• The Journal of the Acoustical Society of Korea
• /
• 제24권2E호
• /
• pp.67-70
• /
• 2005

To realize a traditional music recognition system, some characteristics pertinent to Far East Asian music should be found. Using Spectrogram, some distinct attributes of Korean traditional music are surveyed. Frequency distribution, beat cycle and frequency energy intensity within samples have distinct characteristics of their own. Experiment is done for pre-experimentation to realize Korean traditional music recognition system. Using characteristics of Korean traditional music, $94.5\%$ of classification accuracy is acquired. As Korea, Japan and China have the same musical roots, both in instruments and playing style, analyzing Korean traditional music can be helpful in the understanding of Far East Asian traditional music.

• 한국멀티미디어학회논문지
• /
• 제21권9호
• /
• pp.1062-1067
• /
• 2018

Conventional active sonar technology has relied heavily on the hearing of sonar operator, but recently, many techniques for automatic detection and classification have been studied. In this paper, we extract the image data from the spectrogram of the active sonar signal and classify the extracted data using CNN(convolutional neural networks), which has recently presented excellent performance improvement in the field of pattern recognition. First, we divided entire data set into eight classes depending on the ratio containing the target. Then, experiments were conducted to classify the eight classes data using proposed CNN structure, and the results were analyzed.

• 대한기계학회논문집A
• /
• 제24권7호
• /
• pp.1731-1739
• /
• 2000

The Vibration signals of a gear driving system is often associated with gear tooth faults. Many studies have been done on the detection of impulsive vibration signals, which characterize the breaka ge of a gear tooth. Also, most of the studies on gear fault diagnosis are only about the fault existence at one gear-pair. This study concerns on the several possible faults of a geared motor that has three gear pairs. The measurement and analysis on the vibration signals of a running geared motor shows the relationship between the gear faults and the vibration signals. This study also shows that adaptive interference canceling technique can be appropriately applicable to detect which gear-pair has the fault, and that wavelet is better than spectrogram to figure out the gear fault.

• 음성과학
• /
• 제14권3호
• /
• pp.59-76
• /
• 2007

The purpose of this study is to investigate the pitch rules of Chinese poetry. Pitch rules are concerned with the high tone and the low tone. Because Chinese poetry is a fixed form of verse, it must keep pitch rules to compose Chinese poetry. But until now there has been no acoustic study of pitch rules of Chinese poetry. So, for the first time the present study investigates pitch rules of Chinese poetry acoustically. Pitch contours were analyzed from the sound spectrogram made by Praat. Results showed that actual pitch patterns did not coincide with theoretical pitch rules in reciting Chinese poetry. Therefore, in studying Chinese classics, the Chinese poetry, which has traditionally been considered to be recited according to original Chinese pitch rules, must now be considered in terms of how pitch rules may have changed over time in Korea since it was first introduce to Korean scholars.

• 한국군사과학기술학회지
• /
• 제10권3호
• /
• pp.43-50
• /
• 2007

A range-frequency interference pattern is analyzed in the course of the propagation of ship noise in shallow water. It has been shown to exhibit striated bands of intensity maxima and minima in the spectrogram. The slope of the striations is an invariant of the modal interference and is described by a waveguide invariant parameter $\beta$. It turns out that this interference pattern is useful for identifying the physical properties of the waveguide such as seabed properties. In this article, the interference pattern is analyzed using image processing techniques to produce the distribution of the beta and the effects of sediment types and geoacoustic parameters on beta distribution are examined and characterized by moments of the distributions.

• 한국임상수의학회지
• /
• 제19권1호
• /
• pp.23-27
• /
• 2002

This study was performed to compare the individual characteristics of the vocalization and behavior in the adult female German Shepherd in military service. In this study, a stranger and an other strange dog approached their kennel. Their body postures included ears forward and up, slowly wagged tails, lips raised, mouth open and teeth exposed. It was Interesting that their vocalizations were only the bark without any combination of other vocalizations. There were significant differences between duration of call(DC), pitch(P), Fl formant, F2 formant, F3 formant and F4 formant(p<0.05) except interval between call(IBC) and intensity(I) among their barks. It was suggested that the differences between same breed dogs'barks could be recognized and the data of spectrogram, especially formant contour, could be used to discriminate the sender characteristics. The body postures could also be used to understand their mind.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.1213-1214
• /
• 2023

현재 국내외 CCTV 구축량 증가로 사생활 침해와 높은 설치 비용등이 문제점으로 제기되고 있다. 따라서 본 연구는 Early Fusion을 적용한 위급상황 음향 분류 모델을 제안한다. 음향 데이터에 STFT(Short Time Fourier Transform), Spectrogram, Mel-Spectrogram을 적용해 특징 벡터를 추출하고 3차원으로 Early Fusion하여 ResNet, DenseNet, EfficientNetV2으로 학습한다. 실험 결과 Early Fusion 방법이 가장 좋은 결과를 보였고 DenseNet, EfficientNetV2가 Accuracy, F1-Score 모두 0.972의 성능을 보였다.

• 한국섬유공학회:학술대회논문집
• /
• 한국섬유공학회 1993년도 ACT 93
• /
• pp.266-272
• /
• 1993

• 한국음향학회지
• /
• 제34권4호
• /
• pp.257-263
• /
• 2015

음향 공명 이론을 이용하여 단일층 원통형 껍질 속 내부 물질의 음향 식별을 연구하였다. 원통형 껍질의 이론적인 공명 피크 주파수들은 내부 물질의 밀도 변화에 의해서는 거의 영향을 받지 않으나, 음속 변화에 의해서는 두드러지게 변화를 보인다. 이와 같은 음향 의존성을 원통형 껍질 속 내부 물질을 식별하는 데 활용할 수 있다. 단일층 원통형 껍질에 대한 음향 공명 스펙트로그램을 정규화 주파수 및 내부 물질 음속의 함수로서 이론적으로 작성한다. 이 스펙트로그램에 측정한 후방 산란 음압장의 음향 공명 피크들을 중첩함으로써 내부 물질을 음향학적으로 식별할 수 있다. 이를 실험적으로 확인하기 위하여 물, 기름 또는 에틸렌글리콜을 넣은 원통형 껍질의 후방 산란 음압장을 수조 안에서 측정하였다. 단일 송수신 방식으로 중심주파수 1.05 MHz인 음파 변환기로 측정한 후방 산란 음압장의 음향 공명 피크로 내부 물질을 식별할 수 있었다.

• 한국산학기술학회논문지
• /
• 제10권8호
• /
• pp.2110-2116
• /
• 2009

문화 산업은 보건, 의료 산업과 함께 삶의 혜택을 누릴 수 있는 기회를 제공해 주는 분야라고 할 수 있을 정도로 현대 사회에서 많은 관심을 받고 있다. 특히, 대중적 지지 기반을 보유하고 있는 음악 산업은 대중성과 독창성이 함께 공존하여 감정을 표출하고 쉽게 접근할 수 있는 예술적 가치로 인정받고 있다. 본 논문에서는 이러한 음악산업에서 핵심적인 부분이라 할 수 있는 가수의 음악적 재능을 평가하는 지표를 설계하고자 한다. 이를 위해 동일한 음악에 대한 가수의 목소리와 일반인의 목소리에서 성도의 모양 변화에 대한 분석을 수행하기 위해 스펙트로그램 분석 요소를 적용하였으며 결과 파형의 패턴 분석을 실험하여 두 집단간의 비교, 분석을 수행하였다. 따라서 실험에 사용될 대중적 음악을 선정하고 동일 부분에 대한 가수와 일반인의 목소리를 수집하여 시간의 흐름에 따른 성도 모양의 변화를 패턴 분석하고 이를 비교, 분석하여 음악성을 평가할 수 있는 지표를 설계하였다.