• Title/Summary/Keyword: 음악 특징 추출

Search Result 79, Processing Time 0.023 seconds

Multistage Feature-based Classification Model (다단계 특징벡터 기반의 분류기 모델)

  • Song, Young-Soo;Park, Dong-Chul
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.46 no.1
    • /
    • pp.121-127
    • /
    • 2009
  • The Multistage Feature-based Classification Model(MFCM) is proposed in this paper. MFCM does not use whole feature vectors extracted from the original data at once to classify each data, but use only groups related to each feature vector to classify separately. In the training stage, the contribution rate calculated from each feature vector group is drew throughout the accuracy of each feature vector group and then, in the testing stage, the final classification result is obtained by applying weights corresponding to the contribution rate of each feature vector group. In this paper, the proposed MFCM algorithm is applied to the problem of music genre classification. The results demonstrate that the proposed MFCM outperforms conventional algorithms by 7% - 13% on average in terms of classification accuracy.

High Precision Audio Contents Retrieval Method by Effective Melody Representation Method (효과적인 멜로디 표현법에 의한 고정도 오디오 콘텐츠 검색 기법)

  • Heo Sung-Phil;Suk Soo-Young;Chung Hyun-Yeol
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • autumn
    • /
    • pp.147-150
    • /
    • 2004
  • 허밍에 의한 고정도의 오디오 정보 검색 시스템을 구현하기 위해서는 시스템 측에서 발생 가능한 문제점과 유저 측에서 발생 가능한 문제점을 함께 고려한 해결 기법이 요구된다. 유저 측에서는 허밍시 자신의 애매한 기억에 기인한 음표의 삽입이나 탈락과 같은 가창실수, 허밍 도중에 음정 및 박자의 불안정한 변화, 같은 곡을 노래 부를지라도 개인차에 의해 상이한 음정과 템포 등이 발생한다. 또한 시스템 측에서 발생 가능한 사항으로써, 비록 허밍질의가 완벽하더라도 입력 허밍 신호를 멜로디 매칭에 이용되는 정확한 특징량의 추출 및 음악 표기로의 변환이 어렵다는 점이다. 종래의 오디오 정보 검색 시스템에서는 이러한 문제점을 해결하기 위해 다양한 멜로디 표현법과 매칭 방법이 제안되고 있으나, 성능 면에서는 아직 만족할 만한 결과를 얻지 못하고 있다. 따라서 이러한 문제점들을 해결하기 위해서 본 논문에서는 허밍 멜로디의 효과적인 표현방법과 시스템 및 유저 측에서 발생 가능한 오류에 강건한 멜로디 매칭 방법을 제안한다.

  • PDF

Advanced Multistage Feature-based Classification Model (진보된 다단계 특징벡터 기반의 분류기 모델)

  • Kim, Jae-Young;Park, Dong-Chul
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.47 no.3
    • /
    • pp.36-41
    • /
    • 2010
  • An advanced form of Multistage Feature-based Classification Model(AMFCM), called AMFCM, is proposed in this paper. AMFCM like MFCM does not use the concatenated form of available feature vectors extracted from original data to classify each data, but uses only groups related to each feature vector to classify separately. The prpposed AMFCM improves the contribution rate used in MFCM and proposes a confusion table for each local classifier using a specific feature vector group. The confusion table for each local classifier contains accuracy information of each local classifier on each class of data. The proposed AMFCM is applied to the problem of music genre classification on a set of music data. The results demonstrate that the proposed AMFCM outperforms MFCM by 8% - 15% on average in terms of classification accuracy depending on the grouping algorithms used for local classifiers and the number of clusters.

Automatic Recognition and Performance of Printed Musical Sheets Using Fuzzy ART (퍼지 ART 알고리즘을 이용한 인쇄 악보의 자동 인식과 연주)

  • Kim, Kwang-Baek;Lee, Won-Joo;Woo, Young-Woon
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.6 no.1
    • /
    • pp.84-89
    • /
    • 2011
  • Musical sheet recognition is an emerging area as the role of computers in music increases. Although there are several well-known programs for composition, they have a limitation in that they cannot edit or play music generated from other programs. In this paper, we propose an algorithm that can read, recognize, and play music using printed sheets. The proposed algorithm first removes lines using horizontal histogram and extracts symbols. The symbols belong to one of the three categories; notes, rests, and other signs. Notes are recognized using the context information and rests and signs are recognized using a fuzzy ART algorithm. The proposed algorithm were applied to 50 pages of musical sheets and the experimental results showed that it is effective in automatic recognition of musical sheets.

The Melodic Structure of the Bulmosan Youngsanjae, Ongho-ge (불모산 영산재 범패 옹호게의 선율구조)

  • Choi, Heon
    • (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.

Detecting Prominent Content in Unstructured Audio using Intensity-based Attack/release Patterns (발생/소멸 패턴을 이용한 비정형 혼합 오디오의 주성분 검출)

  • Kim, Samuel
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.50 no.12
    • /
    • pp.224-231
    • /
    • 2013
  • Defining the concept of prominent audio content as the most informative audio content from the users' perspective within a given unstructured audio segment, we propose a simple but robust intensity-based attack/release pattern features to detect the prominent audio content. We also propose a web-based annotation procedure to retrieve users' subjective perception and annotated 18 hours of video clips across various genres, such as cartoon, movie, news, etc. The experiments with a linear classification method whose models are trained for speech, music, and sound effect demonstrate promising - but varying across the genres of programs - results (e.g., 86.7% weighted accuracy for speech-oriented talk shows and 49.3% weighted accuracy for {action movies}).

A Study on An Identification System for Scanned Cartoon Book (북스캔 만화 저작물 식별 시스템에 관한 연구)

  • Han, Byung Jun;Kim, Tae-Hyun;Kang, Ho-Gap;Cho, Seong-Hwan;Lee, Kyun Young
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.14 no.1
    • /
    • pp.131-137
    • /
    • 2014
  • Although illegal reproduction of cartoon books are prevalent with rapid growth of webhard services and smartphone use, fingerprinting technology for product identification, as seen in music and videos, has not been developed yet. This leads to indiscriminate illegal reproduction of cartoon books, causing great amount of copyright damages from copyright infringement of the rightful owners. The copyright R&D project granted from the Korea Copyright Permission (Project Title: Identification and Copy Protection Technology of Bookscaned Text/Comic Books) has been carried out in order to develop technology to effectively identify illegal reproduction and distribution of scanned cartoon books. The developed technology will contribute to increase of royalty payments and robust ecosystem of cartoon book markets. The study is to propose an enhanced implementation model for identification of scanned cartoon books on the basis of hierarchical symmetric difference feature algorithms adopted from existing feature extraction algorithms for video.

Deep Learning based Raw Audio Signal Bandwidth Extension System (딥러닝 기반 음향 신호 대역 확장 시스템)

  • Kim, Yun-Su;Seok, Jong-Won
    • Journal of IKEEE
    • /
    • v.24 no.4
    • /
    • pp.1122-1128
    • /
    • 2020
  • Bandwidth Extension refers to restoring and expanding a narrow band signal(NB) that is damaged or damaged in the encoding and decoding process due to the lack of channel capacity or the characteristics of the codec installed in the mobile communication device. It means converting to a wideband signal(WB). Bandwidth extension research mainly focuses on voice signals and converts high bands into frequency domains, such as SBR (Spectral Band Replication) and IGF (Intelligent Gap Filling), and restores disappeared or damaged high bands based on complex feature extraction processes. In this paper, we propose a model that outputs an bandwidth extended signal based on an autoencoder among deep learning models, using the residual connection of one-dimensional convolutional neural networks (CNN), the bandwidth is extended by inputting a time domain signal of a certain length without complicated pre-processing. In addition, it was confirmed that the damaged high band can be restored even by training on a dataset containing various types of sound sources including music that is not limited to the speech.

A Study of the Time-Space and Appreciation for the Performance Culture of Gwanseo Region in Late Joseon Period: Focusing on Analysis of Terminology (조선후기 관서지방의 공연 시공간과 향유에 관한 연구)

  • Song, Hye-jin
    • (The) Research of the performance art and culture
    • /
    • no.22
    • /
    • pp.287-325
    • /
    • 2011
  • This paper studies the time-space and appreciation of the performance culture of Gwanseo region, which is considered to have formed a characteristic culture in late Joseon period. For this purpose, 4 gasa written in hangeul (Korean alphabet), as well as 4 yeonhaeng gasa, 108 articles of Gwanseoakbu were examined. Plus, among the 9 types of yeonhaengrok (Documents of Performance culture) written in Chinese character, those parts which describe the performance traits have been analyzed. Then, 'main list of terminology' has been deduced based on the categorization according to the following points : 1) subjects of performance and appreciation 2) time and period of performance 3) space of performance 4) contents of performance 5) background and motive for performance and 6) method of performance. Through this process, various 'nouns' and 'predicate verbs' in relation to performance culture emerged, which were systemized according to types of performance elements and categories. Major terminology includes predicate verbs and symbolic verbs such as nokuihongsang,' 'baekdaehongjang,' 'jeolsaekgeumga,' 'cheonga,' 'hwaryu,' 'gamuja,' and 'tongsoja,' as well as the terms already known such as gisaeng, iwon, yangbang, akgong, and jeonak, which refer to musicians and dancers. Subjects of performance were divided into performers and listeners, categorized into concert, music, and dance, according to performance form. In the case for music, it was divided into instrumental or vocal, solo or accompanied (byeongju, self-accompaniment). In the case for vocal music, noteworthy was the inclusion of profesional artist's singing (called gwangdae or uchang). The record of 23 names of popular artists from Gwanseo region, with mention of special talents for each person, reflects the degree of activeness and artistic level of the province. Depending on the appreciating patrons, the audience were indicated as the terms including 'yugaek (party guest),' jwasang,' 'on jwaseok,' and 'sonnim (guests).' It seems that appraisal for a certain performance was very much affected by the tastes, views, and disposition of the appreciating patrons. Therefore it is interesting to observe different comparative reviews of concerts of different regions given by literary figures, offering various criticism on identical performance. In terms of performance space, it has been divided into natural or architectural space, doing justice to special performance sites such as a famous pavilion or an on-the-boat performance. Specific terms related to the scale and brightness of stage, as well as stage props and cast, based on descriptions of performance space were found. The performance space, including famous pavilions; Yeongwangjeong, Bubyeokru, Baeksangru, Wolparu, and Uigeomjeong, which are all well-known tourist sites of Gwanseo province, have been often visited by viceroys. governors, and envoys during a tour or trip. This, and the fact that full-scale performances were regularly held here, and that more than 15 different kinds of boats which were used for boat concert are mentioned, all confirm the general popularity of boat concerts at the time. Performance time, categorized by season or time of day (am/pm/night) and analyzed in terms of time of occurrence and duration, there were no special limitation as to when to have a performance. Most morning concerts were held as part of official duties for the envoys, after their meeting session, whereas evening concerts were more lengthy in duration, with a greater number of people in the audience. In the case of boat concert, samples include day-time concert and performances that began during the day and which lasted till later in the evening. Major terminology related to performance time and season includes descriptions of time of day (morning, evening, night) and mention of sunset, twilight, moonlight, stars, candles, and lamps. Such terms which reflect the flow of time contributed in making a concert more lively. Terminology for the contents of performance was mostly words like 'instrumental,' 'pungak,' or 'pungnyu.' Besides, contextual expressions gave hints as to whether there were dance, singing, ensemble, solo, and duets. Words for dance and singing used in Gwanseo province were almost identical to those used for gasa and jeongjae in the capital, Hanyang. However, many sentences reveal that performances of 'hangjangmu' of hongmunyeon, sword dance, and baettaragi were on a top-quality level. Moreover, chants in hanmun Chinese character and folk songs, which are characteristic for this region, show unique features of local musical performance. It is judged that understanding the purpose and background of a performance is important in grasping the foundation and continuity of local culture. Concerts were usually either related to official protocol for 'greeting,' 'sending-off,' 'reports,' and 'patrols' or for private enjoyment. The rituals for Gwanseo province characteristically features river crossing ceremony on the Daedong river, which has been closely documented by many. What is more, the Gwanseo region featured continued coming and goings of Pyeongan envoys and local officers, as well as ambassadors to and fro China, which required an organized and full-scale performance of music and dance. The method of performance varied from a large-scale, official ones, for which female entertainers and a great banquet in addition to musicians were required, to private gatherings that are more intimate. A performance may take the form of 'taking turns' or 'a competition,' reflecting the dynamic nature of the musical culture at the time. This study, which is deduction of terminology in relation to the time-space and appreciation culture of musical performances of Gwanseo region in late Joseon period, should be expanded in the future into research on 'the performance culture unique to Gwanseo region,' in relation to the financial and administrative aspects of the province, as well as everyday lifestyle. Furthermore, it could proceed to a more intensive research by a comparative study with related literary documents and pictorial data, which could serve as the foundation for understanding the use of space and stage, as well as the performance format characteristic to Korean traditional performing arts.