• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.12
• /
• pp.6038-6053
• /
• 2017

In this study, we propose an automatic melody extraction algorithm using deep learning. In this algorithm, feature images, generated using the energy of frequency band, are extracted from polyphonic audio files and a deep learning technique, a convolutional neural network (CNN), is applied on the feature images. In the training data, a short frame of polyphonic music is labeled as a musical note and a classifier based on CNN is learned in order to determine a pitch value of a short frame of audio signal. We want to build a novel structure of melody extraction, thus the proposed algorithm has a simple structure and instead of using various signal processing techniques for melody extraction, we use only a CNN to find a melody from a polyphonic audio. Despite of simple structure, the promising results are obtained in the experiments. Compared with state-of-the-art algorithms, the proposed algorithm did not give the best result, but comparable results were obtained and we believe they could be improved with the appropriate training data. In this paper, melody extraction and the proposed algorithm are introduced first, and the proposed algorithm is then further explained in detail. Finally, we present our experiment and the comparison of results follows.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.5
• /
• pp.109-118
• /
• 2005

In this paper, we present a music retrieval system that compares the geometric structure of a melody specified by a user with those in a music database. The system finds matches between a query melody and melodies in the database by analyzing both structural and contextual features. The retrieval method is based on the geometric hashing algorithm which consists of two steps; the preprocessing step and the recognition step. During the preprocessing step, we divide a melody into several fragments and analyze the pitch and duration of each note of the fragments to find a structural feature. To find a contextual feature, we find a main chord for each fragment. During the recognition step, we divide the query melody specified by a user into several fragments and search through all fragments in the database that are structurally and contextually similar to the melody. A vote is cast for each of the fragments and the music whose total votes are the maximum is the music that contains a matching melody against the query melody. Using our approach, we can find similar melodies in a music database quickly. We can also apply the method to detect plagiarism in music.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.1
• /
• pp.156-161
• /
• 2014

With the proliferation of digital music, public's interest in music and desire to sing well are increasing. This paper presents the implementation of a tone correction system through a visualization of comparison between music and humming data. For this we extract MIDI note from music and humming data and then design a matching engine using DTW algorithm which is for robust matching results against local timing variation and inaccurate tempo. This system is expected to correct the user's wrong tone by visualization and feedback from the result.

• Journal of Korea Game Society
• /
• v.12 no.1
• /
• pp.33-42
• /
• 2012

This study is intended to design a rhythm game improving the student's capacity to learn and appreciate music. This game was tested in the music classes of an elementary school. The note patterns reflecting melody affected the perception of pitch, duration, and loudness of the music. This study also presented that the factor influencing students' immersion in music and learning music was the multi-sense of sight, hearing, and touch.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.1059-1062
• /
• 2009

As the electronic processing of music gradually is developed, there has been growing interest in automatical input of music. As a result, various researches which input music in the computer has been studied. However, previous studies have drawbacks that only the experts can do it. In other words, if beginners would like to use traditional production program of music scores than prior knowledge is required. To resolve this, we propose system painting music scores automatically using a bandwidth of soundsource, after extracting the voice sounds created by amateurs. The System provides amateurs with convenience so that they can compose. As well as, the System provides the ability to play music that produced by the computer. By using the system, amateurs can compose using voice and simple system handling. And, they can make a music that plays desired instruments.

• (The) Research of the performance art and culture
• /
• no.34
• /
• pp.383-421
• /
• 2017

Because the Jitsori and the Hotsori of the Beompae(the Korean Budhhist chant) has no meter and no Jangdan(a Rhythmic cycle of the Korean Music), so it is hard to analyze the melody of the Beompae. Also the melody of the Beompae is different from that of the other Korean traditional music, so studying of the Beompae has been out of the limelight of many scholars, studying the Korean music. But the melody of Beompae had been handed down for thousands of years in Korea, it and other Korean trditional music, had exchanged the impacts each other for a longtime. So I thinks that the Korean Beomapae have shared the similarity of the musical features with the other Korean traditional music. Because the Beompae of the Bulmosan Yeongsanjae on the Geongsangnamdo province has also no meters and no Jangdan, it is difficult to understand, too. But because the Onghoge of Bulmosan Yeongsanjae have a well-regulated melodic structure in comparison with the Beompae of the Seoul province, so called Geongjae Beompae, it seem to be easy to analyze its melody. So I will analyze the melody of Bulmosan Yeongsanjae Onghoge. This analyze should be contribute to investigate the rule of the melodic progress method on the convoluted Beompae melody. Onghoge has been sung on the procedure for Siryeon, Samsiniun(Goebuliun), Jojeonjeoman, Sinjungjakbeop. And the monk for the ritual has sung the chant first to purify the ritual place and to protect the soul. They has called the song, Onghoge a Jitsori at the Bulmosan Yeongsanjae preservation society of the Gyeongnam province. Commonly, there were Jitsori and Hotsori in the Beompae melody, and the melody of Jitsori is longer than that of the Hotsori. So, the melody of Onghoge is lengthened. In other word, the melody of the Onghoge show the lengthened and curved melodic feture of the Beompae very well. Hahn Manyeong, who had studied on the Beompae, Budhhist chant, said that the Hotsori has five letters in a phrase, and there were 4 phrases in a song. And he had insisted that the form of the song, Hotsori, is ABAB. I analyze the melody of the Onghoge by the Hahn's method. I will extract the Wonjeom(a primary tone of a skeletal melodic structure) from the melody of Onghoge, and in the progress of the Wonjeom of Onghoge melodies, I will arrange the repeat of the Wonjeom melody. It is a structural melody of Onghoge. The first phrase of Bulmosan Yeongsanjae Onghoge, 'Pal bu geum gang ho do ryang(八部金剛護道場)' have 4 structural melodies, the second phrase 'Gong sin sog bu bo cheon wang(空神速赴報天王)', the third phrase 'Sam gye je cheon ham le jip(三界諸天咸來集)', the firth phrase 'Yeo geum bul chal bo jeong sang(如今佛刹補禎祥)' have 2 structural melodies each. The structural melodies of Onghoge are 10 in total. And the structural melody of the Onghoge is formed the shape of 'Mi - La - do - La - Mi'. All of the Onghoge melodies is repeated 10 times by the melodic shape. The form of the Onghoge is not ABAB by Hahn, but is 10 times repeat of the shape.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.69-77
• /
• 2021

This paper deals with the development of an application that converts the PDF music score entered by the user into a MIDI file of the chord the user wants. This application converts the PDF file into a PNG file for chord conversion when the user enters the PDF music score file and the chord which the user wants to change. After recognizing the melody of sheet music through image processing algorithm and recognizing the tempo of sheet music notes through deep learning, then the MIDI file of chord for existing sheet music is produced. The OpenCV algorithm and deep learning can recognize minim note, quarter note, eighth note, semi-quaver note, half rest, eighth rest, quarter rest, semi-quaver rest, successive notes and chord notes. The experiment shows that the note recognition rate of the music score was 100% and the tempo recognition rate was 90% or more.

• (The) Research of the performance art and culture
• /
• no.39
• /
• pp.801-833
• /
• 2019

This article has reviewed on the characteristics of the Beompae (Buddhist chanting) performed by Gyeongjaeeosan Wonmyeongchang(唱) based on the result of musical style of Gyeongjae Anchaebi-sori as defined under the previous studies. And, through the comparison with the Beompae performed by Songam-chang (唱), a same type of musical piece, it contemplates on musical differences between the two singers. Results of the study are shown as follows. of Gyeongjaeeosan Seolhoeinyu-pyeon and of Socheongsaja-pyeon are sunged as Yuchi-Seong(聲) among Anchaebi-sori. 'main melody type' and 'ending type' are generally similar to the musical characteristics of the Yuchi-Seong(聲), and the differences between the two singers are detected from main melody type D and ending type b. In particular, under of Socheongsaja-pyeon, only the type a is detected among the two types. becouse ending note of ending-type 'a' is ended with 'sol'. The basic frame of the Jjaimsae(musical form) has been clarified in the previous studies that the Jjaimsae of Yuchi-Seong(聲) has been maintained just the way it is. However, even for the same Seong(聲), the combination of the 'main melody type' of passage has not been unified, and depending on the musical piece, it has been discovered that the combination of the 'main melody type' has been diversely organized. of Gyeongjaeeosan Bongsongsajapyeon belongs to Pyeon-gae-seong(聲) broadly from the Anchaebi-sori and it is shown to be So-seong(聲) in details. In particular, in the previous studies, the 'ending melody' of So-seong(聲) and the closing melody of were similar with a slight difference for the 'ending melody'. Such a difference is relation to the characteristics for sequentially descending melody of Wonmyeong-chang(唱). The 'Jjaimsae(The musical structure)' is not much different from the previous studies, and the 'yeok-eum(weaving lyrics)' of Songam-chang(唱) has strong tendency of 3-sobak rhythm while the Wonmyeong-chang (唱) is shown the tendency of 2-sobak rhythm in general for the difference.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.482-486
• /
• 2009

Conventional music players offer simple replay and one way entertainment. The paper presents an algorithm to extract, within a digitally recorded music file, the temporal information of a sequence of target notes (i.e. melody). We assume to have the score (e.g. MIDI or printed score), and using this information, it becomes possible to first sequentially predict the probable location of the target notes. However, recorded music is hardly performed according to the score, especially temporally. Thus, additional analysis is carried out to hone in on the exact location of the target note from the initially predicted location. This prediction and correction process is repeated to find one note after another. This allows us to develop an interactive music player that is enacted by rhythmic interaction, and induce a new user experience, i.e. as if one is playing the music oneself.

• Korean Journal of Child Education & Care
• /
• v.18 no.3
• /
• pp.179-189
• /
• 2018

Objective: This study composed a melody program through handbells, and applied it to the mixed-age edu-care children. Methods: This study implemented a handbell melody program suitable for children's interest and development characteristics, based on Nuri Curriculum, to 15 mixed-aged edu-care children aged 3 to 4 at C Kindergarten located in Seoul for 12 weeks (once a week) from October 2015. Results: The program consisted of the origin of handbell, promises to keep in playing the handbell, partial literary introduction, and musical note activities using teaching aids or games in an integrated way with other areas. Through the program, dynamic class could be carried out with mutual leading participation of a teacher and children. Consequently, children aged 3 to 4 could easily encounter playing the handbell, being interested in playing, and showed cooperative spirit and society-friendly behaviors. The mixed age edu-care teacher felt pleasure and achievement of challenge by performing the class herself, which had depended upon extracurricular activities. Conclusion/Implications: A further study as action research for edu-care teachers, focused on change of edu-care teachers themselves, is proposed.