http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Automatic melody extraction algorithm using a convolutional neural network
( Jongseol Lee ),( Dalwon Jang ),( Kyoungro Yoon ) 한국인터넷정보학회 2017 KSII Transactions on Internet and Information Syst Vol.11 No.12
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.
Korean Traditional Music Genre Classification Using Sample and MIDI Phrases
( Jongseol Lee ),( Myeongchun Lee ),( Dalwon Jang ),( Kyoungro Yoon ) 한국인터넷정보학회 2018 KSII Transactions on Internet and Information Syst Vol.12 No.4
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.
Kim Jongseol,Lee Ahmi,Moon Yong-Suk,So Jae-Seong,Koh Sung-Cheol The Microbiological Society of Korea 2006 The journal of microbiology Vol.44 No.1
We investigated the effects of halogenated aromatic compounds (HACs) including naturally occurring ones (L-thyroxine, 3-chloro-L-tyrosine, 5-chloroindole, 2-chlorophenol, 4-chlorophenol and chlorobenzene) on polychlorinated biphenyl (PCB) dechlorination in sediment cultures. A PCB-dechlorinating enrichment culture of sediment microorganisms from the St. Lawrence River was used as an initial inoculum. When the culture was inoculated into Aroclor 1248 sediments amended with each of the six HACs, the extent of dechlorination was not enhanced by amendment with HACs. The dechlorination patterns in the HAC-amended sediments were nearly identical to that of the HAC-free sediments except the 3-chloro-L-tyrosine-amended ones where no dechlorination activity was observed. When these sediment cultures were transferred into fresh sediments with the same HACs, the dechlorination specificities remained the same as those of the initial inoculations. Thus, in the present study, the substrate range of the highly selected enrichment culture could not be broadened by the HACs. It appears that HACs affect PCB dechlorination mainly through population selection rather than enzyme induction of single population.
이아미,김나영,김소연,김종설,Lee Ahmi,Kim Nayoung,Kim Soyeon,Kim Jongseol 한국미생물학회 2005 미생물학회지 Vol.41 No.3
To assess microbiological indoor air quality in schools, concentrations of viable airborne microorganisms were monitored at classrooms and corridors of 3 middle or high schools in Ulsan. Airborne microorganisms were sampled at various situations during a semester (class-hour, lunchtime, after school) and during a vacation with an impaction-type air sampler. During the semester, the number of bacteria was the highest at lunchtime in corridor with an average of $1,111\;MPN/m^{3}$ and lowest at class-hour in corridor with an average of $132\;MPN/m^{3}$. During the vacation, the bacterial concentrations at classrooms and corridors were only $5{\%}$ and $27{\%}$ of the values during class-hours of the semester, respectively. Among the colonies tested, $60{\%}$ were identified as relatively harmless Micrococcus species and $12{\%}$ were Staphylococcus species. During the semester, the average values of fungal concentrations at each situation ranged from 105 to $213\;MPN/m^{3}$, and the values during the vacation were $32\;MPN/m^{3}$ at classrooms and $83\;MPN/m^{3}$ in corridors. Fungal genera such as Cladosporium, Penicillium, and Aspergillus were identified from the colonies. The obtained data can be considered as a step to set a guideline for bioaerosols in indoor environment of schools. 미생물학적 실내공기질을 평가하기 위하여, 울산에 위치한 중${\cdot}$고등학교 3곳이 교실과 복도에서, 학기 중(수업시간, 점심시간, 방과 후)과 방학 중 등 상황별로 공기중 미생물의 농도를 조사하였다. 미생물의 포집에는 충돌식 공기 채취기를 사용하였으며, 세균수는 plate count agar, 진균수는 dichloran rose bengal chloramphenicol agar를 사용하여 측정하였고, 이들 배지로부터 세균과 진균을 분리하여 동정하였다. 학기 중 세균 농도는 점심시간의 복도에서 평균 $1,111\;MPN/m^{3}$로 가장 높았고, 수업시간의 복도에서 평균 $132\;MPN/m^{3}$로 가장 낮았으며, 방학 중의 측정값은 교실과 복도에서 각각 학기 중 수업시간의 $5{\%}$와 $27{\%}$ 수준이었다. 조사한 집락의 $60{\%}$는 병원성과 관련이 적은 Micrococcus spp.로 동정되었고. Staphylococdcus 속은 $12{\%}$를 차지하였다. 학기 중 진균의 평균 농도는 상황별로 $105{\~}213\;MPN/m^{3}$의 범위였으며, 방학 중의 측정값은 교실과 복도에서 각각 $32\;MPN/m^{3}$와 $83\;MPN/m^{3}$이었다. 공기중 진균의 집락으로부터 Cladosporium 속, Penicillium 속, Aspergillus 속 등을 확인할 수 있었으며, 언급한 3 속이 조사한 집락의 $77{\%}$를 차지하였다. 연구의 결과는 학교 실내에서 학생수와 함께 활동성과 연관된 상황에 따른 세균 농도의 변이를 보여주었으며, 학교 환경에서 bioaerosol의 허용수준을 결정함에 있어 이를 고려해야 함을 제안하고 있다.