• Proceedings of the KSR Conference
• /
• 한국철도학회 2006년도 추계학술대회 논문집
• /
• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2002년도 추계학술발표논문집 (상)
• /
• pp.747-750
• /
• 2002

본 논문에서는 일반적으로 사용되는 마이크가 잡음에 민감하여 음성인식피치 성능을 저하시키기 때문에 잡음치 영향을 받지 않는 고지향성을 가지는 넥마이크로 입력되는 음성신호에 대한 특성을 고찰하고 기존의 일반마이크 입력 음성을 이용하는 인식시스템에서의 인식성능을 살펴본다. 넥마이크는 일반마이크와 동일한 원리로 음성을 채집하는 목부위에 장착된다. 실험에서 넥마이크에 의한 음성은 일반마이크 입력 음성에 비해 인식 성능이 저하되는 결과를 보여주어 앞으로 새로운 인터페이스의 연구대상으로 여겨진다.

• Journal of the Korean Institute of Navigation
• /
• 제20권4호
• /
• pp.71-79
• /
• 1996

When navigating in or near an area of restricted visibility, it is necessary to be heard the whistle, bell and/or the siren of lighthouses or ships at times. Even though we can get the brief informations about the property of sound, the direction and range of a sound radiator, it is not enough to get the accurate informations for decision making. Generally the audio frequency is known as 16~20, 000Hz, but the earshot is shorten and discrimination of sound is more difficult when there is some noise. The sound pressure is 60dB at the moment when human speaks 1 meter away. Usually the noise pressures are 40dB in a silent room and 60dB on the quiet street, respectively. It this study, the basic algorithm and a method of signal processing are suggested to trace the direction and range of the source radiator using the signals received through not a physical sense but the microphone sensors.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 1993년도 하계학술대회 논문집 B
• /
• pp.692-694
• /
• 1993

Acoustic noise from the various facilities makes man unpleasant and let researchers find the way for reducing it on environmental point of view. Special way to reduce the acoustic noise had suggested by the concept of Active Silencer. But, it has propagation delay time accumulated during the signal passage and howling effect. This paper suggestes a way to anhilate howling effects, and reduces the total delay time drasticaly by attaching microphone to the speaker. This paper will show how it works by some materials.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 한국소음진동공학회 2001년도 추계학술대회논문집 II
• /
• pp.1132-1137
• /
• 2001

The smart foam that is first proposed by Fuller(2) is not applicable to active noise control in a duct having flow. Thus. this paper presents the ring-type smart foam as an alternative. The ring-type smart foam consists of polyurethane acoustic foam of lining shape and PVDF film embedded along the mid-surface of the foam lining. A feedforward adaptive filtered-x LMS controller is used to minimize the signal from the error microphone. To enlarge quiet sound region. two error microphones are used to update system modeling filter (SIMO method). Sound intensity control using the ring-type smart foam is also discussed

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• 제14권7호
• /
• pp.569-576
• /
• 2004

In this paper, to detect external sound frequencies on the latticed structure, fiber optic sensor net using Sagnac interferometer was fabricated and tested. The latticed structure was fabricated with a dimension of 50 cm in width and 50 cm in height. The optical fiber of 50m in length was distributed and fixed on the surface of the latticed structure. Single mode fiber, a laser with 1,550 nm in wavelength, 2 ${\times}$ 2 coupler were used. External sound signal, 240 Hz, 495 Hz, 1.445 kHz, 2k Hz, applied to the fiber optic sensor net and the detected optical signals were compared to the detected microphone signals against time and frequency domains. Based on the experimental results, fiber optic sensor net using Sagnac interferometer detected external sound frequency, effectively. This system can be expanded to the structural health monitoring system.

• Journal of the Korea Society of Computer and Information
• /
• 제24권9호
• /
• pp.21-27
• /
• 2019

In this paper, we propose a deep auto-encoder-based pipe leak detection (PLD) technique from time-series acoustic data collected by microphone sensor nodes. The key idea of the proposed technique is to learn representative features of the leak-free state using leak-free time-series acoustic data and the deep auto-encoder. The proposed technique can be used to create a PLD model that detects leaks in the pipeline in an unsupervised learning manner. This means that we only use leak-free data without labeling while training the deep auto-encoder. In addition, when compared to the previous supervised learning-based PLD method that uses image features, this technique does not require complex preprocessing of time-series acoustic data owing to the unsupervised feature extraction scheme. The experimental results show that the proposed PLD method using the deep auto-encoder can provide reliable PLD accuracy even considering unsupervised learning-based feature extraction.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제14권6호
• /
• pp.1249-1256
• /
• 2019

In this paper, we propose a new algorithm to remove acoustic feedback and noise in hearing aids. Instead of using the conventional FIR structure, this algorithm is a deep learning algorithm using neural network adaptive prediction filter to improve the feedback and noise reduction performance. The feedback canceller first removes the feedback signal from the microphone signal and then removes the noise using the Wiener filter technique. Noise elimination is to estimate the speech from the speech signal containing noise using the linear prediction model according to the periodicity of the speech signal. In order to ensure stable convergence of two adaptive systems in a loop, coefficient updates of the feedback canceller and noise canceller are separated and converged using the residual error signal generated after the cancellation. In order to verify the performance of the feedback and noise canceller proposed in this study, a simulation program was written and simulated. Experimental results show that the proposed deep learning algorithm improves the signal to feedback ratio(: SFR) of about 10 dB in the feedback canceller and the signal to noise ratio enhancement(: SNRE) of about 3 dB in the noise canceller than the conventional FIR structure.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• 제22권6호
• /
• pp.725-733
• /
• 1998

The pressure fluctuation on the surface of a submerged body has been recognized as a dominant noise source. There have been many studies concerning the flow induced noise on a flat plate. However, the noise over an axisymmetric body has not been well reported. This paper addresses the way in which we have investigated the mechanism of noise generation due to an axisymmetric body. The associated experiments and signal processing methods are introduced. A 3-dimensional axisymmetric body whose length and diameter were 2 m and 10.4 cm, was prepared as a test specimen. The wall pressure on the surface of the body was measured in a large scale low noise wind tunnel at KIMM(Korea Institute of Machinery and Metals). To measure the wall pressure, we used two microphone arrays which were tangential and normal to the flow. Based on the measured signal, frequency-wavenumber spectrum which explains the structure of turbulence noise, was estimated. Tangential to the flow, there exists convective ridge at a relatively higher wavenumber region; this can cause spatial aliasing. To circumvent this problem, the cross spectrum was interpolated. The interpolation has been performed by unwrapping the phase and smoothing the cross spectrum. The phase unwrapping was done based on the Corcos model; the phase of cross spectrum decreases linearly with the distance between microphones. Aforementioned signal processings are possible by employing the experimental results that the estimated wavenumber spectrum quite resembles the Corcos model. We try to modify the Corcos model which is applicable to the flat plate, by altering the magnitude of cross spectrum to fit the experimental data more accurately. We proposed that this wavenumber spectrum model is suitable for the 3-dimensional axisymmetric body. Normal to the flow, there exists a little correlation between signals of different microphones. The circumferential wavenumber spectrum contains uniform power along the wavenumbers.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제15권5호
• /
• pp.807-812
• /
• 2020

This paper proposes a blind speech source separation algorithm using a microphone to separate only the target speech source signal in an environment in which various speech source signals are mixed. The proposed algorithm is a model of frequency domain representation based on independent component analysis method. Accordingly, for the purpose of verifying the validity of independent component analysis in the frequency domain for two speech sources, the proposed algorithm is executed by changing the type of speech sources to perform speech sources separation to verify the improvement effect. It was clarified from the experimental results by the waveform of this experiment that the two-channel speech source signals can be clearly separated compared to the original waveform. In addition, in this experiments, the proposed algorithm improves the speech source separation performance compared to the existing algorithms, from the experimental results using the target signal to interference energy ratio.