• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.472-484
• /
• 2019

This paper proposes a time-domain sound event detection algorithm using DNN (Deep Neural Network). In this system, time domain sound waveform data which is not converted into the frequency domain is used as input to the DNN. The overall structure uses CRNN structure, and GLU, ResNet, and Squeeze-and-excitation blocks are applied. And proposed structure uses structure that considers features extracted from several layers together. In addition, under the assumption that it is practically difficult to obtain training data with strong labels, this study conducted training using a small number of weakly labeled training data and a large number of unlabeled training data. To efficiently use a small number of training data, the training data applied data augmentation methods such as time stretching, pitch change, DRC (dynamic range compression), and block mixing. Unlabeled data was supplemented with insufficient training data by attaching a pseudo-label. In the case of using the neural network and the data augmentation method proposed in this paper, the sound event detection performance is improved by about 6 %(based on the f-score), compared with the case where the neural network of the CRNN structure is used by training in the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.708-717
• /
• 2017

Tracking of sound-location is widely used in various area such as intelligent CCTV, video conference and voice commander. In this paper we introduce the real-time sound-location tracking method for smart lecture system using TDoA(Time Difference of Arrival) with orthogonal microphone array on the ceiling. Through discussion on some models of TDoA detection, cross correlation method using linear microphone array is proposed. Orthogonal array with 5 microphone could detect omni direction of sound-location. For real-time detection we adopt the threshold of received energy for eliminating no-voice interval, signed cross correlation for reducing computational complexity. The detected azimuth angles are processed using median filter for lowering the angle deviation. The proposed system is implemented with high performance MCU of TMS320F379D and MEMs microphone module and shows the accuracy of 0.5 and 6.5 in degree for white noise and lectured voice, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1820-1825
• /
• 2004

In this paper, we propose a humanoid active audition system which detects the direction of sound and performs speech recognition using just three microphones. Compared with previous researches, this system comprises simpler algorithm and better amplifier system having advantages to increase a detectible distance of sound signal in spite of simple circuit. In order to verify our system's performance, we install the proposed active audition system to the home service robot, called Hombot II, which has been developed at the KIST (Korea Institute of Science and Technology), thus we confirm excellent performance by experimental results

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2007.02a
• /
• pp.35-40
• /
• 2007

본 논문에서는 사운드디자이너가 주어진 영상조건 속에서 음원(sound source)을 어떻게 구성하고, 디자인하고, 믹싱하는가 에 따라 수용자의 그 감응도(감정적변화:sympathy response)와 인지도(이해와 기억도:acknowl-edgment)가 달라질 수 있는가를 분석하고자 한 것이다. 그 방법으로 영상음향의 구조에서 음악, 음향, 대사의 상호크기, 연결, 편집, 강조, 등을 달리한 영상 내에서 사운드디자인과 믹싱을 달리하여 실험하였으며 주관적평가방법과 뇌파변화측정방법 2가지로 하여 비교, 평가 분석하고자 했다. 사운드의 디자인구조가 수용자에게 미치는 영향도를 알아보는 이러한 연구는 영화, 방송 등 미디어사운드에서 사운드디자인 구조를 어떻게 만들어야 하는가? 에 대한 방법론적 정리에 기여할 것으로 기대된다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.04a
• /
• pp.662-663
• /
• 2014

In most vehicle manufactures have traditionally relied on find-fix method of human auditor, mainly due to variation excitation source. To solve the BSR noise, the requirements for BSR test are presented in terms of detection of noise source, analysis of time-frequency and sound pressure, sound quality for noise. A number of new technology direction, particularly in the field of noise source identification application and psycho-acoustics from the Zwicker's sound quality parameter, the computed objective sound metrics and subjective jury test result.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1113-1116
• /
• 2003

In this paper, it is suggested that the technology sound measurement which is to search the inferiority of the plate during the pressing. We evaluate whether there is a inferiority by analysing and comparing the satisfactory and inferior plate with the method of a spectrum analysis by measuring the sound which is emitted during pressing. We designed the analysis algorithm to detect inferior plate throughout comparison of measured sound data using FFT, DFT and DASYLab S/W. In addition to these, we suggest the way to compare both inferior and satisfactory signal statistically.

• Proceedings of the KSR Conference
• /
• 2006.11b
• /
• pp.144-151
• /
• 2006

Sound generated from a moving vehicle often carries information on the condition of vehicle, for example, whether it has faults or not, where the fault exists. The latter is possible especially by MFAH(moving frame acoustic holography) and beamforming method. MFAH is applicable to the sound source of pure tone or narrow band noise. For the beamforming method, we have to know what kind of wave the sound source radiates, for example, plane wave or spherical wave. That is, whether the above methods are applicable depends on the characteristics of sound source. To apply these methods to the fault detection, we have to know the characteristics of wave from faults. In this research, a machine diagnosis technique based on the above holographic approaches is introduced to find the position of faults. The signal due to faults is modeled based on the fact that the faults radiate impulsive noise, and analyzed in time and frequency domain. The way how MFAH and beamforming method can be used is introduced to find the position of source.

• Journal of KIISE
• /
• v.43 no.1
• /
• pp.13-26
• /
• 2016

This paper proposes a new sound localization algorithm that can improve localization performance based on a tetrahedron-shaped microphone array. Sound localization system estimates directional information of sound source based on the time delay of arrival(TDOA) information between the microphone pairs in a microphone array. In order to obtain directional information of the sound source in three dimensions, the system requires at least three microphones. If one of the microphones fails to detect proper signal level, the system cannot produce a reliable estimate. This paper proposes a tetrahedron- shaped sound localization system with a coordinate transform method by adding one microphone to the previously known triangular-shaped system providing more robust and reliable sound localization. To verify the performance of the proposed algorithm, a real time simulation was conducted, and the results were compared to the previously known triangular-shaped system. From the simulation results, the proposed tetrahedron-shaped sound localization system is superior to the triangular-shaped system by more than 46% for maximum sound source detection.

• Journal of Ocean Engineering and Technology
• /
• v.8 no.1
• /
• pp.62-70
• /
• 1994

In order to estimate the detection range of a active SONAR system, the SONAR equation is commonly used. In this paper, an algorithm to calculate detection range in active SONAR system as function of SONAR depth and target depth is presented. For given SONAR parameters and environment, the transmission loss and background level are found, signal excess is computed. Using log-normal distribution, signal excess is converted to detection probability at each range. Then, the detection range is obtained by integrating the detection probability as function of range for each depth. The proposed algorithm have been applied to the case of omni-directional source with center frequency 30Hz for summer and winter sound profiles. It is found that the optimal search depth is the source depth since the detection range increase at source depth where the signal excess is maximized.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.5
• /
• pp.241-246
• /
• 2001

The conventional stethoscope can not store its stethoscopic sounds. Therefor a doctor diagnoses a patient with instantaneous stethoscopic sounds at that time, and he can not remember the state of the patient's stethoscopic sounds on the next. This prevent accurate and objective diagnosis. If the electronic stethoscope, which can store the stethoscopic sound, is developed, the auscultation will be greatly improved. This study describes an amplifier for electronic stethoscope system that can extract heart sounds of fetus as well as adult and alow us hear and record the sounds. Using the developed stethoscopic amplifier, clean heart sounds of fetus and adult can be heard in noisy environment, such as a consultation room of a university hospital, a laboratory of a university. Surprisingly, the heart sound of a 22-week fetus was heard through the developed electronic stethoscope. Pitch detection experiments using the detected heart sounds showed that the signal represents distinct periodicity. It can be expected that the developed electronic stethoscope can substitute for conventional stethoscopes and if proper analysis method for the stethoscopic signal is developed, a good electronic stethoscope system can be produced.