traditional music because of the lack of datasets. This paper analyzes raw audio and MIDI phrases in Korean traditional music, performed using Korean traditional musical instruments. The classified samples and MIDI, based on our classification system, will be used to construct a database or to implement our Kontakt-based instrument library. Thus, we can construct a management system for a Korean traditional music library using this classification system. Appropriate feature sets for raw audio and MIDI phrases are proposed and the classification results-based on machine learning algorithms such as support vector machine, multi-layer perception, decision tree, and random forest-are outlined in this paper.

• CELLMED
• /
• v.6 no.3
• /
• pp.20.1-20.3
• /
• 2016

Changbu-taryung has long been known as a one of the best folksong in Korea. There had been no report for music therapy on stress management. The purpose of this article debates that Changbu-taryung may has beneficial effect on stress management. As a wonderful food can make people recover of disease, listen to delightful music can be a healthy way of healing our emotions. People tend to listen to glad music when they want to progress their mood because peculiar qualities comprised in that music entertain us and promote emotional state. Tae-yong Jeon is a creative destroyer and an out-of-box singer on Changbu-taryung. He has a good command of melody and rhythm. And he was singing with diverse and sweet tunes. That is where he is at his strongest. He rejected the conventional singing that would confine him to particular skill. As if he does enjoy the pleasure of his own cooking. The author recommend you listen to delightful and shapeshifter music when you often feel stressed out. This article indicates that Changbu-taryung may have beneficial effect on stress management.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.113-116
• /
• 2001

This paper describes an analysis of the music as a time series and the fuzzy logic-based modeling of it. All music is made up of a finite number of musical notations known as the musical symbols, such as clefs, staff, tine signature, notes, rests, etc. . The musical score uses musical symbols to present various characteristics, such as rhythm, melody, chord, etc,. for interpreting the music. In this paper, it is possible to transform the beat and pitch in the musical into time series from the viewpoint of recognizing beat and pitch of sounding tone at each time. On the basis of the identified features of the musical score, a musical score is represented as a time series and then is constructed to fuzzy logic-based model for predicting them. Examples are presented to illustrate the validity of the proposed method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.258-260
• /
• 2011

이 논문에서는 쿼리-바이-싱잉/허밍 (Query-by-singing/humming, QbSH) 시스템 또는 커버 노래 인식 (cover song identification) 시스템에서 사용 가능한 멜로디 유사도를 제안한다. QbSH 또는 커버 노래 인식은 디지털 음악의 사용이 보편화되면서 음악 검색의 방법으로 많은 연구가 진행되어 오고 있다. 멜로디 유사도는 이런 시스템을 구현하는데 필수적인 요소이며, 두 개의 음악에서 멜로디가 추출되었다고 가정하고, 추출된 멜로디 사이의 유사한 정도를 수치로 표현한다. QbSh 시스템이나 커버 노래 인식 시스템은 멜로디 유사도에 기반하여 입력 노래와 유사한 노래를 데이터베이스에서 검색하는 작업을 수행한다. 이 논문에서 제안하는 멜로디 유사도 방식은 기존의 많이 연구되던 동적 시간 왜곡 (dynamic time warping, DTW) 방법과 크로마 표현 방법 (chroma representation)을 사용하였다. DTW방법은 비대칭적으로 사용하고 미디 노트 영역에서 표현된 멜로디 특징은 0이상 12 미만의 크로마 레벨로 표현하였다. 기존의 방법에서는 정수값을 많이 사용하였으나 이 논문에서는 실수값을 사용한다. DTW 에 사용하는 거리 함수를 기존에 사용하던 차이의 절대값 대신 꺾인 함수 형태를 사용함으로써 성능을 높였다. QbSH 시스템에서의 실험을 통해서 성능을 검증하였다. 본 논문에서는 10-12초 길이의 1000번의 쿼리(Query)에 대해서 28시간 정도의 데이터베이스에서 실험한 결과, 순위 역의 평균 (Mean reciprocal rank, MRR) 값이 0.713을 보였다.