• The Journal of Korean Institute of Information Technology
• /
• v.17 no.6
• /
• pp.85-94
• /
• 2019

Warhead and debris show the different micro-Doppler frequency shape in the spectrogram because of the different micro motion. So we can classify them using the micro-Doppler features. In this paper, we classified warhead and debris in the separation phase using CNN(Convolutional Neural Networks). For the input image of CNN, we used micro-Doppler spectrogram. In addition, to improve classification performance of warhead and debris, we applied the preprocessing using CA-CFAR to the micro-Doppler spectrogram. As a result, when the preprocessing of micro-Doppler spectrogram was used, classification performance is improved in all signal-to-noise ratio(SNR).

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.8 no.2
• /
• pp.161-165
• /
• 1997

Background : The rhinomanometry and acoustic rhinometry can assess e nasal passage dynamically and statically Recently, analytic methods such as nasometer and sound spectrogram are gaining wide attention to evaluate the nasality objectively. Objectives : firstly to determine if ere was a relationship between the new methods and nasal airway resistance, and secondly to establish if the measurement of nasalance and sound spectrum could be used as an alternative to rhinomanometry and acoustic rhinometry. Materials and Methods : Thirty two patients who underwent either septoplasty and turbinectomy for nasal obstruction were studied. And their ages ranged form 15 to 45 years, with an average of 26.1 years. The rhinomanometry, nasometer, sound spectrogram were performed at preoperative and postoperative 4 weeks day. Results : After operation, subjective symptoms and rhinomanometric results were significantly improved but nasalance and slope of nana, mama and mamma passage had not meningful change. The significnat changes were noted in nasalance and first nasal formant frequency of nasal consonant of velum(angang). Conclusion : Nasometer and sound spectrogram had a limitation for the measure of nasal patency.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.05a
• /
• pp.1009-1009
• /
• 2003

VIPER a new tool for the VIsual PERception of sound quality and for sound design will be presented. Requirement for the visualization of sound quality is a signal analysis modeling the information processing of the ear. The first step of the signal processing implemented in VIPER, calculates an auditory spectrogram by a filter bank adapted to the time- and frequency resolution of the human ear. The second step removes redundant information by extracting time- and frequency contours from the auditory spectrogram in analogy to contours of the visual system. In a third step contours and/or auditory spectrogram can be resynthesised confirming that only aurally relevant information were extracted. The visualization of the contours in VIPER allows intuitively to grasp the important components of a signal. Contributions of parts of a signal to the overall quality can be easily auralized by editing and resynthesising the contours or the underlying auditory spectrogram. Resynthesis of time contours alone allows e.g. to auralize impulsive components separately from the tonal components. Further processing of the contours determines tonal parts in form of tracks. Audible differences between two versions of a sound can be visually inspected in VIPER through the help of auditory distance spectrograms. Applications are shown for the sound design of several interior noises of cars.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1044-1049
• /
• 2018

CNN (Convolutional Neural Networks) is a neural network that models animal visual information processing. And it shows good performance in various fields. In this paper, we use CNN to classify target and non-target data by analyzing the spectrogram of active sonar signal. The data were divided into 8 classes according to the ratios containing the targets and used for learning CNN. The spectrogram of the signal is divided into frames and used as inputs. As a result, it was possible to classify the target and non-target using the characteristic that the classification results of the seven classes corresponding to the target signal sequentially appear only at the position of the target signal.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.43-46
• /
• 2023

호흡기 관련 전염병의 주된 증상인 기침은 공기 중에 감염된 병원균을 퍼트리며 비감염자가 해당 병원균에 노출된 경우 높은 확률로 해당 전염병에 감염될 위험이 있다. 또한 사람들이 많이 모이는 공공장소 및 실내 공간에서의 기침 탐지 및 조치는 전염병의 대규모 유행을 예방할 수 있는 효율적인 방법이다. 따라서 본 논문에서는 탐지해야 하는 기침 소리 및 일상생활 속 발생할 수 있는 기침과 유사한 배경 소리 들을 Mel-Spectrogram으로 변환한 후 시각화된 특징을 CNN 모델에 학습시켜 기침 탐지를 진행하며, 일반적으로 사용되는 사전 학습된 CNN 모델에 제안된 Attention 모듈의 적용이 기침 탐지 성능 향상에 도움이 됨을 입증하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.685-692
• /
• 2024

In this paper, we propose a new CNN model to improve the recognition performance of command voice signals. This method obtains a spectrogram image after performing a short-time Fourier transform (STFT) of the input signal and improves command recognition performance through supervised learning using a CNN model. After Fourier transforming the input signal for each short-time section, a spectrogram image is obtained and multi-classification learning is performed using a CNN deep learning model. This effectively classifies commands by converting the time domain voice signal to the frequency domain to express the characteristics well and performing deep learning training using the spectrogram image for the conversion parameters. To verify the performance of the speech recognition system proposed in this study, a simulation program using Tensorflow and Keras libraries was created and a simulation experiment was performed. As a result of the experiment, it was confirmed that an accuracy of 92.5% could be obtained using the proposed deep learning algorithm.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.73-80
• /
• 2007

In this paper, the characteristics of noise and vibration of high speed train is analyzed depending on its speed. The speed is a very important parameter because it can affect the interaction between the train and the environment as well as the characteristics of the train itself. To measure its characteristics, we analyzed the signals from microphones and accelerometers which were attached to the passenger car of the high speed train. The signals from each sensor were stored in the recorder, and then analyzed by using the signal processing program. The data from each sensor are analyzed with the spectrogram. From the spectrogram, we found some distinct characteristics of the passenger car. Also, the characteristics of the noise propagation were inferred from the spectrogram.

• Journal of Biomedical Engineering Research
• /
• v.34 no.2
• /
• pp.47-54
• /
• 2013

Electrical stimulation is delivered to auditory nerve (AN) through the electrodes in cochlear implant system. Neurogram is a spectrogram that includes information of neural response to electrical stimulation. We hypothesized that the similarity between a neurogram and an input-sound spectrogram could show how well a cochlear implant system works. In this study, we evaluated electrical stimulus configuration of CIS strategy using the computational model. The computational model includes stochastic property and anatomical features of cat auditory nerve fiber. To evaluate similarity between a neurogram and an input-sound spectrogram, we calculated Structural Similarity Index (SSIM). The results show that the dynamic range and the stimulation rate per channel influenced SSIM. Finally, we suggested the optimal configuration within the given stimulus CIS. We expect that the results and the evaluating procedure could be employed to improve the performance of a cochlear implant system.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.19 no.2
• /
• pp.101-106
• /
• 2008

The speech signal has been put into a form suitable for storage and analysis by computer, several different operation can be performed. Filtering, sampling and quantization are the basic operation in digiting a speech signal. The waveform can be displayed, measured and even edited, and spectra can be computed using methods such as the Fast Fourier Transform (FFT), Linear predictive Coding (LPC), Cepstrum and filtering. The digitized signal also can be used to generate spectrograms. The spectrograph provide major advantages to the study of speech. So, author introduces the basic techniques for the acoustic recording, digital signal processing and the principles of spectrum and spectrogram.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.1
• /
• pp.43-47
• /
• 2016

This system is a diagnosis system that checks whether it causes a partial discharge of a power cable or not. It is to classify normal from abnormal-normal, PD (Partial Discharge) sound through analysis of RLCR (Relative Level Crossing Rate) and spectrogram energy algorithm. Partial discharge diagnostic system has a function that stores PD sound and analyzes the data. The wave shape of PD sound is similar to noise and is systematically generated by partial discharge. Therefore, in this paper, we could discreminate between normal and abnormal case using relative level crossing rate (RLCR) and spectrogram of frequency energy rate.