• The Journal of the Acoustical Society of Korea
• /
• v.29 no.2
• /
• pp.102-110
• /
• 2010

Music transcription is extracting pitch (the height of a musical note) and rhythm (the length of a musical note) information from audio file and making a music score. In this paper, we decomposed a waveform into frequency and rhythm components using Non-Negative Matrix Factorization (NMF) and Non-Negative Sparse coding (NNSC) which are often used for source separation and data clustering. And using the subharmonic summation method, fundamental frequency is calculated from the decomposed frequency components. Therefore, the accurate pitch of each score can be estimated. The proposed method successfully performed music transcription with its results superior to those of the conventional methods which used either NMF or NNSC.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.207-213
• /
• 2024

In this paper, we study how to improve the performance of a machine learning-based automatic music transcription model by adding musical information to the input data. Where, the added musical information is information on the number of pitches that occur in each time frame, and which is obtained by counting the number of notes activated in the answer sheet. The obtained information on the number of pitches was used by concatenating it to the log mel-spectrogram, which is the input of the existing model. In this study, we use the automatic music transcription model included the four types of block predicting four types of musical information, we demonstrate that a simple method of adding pitch number information corresponding to the music information to be predicted by each block to the existing input was helpful in training the model. In order to evaluate the performance improvement proceed with an experiment using MIDI Aligned Piano Sounds (MAPS) data, as a result, when using all pitch number information, performance improvement was confirmed by 9.7 % in frame-based F1 score and 21.8 % in note-based F1 score including offset.

• (The) Research of the performance art and culture
• /
• no.43
• /
• pp.79-120
• /
• 2021

Nagyangchun is a Dangak that has been handed down to the present time with Boheoja as a Saak of the Song Dynasty which was introduced in the Goryeo Dynasty. The title and lyrics of Nagyangchun are conveyed in the Dangakjo of Goryeosa-akji and the Jeungbomunheonbigo. The remaining scores containing Nagyangchun include Akjangyoram, Sogagwonbo Vol.4 and Vol.6 of the Joseon Dynasty and Aakbu-akbo, the 6th Aaksaeng-gyogwacheol, Leewangjikaakbu-oseonakbo during the Japanese colonial period. Besides, the current melody of Nagyangchun is based on Hangugeumak and Gugakjeonjib published by the National Gugak Center. This paper aims to examine how Nagyangchun, which is currently being performed at the National Gugak Center, went through the process of change to have the same structure and form as it is now using these scores as a research subject. The study results are summarized as follows. First, the song of Nagyangchun, which was originally Saak but transmitted as an instrumental piece without lyrics, first appeared in the Hangugeumak Vol.16 and Gugakjeonjib Vol.7 published by the National Gugak Center in 1978 and 1979. In this process, the Janggu added by Kim Ki-soo is now disappearing and is replaced by Jwago. Second, though the five notes of 黃, 太, 仲, 林, and 南 have been maintained unchanged since the Akjangyoram, the pitch of 無/應 and 夾/姑, which appear once each, gradually rises and is unified into 應 and 姑 during the period of Aaksaeng-gyogwacheol or at the latest Leewangjikaakbu-oseonakbo, and reached the present. Third, the current melody of Nagyangchun consists of a structure in which the tones and range of each phrase rises within the form of Mijeonsa (a·b·c·d) and Mihusa (e·b'·c'·d'). Particularly, except for the a-type and e-type melodies, which are the introduction for the Mijeonsa and Mihusa, the remaining melodic types show a gradually descending structure within the corresponding phrase, so the structure of ascending and descending is generally in harmony. Forth, the Ganeum that appeared from Aakbu-akbo are currently classified into seven types, and they appear in ascending pitches of 2nd, 3rd, 4th, and 5th and play a role in smoothly or fluently connecting melodic progression. Fifth, after Akjangyoram, Nagyangchun, which had been handed down as an instrumental piece without lyrics, was restored in 1960 by Lee Hye-gu, and is being passed down as the form of male and female vocals added to the instrumental accompaniment. As a result of examining the current Nagyangchun, which was formed through the process of change after Akjangyoram, it was found that there were tasks that required reconsideration of the current Nagyangchun, which is being played at the National Gugak Center, such as the arrangement of Janggu, the identification of the key, and the investigation of the lyrics. When follow-up studies are continued in the future, it will be able to contribute to the cultural transmission of Nagyangchun.