• Journal of the Korea Society of Computer and Information
• /
• v.20 no.5
• /
• pp.53-63
• /
• 2015

Singing voice synthesis is the generation of a song using a computer given its lyrics and musical notes. Hidden Markov models (HMM) have been proved to be the models of choice for text to speech synthesis. HMMs have also been used for singing voice synthesis research, however, a huge database is needed for the training of HMMs for singing voice synthesis. And commercially available singing voice synthesis systems which use the piano roll music notation, needs to adopt the easy to read standard music notation which make it suitable for singing learning applications. To overcome this problem, we use a speech database for training context dependent HMMs, to be used for singing voice synthesis. Pitch and duration control methods have been devised to modify the parameters of the HMMs trained on speech, to be used as the synthesis units for the singing voice. This work describes a singing voice synthesis system which uses a MusicXML based music score editor as the front-end interface for entry of the notes and lyrics to be synthesized and a hidden Markov model based text to speech synthesis system as the back-end synthesizer. A perceptual test shows the feasibility of our proposed system.

• Proceedings of the KAIS Fall Conference
• /
• 2009.05a
• /
• pp.357-360
• /
• 2009

노래를 부르는 가수에게 있어 가장 중요한 부분은 정확한 음정과 박자이다. 그와 더불어 중요한 부분이 바로 발음인데, 노래라고 하는 것이 멜로디와 가사말로 구성되어 있기 때문에 발음이 불명확하면 내용이 전달되지 않기 때문이다. 성악이나 판소리의 경우 사전에 충분한 훈련을 통해 음정, 박자와 더불어 발음부분까지 충분히 숙지하는 경우가 대부분이지만 대중음악부분은 모든 가수들이 충분한 훈련 기간을 거쳐 데뷔하는 경우가 많지 않기 때문에 상당부분 미숙한 것이 사실이다. 그중에 가장 소홀히하는 부분이 발음인데, 노래에 멋을 부린다고 하기엔 발음이 너무 과하거나 왜곡되게 표현되는 부분이 많다. 본 연구에서는 노래를 부를 때의 정확한 발음법과 노래의 느낌을 살릴 수 있는 효과적인 발음법에 관해 연구해 본다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.701-704
• /
• 2010

본 논문에서는 블로그의 포스트로부터 주요 키워드를 추출하여 노래 가사 데이터와 유사도를 분석, 해당 블로그 포스트에 적합한 음악을 추천하는 기법을 제안한다. 또한, 블로거가 포스트마다 제시한 태그들도 주요한 키워드로서 활용한다. 이를 위해서, 첫째로 TF-IDF 기법을 사용하여 텍스트로 구성된 포스트의 중요 키워드를 추출한다. 둘째로 포스트의 태그와 추출된 키워드를 기반으로 유사한 노래 가사를 LSA 기법으로 검색하여 가장 높은 유사도를 갖는 음악을 선택, 적합한 음악으로써 추천한다. 사용자 만족도 평가 실험을 통해서 제안하는 기법이 실제 추천에 적합한지 검증한다.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.8
• /
• pp.91-102
• /
• 2020

The purpose of this study is to analyze musical songs from an academic perspective by applying vocal techniques that can express songs in depth in three dimensions. Singing a musical song cannot be completed with just the musical part, rather, it should be accompanied by the analysis of various aspects such as the emotional state of the scenes and the characters. To this end, this study performed a multi-dimensional analysis of fields such as theatrical structure, lyrics, musical structure, and dynamics. In addition, the study explored and applied Estill Voice Training(EVT) that actors can best express songs with the emotions of the theater and music. EVT categorizes voice into six tones: speech, sob/cry, falsetto, twang, opera, and belting. In this study, in addition to these six sounds, the positions of vocal cords and larynx were also applied to seek ways to effectively express songs using "Gar Nichts" from the musical "Elisabeth" as a case study. "Gar Nichts" is a song sung by the protagonist Elisabeth, which expresses the self and the conflict at the peak of pain. Musically, this song requires various sound and voice-changing techniques to cover the range of "G#3-Gb5." As a result, it was confirmed that in order to embody the emotions of the characters and the songs in depth, the analysis of scenes and characters as well as various singing techniques need to be applied in harmony.

• Journal of the Korea Convergence Society
• /
• v.12 no.3
• /
• pp.237-245
• /
• 2021

The puropose of this study is to propose an effective diction training techniqe that conductors can use in choral communication. In chorus, the phonology of the language used in the lyrics influences the diction. Therefore, Korean lyrics must be pronounced according to Korean phonology. In verbal language, accuracy of pronunciation is important, but when expressing lyrics in a song, both vocalization and diction are important. In particular, chorus is sung by many people, so if the diction is not accurate, the lyrics will not be delivered properly. In this study, the dictions of lyrics frequently used in actual Korean choral songs were systematically analyzed according to Korean phonological rules. As a result of the study, the main factor that makes choral diction difficult is the phenomenon of phonological fluctuations in Korean. In particular, phonological fluctuations often occurred when pronouncing the final sound and when consonants and consonants were combined. A follow-up study intends to contribute to the development of choral communication by presenting a systematic choral diction based on Korean phonology.

• Journal of Music and Human Behavior
• /
• v.16 no.1
• /
• pp.25-46
• /
• 2019

This pilot study involved a single session of song-based music therapy to relieve the anxiety of intensive care unit (ICU) caregivers. Six caregivers of ICU patients participated in the intervention session individually. During the initial stage of the intervention, the participants' current emotional states were identified. Then they listened to familiar songs and playing a tone chime, which was intended to help them relax their body and reduce their psychological resistance. During singing experiences as an essential part of the intervention, the participants discussed the lyrics of songs in an attempt to find the meaning related to them. Also, they sang the songs with a live accompaniment in which their emotional states were reflected with changes in musical elements (e.g., tempo, dynamics, rhythm, or chords). In the final stage, they identified personal application to their everyday lives. To analyze the results, the State-Trait Anxiety Inventory (STAI) and a visual analog scale on emotional states were completed by participants before and after the session, and participants' verbal responses during the session were also recorded. According to the results, STAI anxiety scores significantly declined following the session. Also, they showed significant increases in positive emotions and significant decreases in negative emotions. This suggests that short-term music therapy can be an effective intervention for relieving the psychological distress of ICU caregivers.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05b
• /
• pp.868-870
• /
• 2011

본 논문에서는 음악의 정신과도 같은 노랫말의 분석, 특히 '강산에 3집'에서의 노래가사가 갖고 있는 저항의식을 중심으로 분석을 하였다. 3집은 1996년에 발매 되었는데, 당시의 사회적 분위기와 맞물린 '비판적'가사의 흐름을 중심으로 분석하였다.

• Proceedings of the KAIS Fall Conference
• /
• 2011.12a
• /
• pp.207-209
• /
• 2011

본 논문에서는 음악의 정신과도 같은 노랫말의 분석, 특히 '강산에 4집'에서의 노래가사가 갖고 있는 현실의식을 중심으로 분석을 하였다. 4집은 전작들에 비해 사회나 전쟁 혹은 어떤 불합리한 것에 대한 비판의식이 많이 없어지고 현실에 대한 이야기를 많이 담고 있는데 그의 가사분석을 통해 어떤 의식을 내포 하고 있는지 알아보기로 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.259-262
• /
• 2011

최근 들어 소리의 세기나 하모니, 템포, 리듬 등의 다양한 음악 신호 특성을 기반으로 한 음악 무드 분류에 대한 연구가 활발하게 진행되고 있다. 본 논문에서는 음악 무드 분류의 정확도를 높이기 위하여 음악 신호 특성과 더불어 노래 가사와 소셜 네트워크 상에서의 사용자 평가 등을 함께 고려하는 멀티 모달 음악 무드 분류 기법을 제안한다. 이를 위해, 우선 음악 신호 특성에 대해 퍼지 추론 기반의 음악 무드 추출 기법을 적용하여 다수의 가능한 음악 무드를 추출한다. 다음으로 음악 가사에 대해 TF-IDF 기법을 적용하여 대표 감정 키워드를 추출하고 학습시킨 가사 무드 분류기를 사용하여 가사 음악 무드를 추출한다. 마지막으로 소셜 네트워크 상에서의 사용자 태그 등 사용자 피드백을 통한 음악 무드를 추출한다. 특정 음악에 대해 이러한 다양한 경로를 통한 음악 무드를 교차 분석하여 최종적으로 음악 무드를 결정한다. 음악 분류를 기반한 자동 음악 추천을 수행하는 사용자 만족도 평가 실험을 통해서 제안하는 기법의 효율성을 검증한다.

• Sijohaknonchong
• /
• v.22
• /
• pp.195-223
• /
• 2005

The Younsijo is a stream of Korean poem. not simply an aggregate of stanzas, but an organic structure. Younsijo was an appeared in the 16th century. The 16th century was focused on the literature of Sadaebu (noble family, 사대부). And the make an appearance is Danhyungsijo (simply-sijo, 단형시조), Yonsijo and Kasa(가사). In that case, a social stratum is why does singing each other form. The 16th century set metaphysics(성리학) as the national ideology. Metaphysics became most prevalent at the end of the 16th century. Yonsijo also appreared during the 16th century and was closeiy related to the idea of metaphysics. Both Younsijo and metaphysics were formulated by noble family, The Yonsijo was Formed in 16th century. And the 17th century was succession. The Yonsijo in 16th century is devide to Kanghosijo (강호시조) and Hunminsijo (훈민시조). Also, Kanghosijo is devide to Youkgaline Younsijo (육가계 연시조) and Sasigaline Yonsijo (사시가계 연시조). Hunminsijo used an expressive on the order of Oryoun(오륜). Therefore, this study is forced on , , and . These things, all of the end of the utility. This paper deals with Danhyungsijo and Kasa with main emphasis on works of Songgang(송강) Jungcheol(정철). The reason for dealing one writer's works is the discussion needs consistent standard. In analyzing Songgang's Danhyungsijo, Younsijoand and Kasa, one would discern the differences among three. As a result, one could conclude that both Danhyungsijo and Kasa mainly projects individual's emotional esthetic feeling, particularly, Danhyungsijo for emotional implication, and for in-depth emotional revealing. Younsijo were chosen as it supplements the shortcoming of Sijo(as it consists of three-line only) to effectively contain the ideas of metaphysics.