• The Journal of the Acoustical Society of Korea
• /
• v.29 no.4
• /
• pp.243-250
• /
• 2010

This paper proposes a spectral modeling of Korean traditional instrument, Haegeum, using cepstral analysis to naturally describe Haegeum sounds varying with time. To get a precise result of cepstral analysis, we set the frame size to 3 periods of input signal and more cepstral coefficients are used to extract formants. The performance is enhanced by flexibly controlling the cutoff frequency of bandpass filter depending on the resonances in the synthesis process of sinusoidal components and the deleting peaks remained in the residual signal. To detect the change of pitch, we divide the input frames into silence, attack, and sustain region and determine which region the current frame is involved in. Then, the proposed method readjusts the frame size according to the fundamental frequency in the case of the current frame is in attack region and corrects the extraction errors of the fundamental frequency for the frames in sustain region. With these processes, the synthesized sounds are much more similar to the originals. The evaluation result through the listening test by a Haegeum player says that the synthesized sounds are almost similar to originals (96~100 % similar to the original sounds).

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.6
• /
• pp.526-533
• /
• 2009

This paper proposes a formant synthesis method of Haegeum sounds using cepstral envelope for spectral modeling. Spectral modeling synthesis (SMS) is a technique that models time-varying spectra as a combination of sinusoids (the "deterministic" part), and a time-varying filtered noise component (the "stochastic" part). SMS is appropriate for synthesizing sounds of string and wind instruments whose harmonics are evenly distributed over whole frequency band. Formants extracted from cepstral envelope are parameterized for synthesis of sinusoids. A resonator by Impulse Invariant Transform (IIT) is applied to synthesize sinusoids and the results are bandpass filtered to adjust magnitude. The noise is calculated by first generating the sinusoids with formant synthesis, subtracting them from the original sound, and then removing some harmonics remained. Linear interpolation is used to model noise. The synthesized sounds are made by summing sinusoids, which are shown to be similar to the original Haegeum sounds.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.193-204
• /
• 2019

The explosion of data due to the improvement of sensor technology and computing performance has become the basis for analyzing the situation in the industrial fields, and various attempts to detect events based on such data are increasing recently. In particular, sound signals collected from sensors are used as important information to classify events in various application fields as an advantage of efficiently collecting field information at a relatively low cost. However, the performance of sound-event classification in the field cannot be guaranteed if noise can not be removed. That is, in order to implement a system that can be practically applied, robust performance should be guaranteed even in various noise conditions. In this study, we propose a system that can classify the sound event after generating the enhanced sound signal based on the deep learning algorithm. Especially, to remove noise from the sound signal itself, the enhanced sound data against the noise is generated using SEGAN applied to the GAN with a VAE technique. Then, an end-to-end based sound-event classification system is designed to classify the sound events using the enhanced sound signal as input data of CNN structure without a data conversion process. The performance of the proposed method was verified experimentally using sound data obtained from the industrial field, and the f1 score of 99.29% (railway industry) and 97.80% (livestock industry) was confirmed.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.124-129
• /
• 2006

음악은 소리를 즐긴다는 뜻을 담고 있다. 감상자에게 단순한 청각적 자극을 넘어 즐거움을 주기 위해선 음악적인 경험이 뒷받침되어야 한다. 가상 현실을 이용한 사용자와 시스템 간의 상호작용을 음악 경험 제공에 접목하려는 시도는, 새로운 경험을 통해 일반인들이 보다 쉽게 음악을 접하고 체험함으로써 음악을 통해 즐거움을 얻을 수 있도록 도움을 주는 데에 그 목적이 있다. 가상 오케스트라를 구현하고 지휘 동작을 재현하는 것은 이러한 가능성을 극대화하는 연구이다. 본 논문에서는 가상 오케스트라를 구현하기 위해 필수적인 중간 단계로, 사용자의 지휘 동작을 감지하여 연주의 박자(속도)를 제어하는 지휘 시뮬레이션 시스템을 제시한다. 실제의 지휘 동작을 분석하고, 동작의 변화를 인식하기 위하여 가속도 센서를 이용, 공간상에서 지휘봉의 움직임을 가속도 정보로 수집하여 이에 상응하는 박자의 제어를 구현한다. 사용자의 박자 명시에 따라 변화하는 상하 방향의 가속도를 센서를 통해 전압 신호로 입력 받고, DSP 의 A/D conversion 모듈에서 디지털 신호로 변환, 일정 수준 이상의 신호를 박자 정보로 직렬통신을 통해 컴퓨터에 전달한다. 컴퓨터에서는 Max/MSP를 이용하여 각 박자 사이의 시간 간격을 측정하고 상응하는 MIDI 음악을 재생하는 방식으로 시스템이 구현된다. 기존 연구에서 사용된 CCD 카메라에 의한 Motion Tracking 을 보완하여 동작의 크기에 따라 음량을 조절한다. 본 논문에서 제시되는 시스템은 지휘 동작에서 가장 특징적으로 나타나는 상하 방향의 급격한 가속도 변화를 직접 입력 받기 때문에 기존 시스템에 비해 지휘 동작의 인식 성공률을 높일 수 있으며, 화상 처리 및 계산에 의한 지연을 최소화할 수 있다. 또한, 장치의 규모를 소형화하여 보다 지휘봉의 형태에 가까운 인터페이스를 제공하며, 적합한 응용 콘텐츠를 접목할 경우 게임 컨트롤러로의 발전 가능성이 있다.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.600-605
• /
• 2020

In this paper, we propose a sound event detection method using a multi-channel multi-scale neural networks for sound sensing home monitoring for the hearing impaired. In the proposed system, two channels with high signal quality are selected from several wireless microphone sensors in home. The three features (time difference of arrival, pitch range, and outputs obtained by applying multi-scale convolutional neural network to log mel spectrogram) extracted from the sensor signals are applied to a classifier based on a bidirectional gated recurrent neural network to further improve the performance of sound event detection. The detected sound event result is converted into text along with the sensor position of the selected channel and provided to the hearing impaired. The experimental results show that the sound event detection method of the proposed system is superior to the existing method and can effectively deliver sound information to the hearing impaired.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.1
• /
• pp.14-19
• /
• 2018

Recently, the smart health care industry has been rising rapidly and interest and efforts for public health have been greatly increased. As a result, the public does not visit medical specialists and medical facilities, but the desire to check their health condition in everyday life is increased. Therefore, many domestic and foreign companies continuously research and develop wearable devices that can measure body activity information anytime and anywhere And the market. Especially, it is used for heart activity measurement device using pulse wave sensor and electrocardiogram sensor. However, in this study, a monitoring system that can detect cardiac activity using cardiac sounds, heart sound measurement rather than pulse wave measurement and electrocardiogram measurement, was performed and its performance was evaluated. Experimental results confirmed the predictability of cardiac heart rate and heart valve disease during daily living.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.485-491
• /
• 1997

This paper describes the relationship between skin impedance signal, behavioral signal, and subjective evaluation depending on arousal level. Nz and reaction time had similar trend with mKSS level, but eyeblink rate was different from these two parameters. eye-blink rate increased slowly from mKSS level 1 to 5, and had high increasing rate at mKSS 7. But it showed steep descent at mKSS level 9. Each subject showed different eye-blink rates, but changing rates of EBR was similar at eachm KSS level. Therefore it suggests that rising rate of EBR can be used arousal level criterion. From the result of reaction time test. human performance was decreased rapidly above the mKSS level 5, and false positive and false negative data was observed above the mKSS level 3. It is desirable to give a subject some stimuli such as sound or aroma to rise arousal level between mKSS level 3 and mKSS level 5.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.3A
• /
• pp.198-204
• /
• 2011

Acoustic communication system is a transmission technology sending sound and data simultaneously. However, data signal can be audible in this system when data is transmitted with high transmission power. The more transmission power is reduced, the more distance that can transmit data is shortened. Therefore, the study that increase the transmission distance is needed. In this paper, we would like to increase transmission distance by adapting receive diversity in acoustic communication system. We measure received performance of both proposed system and Single Input Sing Output (SISO) system according to distance with same transmission power. When SISO satisfies Bit Error Rate (BER) of $7{\times}10^{-3}$ at about 2m, Selection Combining (SC) technique satisfies 2 meters, and Equal Gain Combining (EGC) technique satisfies 4 meters.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1506-1513
• /
• 2019

Recently, as the industrial scope of multi-rotor unmanned aerial vehicles(UAV) is greatly expanded, the demands for data collection, processing, and analysis using UAV are also increasing. However, the acoustic data collected by using the UAV is greatly corrupted by the UAV's motor noise and wind noise, which makes it difficult to process and analyze the acoustic data. Therefore, we have studied a method to enhance the target sound from the acoustic signal received through microphones connected to UAV. In this paper, we have extended the densely connected dilated convolutional network, one of the existing single channel acoustic enhancement technique, to consider the inter-channel characteristics of the acoustic signal. As a result, the extended model performed better than the existed model in all evaluation measures such as SDR, PESQ, and STOI.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.491-498
• /
• 2022

In our daily life, quality of sleeping is closely related to happiness index. Whether or not people perceive sleep disturbance as a chronic disease, people complain of many difficulties, and in their daily life, they often experience difficulty breathing during sleep. It is very important to automatically recognize breathing-related disorders during a sleep, but it is very difficult in reality. To solve this problem, this paper proposes a mobile-based non-contact sleeping monitoring for health management at home. Respiratory signals during the sleep are collected by using the sound sensor of the smartphone, the characteristics of the signals are extracted, and the frequency, amplitude, respiration rate, and pattern of respiration are analyzed. Although mobile health does not solve all problems, it aims at early detection and continuous management of individual health conditions, and shows the possibility of monitoring physiological data such as respiration during the sleep without additional sensors with a smartphone in the bedroom of an ordinary home.