• The Journal of the Acoustical Society of Korea
• /
• v.35 no.2
• /
• pp.143-148
• /
• 2016

Deep neural network that effectively capture the characteristics of data has been widely used in various applications. However, the amount of sound database is often insufficient for learning the deep neural network properly, so resulting in overfitting problems. In this paper, we propose a transfer learning framework that can effectively train the deep neural network even with insufficient sound event data by employing rich speech or music data. A series of experimental results verify that proposed method performs significantly better than the baseline deep neural network that was trained only with small sound event data.

• Journal of Advanced Navigation Technology
• /
• v.20 no.4
• /
• pp.367-373
• /
• 2016

We propose an improved direction of arrival (DoA) estimation algorithm based on co-prime array and propagator method. The propagator method with co-prime array does not require singular value decomposition (SVD) requiring much less computational complexity but exhibiting somewhat worse performance in comparison with MUSIC based on co-prime array. We notice that one cause of the performance degradation was in the avoidance of the usage of the diagonal elements of the signal autocorrelation matrix that contains the noise power spectral density. So we propose an algorithm with the diagonal elements of the signal autocorrelation matrix based on the fact that the noise power spectral density can be estimated using noise observation over a long period of time. We observe, through simulations, that the proposed scheme in this paper improves the performance, with 4 times more computational requirement, by signal-to-noise ratio of 1.5dB and by DoA resolution of $0.7^{\circ}$ at the detection probability of 95% compared with the previously introduced co-prime array propagator scheme, resulting in performance much closer to that of co-prime array-based MUSIC scheme.

• Sijohaknonchong
• /
• v.24
• /
• pp.223-258
• /
• 2006

This Research is about the classification of 'Sijochang', or the Korean ode narrative song, in terms of music. Contrary to the literature classification by the number of letters, sijochang varies with the melody. Literally, the classification is generally made as Dansijo(or short ode) Jungsijo(or medium ode) and Jangsijo(or lengthy ode) but the sijochang is normally divided into 'Pyongsijo' (or plain ode), 'Jirumsijo and Saseolsijo'. As while the same Sijochang is called under the different names, the different type of sijochang is also called as the same name, it needs the discussion about its name. Some Korean classical musicians have attempted to define it but they are trying to do it without the specific reasoning about its concept. As a result, the systematic research is required. This study designs to streamline the currently confusing and complex names and set up the sijo's classification system. After reviewing the ancient music note, current sijo score and the traditional theory, I largely classified it into 3 types: Pyongsijo, Jirumsijo and Saseolsijo. And then, 1 analyzed on to which type the sijochang which is presently called belongs, based on several principles. The 67 names of the sijo which I have investigated about are classified with them sharpy reduced into 16. Among the current sijo names. there are some which are of same type yet of different phonetics and there are others which are of different phonetics yet of same type. To avoid such complex and troublesome names, I have orchestrated them as follows, taking the literary and music concept into account. 1) Pyongsijo type : Pyongsijo, Joongherisijo, Wujosijo and Payeonkok 2) Jirumsijo type: Jirumsiro, Namchangjirumsijo(it refers to Jirumsijo sung by male ), Yeochangjirumsijo (it refers to Jirumsijo sung by female), Banjirumsijo(it refers to half the Jiumsiro), Onjirumsijo (it refers to the whole Jirumsijo), Wujojr\irumsijo, Saseoljirumsijo and Whimorisijo) 3) Saseolsijo type : Saseolsijo, Bansaseolsijo(it refers to half the Saseolsijo, Gaksijo or Pyongsiro There are still lots of things to musically streamline, in the fields of disposition of Sijo letters, its form, musical scale and influences on other genre. etc. and as such. the accumulation of theory on them is urgently required. Those musical elements need an in-depth review and study by the experts and the Korean traditional musicians. Later research is expected to play a role of exploring it.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.1 s.45
• /
• pp.51-56
• /
• 2007

Feature functions were used for the classification of music. The spectral roll-off, variance, average peak level, and class were chosen to make up a feature function vector. Among these, it is the spectral roll-off function that has a low-frequency to high-frequency ratio. To find the optimal roll-off point, the roll-off points from 0.05 to 0.95 were swept. The classification success rate was monitored as the roll-off point was being changed. The data that were used for the experiments were taken from the sounds made by a modern violin and a baroque one. Their shapes and sounds are similar, but they differ slightly in sound texture. As such, the data obtained from the sounds of these two kinds of violin can be useful in finding an adequate roll-off point. The optimal roll-off point, as determined through the experiment, was 0.85. At this point, the classification success rate was 85%, which was the highest.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1E
• /
• pp.88-97
• /
• 1995

The main purpose of this paper is to show the realizaability of the proposed highly effective direction finiding method which performs extremely well under the circumstances like low signal-to-noise ratio (S/N), very closely located signal sources, and so on. In order to achieve the purpose, the degree to which the proposed method is superior to the MUSIC(multiple signal classification) with respect to the S/N is discussed, and the result is analyzed in terms of the S/N and the number of sample data.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.29-30
• /
• 2017

본 논문에서는 인간의 청각 기관을 모델링 한 스파이크그램 (spikegram)을 이용한 심층 신경망 기반의 음악 장르 분류 기술을 제안한다. 분류 대상은 GTZAN 데이터 세트의 10개 장르로 정의한다. 본 논문에서는 청각 기관의 인식 방법을 모델링한 방법을 이용하여 스파이크그램을 구하고, 스파이크그램에서 새로운 특성 벡터를 추출하는 방법을 제안한다. 제안하는 방법을 통해 심층 신경망에 적합한 특성 벡터를 구하고 이렇게 구한 특성 벡터로 신경망을 학습시켜 기존에 사용하던 다양한 방법들보다 높은 성능을 얻을 수 있다.

• 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.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.4
• /
• pp.167-172
• /
• 2014

In this paper we propose a waveform design algorithm that localizes the maximum output power in the target direction. We extend existing monostatic radar optimal waveform design schemes to bistatic multiple-input multiple-output (MIMO) radar systems. The algorithm simultaneously calculates the direction of departure (DoD) and the direction of arrival (DoA) using a two-dimensional multiple signal classification (MUSIC) method, and successfully localizes the maximum transmitted power to the target locations by exploiting the calculated DoD. The simulation results confirm the performance of the proposed algorithm.

• Journal of the Korean Society for Library and Information Science
• /
• v.35 no.4
• /
• pp.79-95
• /
• 2001

This study suggests adaptations and expansions of DDC 21 for the Korean libraries. Adapted and expanded tables of Table 2, Table 5, and Table 6 are added regularly in the related subjects in the schedules. Classes of 200 Religion and 745.61 Calligraphy are newly adapted and expanded. Classes for Oriental medicine (610.95) and Korean music (789) are suggested. Other classes of 030, 050, 060, 070, 080, 181, 310, 340, 400, 800, 915, 950 are adapted based on the previous studies.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.211-214
• /
• 2008

일부 음악 장르분류에 관한 기존 연구에서는 특징 추출을 위한 구간 선택 시 사람이 직접 음악의 주요 구간을 지정하는 방법을 사용하였다. 이러한 방법은 분류 성능이 좋은 반면 수작업으로 인한 부담으로 새롭게 등록되는 음악들에 대해 지속적으로 적용하기가 곤란하다. 이러한 이유로 최근 음악 장르 분류와 관련된 연구에서는 자동으로 추출구간을 선정하는 방법을 사용하고 있는데 이러한 연구의 대부분이 고정된 구간 (예, 30초 이후의 30초 구간)에서 특징을 추출하는 관계로 분류의 정확도가 떨어지는 문제점을 갖고 있다. 본 논문에서는 이러한 문제점을 해결하기 위해 음악 전체 구간에 대하여 반복구간을 파악하고, 그 중 음악을 대표할 수 있는 단일 대표구간을 선정한 후, 대표구간으로 부터 특징을 추출하여 장르 분류 시스템에 적용하는 방법을 제안하였다. 실험 결과, 기존 고정구간을 사용한 방법에 비해 괄목할 만한 성능 향상을 얻을 수 있었다.