• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1184-1191
• /
• 2021

In a pop song, the creator's intention is communicated to the user through music and lyrics. Lyric meaning is as important as music, but in most cases lyrics are delivered to users in a static form without non-verbal cues. Providing lyrics in a static text format is inefficient in conveying the emotions of a music. Recently, lyrics video with kinetic typography are increasingly provided, but producing them requires expertise and a lot of time. Therefore, in this system, the emotions of the lyrics are found through the analysis of the text of the lyrics, and the deep learning model is trained with the data obtained by converting the melody into a Mel-spectrogram format to find the appropriate emotions for the music. It sets properties such as motion, font, and color using the emotions found in the music, and automatically creates a kinetic typography video. In this study, we tried to enhance the effect of conveying the meaning of music through this system.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.217-223
• /
• 2023

In this paper, we propose a new model for the conditional generation of music, considering key and rhythm, fundamental elements of music. MIDI sheet music is converted into a WAV format, which is then transformed into a Mel Spectrogram using the Short-Time Fourier Transform (STFT). Using this information, key and rhythm details are classified by passing through two Convolutional Neural Networks (CNNs), and this information is again fed into the Music Transformer. The key and rhythm details are combined by differentially multiplying the weights and the embedding vectors of the MIDI events. Several experiments are conducted, including a process for determining the optimal weights. This research represents a new effort to integrate essential elements into music generation and explains the detailed structure and operating principles of the model, verifying its effects and potentials through experiments. In this study, the accuracy for rhythm classification reached 94.7%, the accuracy for key classification reached 92.1%, and the Negative Likelihood based on the weights of the embedding vector resulted in 3.01.

• Korean Journal of Heritage: History & Science
• /
• v.38
• /
• pp.5-42
• /
• 2005

Based on a field investigation of intangible cultural asset # 2, author Sir Shin Seok-bong of Daejeon Metropolitan Cityinvestigated the music of Antaek-gut, which is the base and core of Anjoon-gut, and found the following musical features: A Jang-gu(drum) and Kkoaengkwari(gong) were used to recitethe Sutra(kyungmoon) of Anjoon-gut. The Jang-gu, located on the right side, played an accompaniment role with regular beats when the Sutra was recited. The Kkoaengkwari, located on the left side, played the role of covering the caesura of the Sutra passages, so it is played with various rhythmic variations in accordance with Kojang(鼓杖). This is one way of playing Korean national classical music that has temporary caesuras, depending on the rector's bre! ath or the contents of a Sutra during the Sutra chanting, with the Jang-gu covering the pause with its variation. In other words, when being played in concert, the instruments that play the main melody are at rest while another instrument takes its turn to play the main melody as a form of prolonged sound. The rhythmic cycles of the sutras of Antaek-gut recited with this instrumental accompaniment consist of five types; a) Woemarch-jangdan (a single beat) of 4 meter by 3 bit, b) Dumarch-jangdan (two beats) of 8 meter by 3 bit, c) Saemarch-jangdan (three beats) of 4 meter by 3 bit with a fast tempo, d) Mak-gojang, uniform beats with a standardized rhythm, and e) incomplete beats deviated from the regular beats. Sir Shin Seok-bong chanted Chang (唱), a traditional native song which he called 'Cheong (淸)' with a cycle of 'Dumarch-jangdan' throughout the places of Antaek-gut. Only 'Toesonggyung' a chant for the gate that was the last location of the Antaek, was chanted with a cycle of 'Woemarch-jan! gdan'. In addition, 'Saemarch-jangdan' and 'Mak-gojang' that had comparatively faster tempos than the former two jangdans, were played without a chant when a female shaman was dancing and catching her spirit-invoking wand. The 'Saemarch-jangdan', particularly, was played while dancing began at a relatively slow tempo, then proceeded at a violent tempo and then back again to the slow tempo. This shows one of the representative tempos of our music with a slow-fast-slow tempo. The organizational tones were 'mi-la-do'-re'', and its key tones of 'mi-la-do'' were performed with perfect fourth and minor third, which was the same as those of Menari-tori. However, it did not show a typical Sigimse, an ornamental tone, of Menari-tory, whose first tone, 'mi', is vibrated and its Sigimse is gliding down from the tone 're' to 'do'. That is because the regional tone-tori of Chungcheong-do have a relatively weaker musical expression than that of Gyeongsang-do. In addition, the rhythmic types in accordance with the words of a song for the Antaek-gut music had a comparatively faster tempo than the other sutras. Also, it was only with 'Toesonggyeong' that the tone 'la' continuously appeared throughout the melody and showed 'a syllabic rhythm', while other places consisted of either a 'syncopation' or 'melismatic' rhythm. Finally, according to a brief investigation of the tone organization in accordance with each sutra, the tone 'la' was given more weight. The tone procedure showed a mainly ascending 'la-do'' and the descending 'la-mi' with minor third and perfect fourth. Also, the overall tempo proceeded with M.M.♩.=116-184, while the tempo for the Gut proceeded with M.M.♩.=120-140, which was suitable for reciting a Sutra.

• Lingua Humanitatis
• /
• v.2 no.2
• /
• pp.5-50
• /
• 2002

This paper aims to illustrate and illuminate the relationship between language and its neighbor disciplines, in particular between language and literature, language and religion, and language and music. 1. Language and literature. Literature is an art of language. Therefore, linguistics, the science of language, should be able to explain how the grammar of literature elevates and ordinary language into a literary language. I illustrate poetic syntax with examples from Shelley, Coleridge, and Wordsworth. 2. Language and religion. I show how a linguistic analysis of a religious text can illuminate the background, authorship, chronology, etc., of a religious text with an example from the Book of Daniel. I also illustrate how a misanalysis of a poetic meter led to a mistranslation with an example from the Book of Psalms. 3. Language and music. First I trace an epochal event in the history of the Western music, i.e., the change of the musical style from the liturgical music of Latin in which the rhythm was created by the alternation of syllable duration into the liberated music of German in which the rhythm was generated by the alternation of lexical stress. I then illustrate a parallelism between linguistic and musical structures with several musical pieces including Gregorian chant, the 16th century music of Palestrina, the 17th century music of Schutz, the 18th century music of Mozart, and the 19th century Viennese music. Finally, the importance of text-tune (verse-melody) association is discussed with examples of mismatches in translated Korean hymns and contemporary Korean lyrical songs. In the concluding part, I speculate on some factors that are responsible for the same organizational devices in three different modes of human communication. An answer may be that all are under the same laws of mind that govern the way man perceives and organizes nature, i.e., the same cognitive abilities of man, in particular, the capacity to organize and impose structure on their respective inputs.

• The KIPS Transactions:PartD
• /
• v.19D no.3
• /
• pp.211-220
• /
• 2012

Recently K-Pop gained worldwide sensational popularity, no longer limited to the domestic pop music scene. One of the main causes can be that K-Pop mostly are "Hook Song" which has the "hook effect": a certain melody or/and rhythm is repeated up to 70 times in one song so that it hooks the ear of the listener. Also, visual effects by K-Pop dance group are supposed to contribute to gaining the popularity. In this paper, we propose a method which traces the changes of preference for Korean pop music according to the passing of time and investigates the causes using acoustic signal analysis. For this, experiments in acoustic signal analysis are performed on Korean pop music of from popular female singers in 1960s to those as of this date. Experimental results by applying acoustic signal processing techniques show that the periods discrimination is possible based on scientific evidences. Also, quantitative, objective and numerical data based on acoustic signal processing techniques are extracted compared with the pre-existing methods such as subjective and statistical data.

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.829-836
• /
• 2018

Sheet music is one of the inevitable elements for successful melody interpretation, playing or rendering, and performance, most of performing artists usually utilize a paper sheet music in the cases. However, the paper sheet music can be a one of the reason to degrade the concentration of audiences and artists or entire performing flows. In addition, it might be a weakness to use a paper sheet music in an outside performing place. We propose an electronic sheet music page tuner application, which can overcome these problems, based on a Tablet PC. The proposed page tuner application, which uses the OpenCV to adapt an eye tracking and behavior recognition, can provide an automatical page pass function to the performing artists. We will expect that the proposed application can highly decrease the weakness of paper sheet music.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.622-628
• /
• 2020

This paper proposes a music generation technique that automatically generates trot music using a Generative Adversarial Network (GAN) model composed of a Recurrent Neural Network (RNN). The proposed method uses a method of creating a chord as a skeleton of the music, creating a melody and bass in stages based on the chord progression made, and attaching it to the corresponding chord to complete the structured piece. Also, a new chorus chord progression is created from the verse chord progression by applying the characteristics of a trot song that repeats the structure divided into an individual section, such as intro, verse, and chorus. And it extends the length of the created trot. The quality of the generated music was specified using subjective evaluation and objective evaluation methods. It was confirmed that the generated music has similar characteristics to the existing trot.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1456-1462
• /
• 2016

In this paper, we apply a chord progression learning model to a rule-based generation of a four-part chorus. The proposed system is given a 32-note melody line and completes the four-part chorus based on the rule of harmonics, predicting the chord progression with the CRBM model. The data for the training model was collected from various harmony textbooks, and chord progressions were extracted with key-independent features so as to utilize the given data effectively. It was shown that the output piece obtained with the proposed learning model had a more natural progression than the piece that used only the rule-based approach.

• Archives of design research
• /
• v.16 no.3
• /
• pp.263-272
• /
• 2003

Motiongraphics is not short film and has a special communication method characteristic of design. As graphic design needs space-composition, motiongraphics requires time-composition. In the 1920's, artists belonged Bauhaus in Germany tried to realize time-composition in the plans for abstract animation. At that time the russian film director Eisenstein experimented with moving image composit on, creating new meanings through the montage of heterogeneous images. In the digital era of today, motiongraphics is composed of such various elements as moving image, photo, illustration, typography, etc. The editing in montage film is one-dimensional. Meanwhile, motiongraphics of these days consists of a lot of layers, composing various elements by editing. Motiongraphics needs time structure and visual rhythm as well as scenario or storyboard for time composition. The principle of time composition in motiongraphics ist similar to that of musical composition. If we compare the time composition of abstract animation or montage film with the melody in a solo, time composition for motiongraphicf is like a symphony. Various composing elements are developed under different tempos at the same time.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.12
• /
• pp.3762-3774
• /
• 2000

The advances of computer hardware and information processing technologies raise the needs of multimedia information retrieval systems. Up to date. multimedia information systems have been developed for text information and image information. Nowadays. the multimedia information systems for video and audio information. especially for musical information have been grown up more and more. In recent music information retrieval systems. not only the information retrieval based on meta-information such like composer and title but also the content-based information retrieval is supported. The content-based information retrieval in music information retrieval systems utilize the similarity value between the user query and the music information stored in music database. In tbis paper. hence. we developed a similarity computation algorithm in which the pitches and lengths of each corresponding pair of notes are used as the fundamental factors for similarity computation between musical information. We also make an experiment of the proposed algorithm to validate its appropriateness. From the experimental results. the proposed similarity computation algorithm is shown to be able to correctly check whether two music files are analogous to each other or not based on melodies.