• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.155-160
• /
• 2021

This paper proposes an automatic method for detecting snore sound, one of the important symptoms of sleep apnea patients. In the proposed method, sound signals generated during sleep are input to detect a sound generation section, and a spectrogram transformed from the detected sound section is applied to a classifier based on a Convolutional Bidirectional Gated Recurrent Unit (CBGRU) with attention mechanism. The applied attention mechanism improved the snoring sound detection performance by extending the CBGRU model to learn discriminative feature representation for the snoring detection. The experimental results show that the proposed snoring detection method improves the accuracy by approximately 3.1 % ~ 5.5 % than existing method.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2003.05a
• /
• pp.1-4
• /
• 2003

본 연구는 경편성물의 특성에 영향을 미치는 중요한 구조변수인 조직, 편환의 계폐여부, 가이드바의 상호 움직임 방향에 따른 소리특성과 생리적 반응 사이의 관계를 파악함으로써 총합적 감성소재 설계를 위한 기초 자료를 제공하고자 하였다. 직물소리발생장치를 이용하여 7가지의 경편성물에 대한 마찰음을 녹음한 후, 이를 마찰음이 유발하는 생리반응을 측정하여 slow alpha파, fast beta파, ECG R-R, RESP, HF/LF, SCL, PV등을 분석하였다. 조직에 따라서는 LPT, Loundness(Z), Roughness(Z)와 Fluctuation strength(Z) 가장 큰 Sharkskin에서 fast beta파, ECG R-R, RESP는 증가하였으며 slow alpha파, PV, HF/LF는 감소하였다. 편환의 개폐여부에서는 폐환보다는 개환에서 Loudness(Z), Sharpness(Z), Fluctuation strength(Z)가 증가하였으며 RESP는 증가하고 HF/LF는 감소하여 개환이 더 불쾌한 감성을 유발하였다. 가이드바의 상호 움직임 방향은 counter보다는 parallel에서 slow alpha의 변화량이 감소하고 fast beta의 변화량이 증가하여 counter보다는 parallel이 더 불쾌한 감성을 유발하는 것으로 보인다. 또한 편성물의 음향특성 중 ΔL, Δf 와 Roughness(Z), Fluctuation Strength(Z)가 생리반응을 예측하는 중요한 요인으로써 나타났다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.595-596
• /
• 2016

열차의 진로를 변경시키는 선로전환기의 고장은 탈선 등과 같은 대형 사고를 유발시킬 수 있는 중요한 시설이다. 따라서 열차운행 안전 측면에서 해당 설비에 대한 모니터링은 필수적이다. 본 논문에서는 선로전환기의 구동 시 발생하는 소리 정보를 이용하여 선로전환기의 이상상황을 탐지하는 시스템을 제안한다. 먼저 제안한 시스템은 소리 센서에서 실시간으로 취득하는 소리 신호를 Power Spectral Density(PSD) 특징으로 변환한다. 추출된 PSD 특징은 이미 성능이 입증된 딥러닝의 대표적인 모델인 Convolutional Neural Network(CNN)에 적용하여 이상상황을 탐지한다. 실제 선로전환기의 전환 시 발생하는 소리 데이터를 취득하여 모의실험을 수행한 결과, 비정상 상황을 안정적으로 탐지함을 확인하였다.

• Korean journal of applied entomology
• /
• v.50 no.4
• /
• pp.383-393
• /
• 2011

Because communication facilitates behaviors that are critical for survival and reproduction, it is central to the study of behavior and evolution. One of the most important and difficult issues with respect to communication has been the definition of communication itself. Broadly, it can be defined as an exchange of information from a signaler to a receiver. However, evolution of a signal is likely possible only under conditions in which both the signaler and receiver increase fitness from the exchange of information, often referred to as "true communication." The three primary sensory channels of communication used by animals are chemical, visual, and acoustic. Chemical signals are the oldest and most widespread method of communication. Visual and acoustic signals convey a great deal of information due to ease of modulation, flexibility of signal production, and fast transmission. The most widespread contexts in which animals communicate are sexual interaction and conflict resolution. Signals used for sexual interaction typically contain information about species identity and sexual attractiveness, whereas signals used for conflict resolution may contain information about resource holding potential. Other contexts under which animals communicate include territorial defense, parent-offspring interactions, social integration, sharing of environmental information, and auto-communication.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.7
• /
• pp.836-842
• /
• 2023

Under the Welfare of Disabled Persons Act, the national qualification test allows disabled and non-disabled people to appear for the same test, and the deaf do not fall under the reason for disqualification from obtaining a license for power-driven water leisure crafts; therefore, even the deaf can obtain a license. During a risk of collision at sea, ships and power-driven water leisure crafts notify the other party of dangerous signals such as maneuvering and warning signals through sound signals to prevent accidents that may occur because surrounding ships are not visible. However, a method is required to prevent marine accidents that may occur when the deaf cannot hear danger signals through sounds from nearby ships or power-driven water leisure crafts during leisure activities owing to hearing impairment. A sound reception system is a device installed on a ship where missionary work is completely deposed to display the amplification of external sounds and the direction of sound reception on the screen. Through visual display of sound signals such as dangerous signals that cannot be heard owing to hearing impairment, improvement measures were proposed to prevent marine accidents that can occur owing to the inability of the deaf to check sound signals during leisure activities.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.489-491
• /
• 2013

In this paper, Electronic Drum based on Arduino and Processing language to communicate with a computer is implemented. First, we made a drum pad by using piezoelectric sensors. The drum pads prevent damage to the sensor and new mechanism was fabricated to mitigate the impact structure. Arduino connected to the pad, the sensor detects a signal when the shock sends it to Arduino. The received signal of Arduino sends a signal to the computer, and the signal received is stored in the computer to output sound of the drum. Through this structure, the micro-controller, the computer and communications technology can be combined and applicable to a many system.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.7
• /
• pp.323-327
• /
• 2007

In this paper, objectively quantified consonance of complex sound is proposed as a new psychoacoustical parameter. Proposing algorithm quantifies consonance of complex sound after applying psycho acoustical models which are parts of human perception such as masking effect, equal loudness contour, and critical band. To verify proposing algorithm, experiments with 10 car horn signals which have different complex sound were performed. The experiments show cross correlation of 0.95 between objectively quantified consonance by proposing algorithm and subjectively assessed consonance by listening tests. Considering the fact that there are few psychoacoustical parameter except Zwicker parameter, proposing algorithm will help to quantify psychoacoustical effect of complex sounds objectively.

• Korean Journal of Optics and Photonics
• /
• v.32 no.3
• /
• pp.108-113
• /
• 2021

We propose and experimentally demonstrate a method of remote sound extraction using laser Doppler interferometry. The output frequency of a laser Doppler interferometer changes to be the same as the frequency of the acoustic wave from than object vibrated by the sound due to the Doppler effect. Based on this phenomenon, we measure the vibrational frequency of a remote target affected by a sound wave in real time, via laser Doppler interferometry. We track the peak frequency of the interferometer's output via appropriate signal processing, which confirms that the characteristics of the so detected wave are the same as that of the original sound source. We also confirm that the same method can retrieve the sound waves not only from remote sources of single tones, but from those of any sound.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.31-37
• /
• 2022

This paper proposes a study on applying signal processing and deep learning for sound recognition that detects sounds commonly heard in daily life (Screaming, Clapping, Crowd_clapping, Car_passing_by and Back_ground, etc.). In the proposed sound recognition, several techniques related to the spectrum of sound waves, augmentation of sound data, ensemble learning for various predictions, convolutional neural networks (CNN) deep learning, and two-dimensional (2-D) data are used for improving the recognition accuracy. The proposed sound recognition technology shows that it can accurately recognize various sounds through experiments.

• Journal of KSNVE
• /
• v.2 no.4
• /
• pp.243-252
• /
• 1992

인체의 귀는 물리적인 크기에 비해 탁월한 능력을 가지고 있는 감각기관이다. 귓바퀴에 모여진 미소한 압력변동은 4cm의 길이에 놓여져 있는 귓구멍, 중이 및 내이 를 통해 작게는 수백 배, 크게는 1,000배까지 기계적으로 증푹시킨다. 불과 완두콩 만한 크기의 달팽이관에서는 소리의 스펙트럼을 순간적으로 분석 처리하며, 비선형 적으로 신호를 압축시키는 응답특성을 가지고 있다. 또, 수많은 청신경 세포가 내재 되어 있어, 들은 소리를 대뇌에서 이용할 수 있는 신경 신호로 변환시켜 준다. 귀가 가지고 있는 신비로운 능력중에서 우리가 알고 있는 지식은 극히 일부에 머무르고 있으며 아직도 많은 의문점이 해답을 기다리고 있다. 국내에서도 하루빨리 공학과 의학 분야가 협력하여 우리가 모르고 있는 청감의 신비를 규명하고 소음이 인체에 미치는 영향에 대한 한국판 연구 결과가 축적될 수 있기를 기대한다.