• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.60-65
• /
• 2018

In this paper, a covariance matrix and modulogram are proposed for realizing amphibian sound classification using CNN (Convolutional Neural Network). First of all, a database is established by collecting amphibians sounds including endangered species in natural environment. In order to apply the database to CNN, it is necessary to standardize acoustic signals with different lengths. To standardize the acoustic signals, covariance matrix that gives distribution information and modulogram that contains the information about change over time are extracted and used as input to CNN. The experiment is conducted by varying the number of a convolutional layer and a fully-connected layer. For performance assessment, several conventional methods are considered representing various feature extraction and classification approaches. From the results, it is confirmed that convolutional layer has a greater impact on performance than the fully-connected layer. Also, the performance based on CNN shows attaining the highest recognition rate with 99.07 % among the considered methods.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.19 no.2
• /
• pp.133-135
• /
• 2008

Background and Objectives: The voice changes can occur in peritonsillar abscess and the labeling of this changes as a "muffled voice". The aim of this study was to investigate the changes in acoustic feature of voice before and after treatment in patients with peritonsillar abscess. Materials and Method: 12 patients with peritonsillar abscess were enrolled in the study. Acoustic analysis on sustained Korean vowels /a/, /i/ and /u/ were performed before and after treatment. Results: In patients with peritonsillar abscess, the first formant frequency (F1) and second formant frequency (F2) of /a/ were decreased. There was tendency of articulation of back-low vowel /a/ as back-high vowel /u/. F1 of /i/ and /u/ were increased, while F2 were decreased. There was tendency of articulation of front-high vowel /i/ as back-low vowel /a/. The third, forth, fifth formant frequency (F3, F4, F5) of /a/, /i/ and /u/ were decreased although statistically not significant. Conclusion: The anatomical and functional changes of oropharynx by peritonsillar abscess can cause changes in resonance and speech quality. We suggest that these changes could be the cause of 'muffled voice' in patients of peritonsillar abscess.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.21 no.1
• /
• pp.48-53
• /
• 2010

Backgraound and Objectives : The voice change can occur in acute epiglottitis or peritonsillar abscess, and the labelings of both changes as a "muffled voice" or "hot potato voice", The aim of this study was to investigate the difference of changes in acoustic feature of voice before and after treatment in patients with acute epiglottitis or peritonsillar abscess. Subjects and Method: 13 patients with acute epiglottitis and 12 patients with peritonsillar abscess were enrolled in the study. Acoustic analysis on sustained Korean vowels /${\alpha}$/, /u/ and /i/ were performed before and after treatment. Results: In patients with acute epiglottitis, the first formant frequency (F1) of /${\alpha}$/ was increased, and the second frequency (F2) of /i/ was decreased. In patients with peritonsillar abscess, F1 and F2 of /${\alpha}$/ were decreased. F1 of /i/ and /u/ were increased, while F2 were decreased. Conclusion : The anatomical and functional changes of oropharynx and larynx by acute epiglottitis and peritonsillar abscess can cause different change in resonance and speech quality. We suggest that these changes could be the cause of 'muffled vocie' in patients of acute epiglottitis or peritonsillar abscess, but different characteristics of phonation in each disease should be distinguished.

• Phonetics and Speech Sciences
• /
• v.11 no.2
• /
• pp.57-64
• /
• 2019

In this paper, we construct a Korean text-to-speech system using the Merlin toolkit which is an open source system for speech synthesis. In the text-to-speech system, the HMM-based statistical parametric speech synthesis method is widely used, but it is known that the quality of synthesized speech is degraded due to limitations of the acoustic modeling scheme that includes context factors. In this paper, we propose an acoustic modeling architecture that uses deep neural network technique, which shows excellent performance in various fields. Fully connected deep feedforward neural network (DNN), recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional LSTM (BLSTM) are included in the architecture. Experimental results have shown that the performance is improved by including sequence modeling in the architecture, and the architecture with LSTM or BLSTM shows the best performance. It has been also found that inclusion of delta and delta-delta components in the acoustic feature parameters is advantageous for performance improvement.

• Journal of The Korean Astronomical Society
• /
• v.35 no.1
• /
• pp.59-65
• /
• 2002

Solar observations support that magnetic reconnect ion ubiquitously occurs in the chromosphere as well as in the corona. It is now widely accepted that coronal magnetic reconnect ion is fast reconnect ion of the Petschek type, and is the main driver of solar flares. On the other hand, it has been thought that the traditional Sweet-Parker model may describe chromospheric reconnect ion without difficulty, since the electric conductivity in the chromoshphere is much lower than that in the corona. However, recent observations of cancelling magnetic features have suggested that chromospheric reconnect ion might proceed at a faster rate than the Sweet-Parker model predicts. We have applied the Sweet-Parker model and Petschek model to a well-observed cancelling magnetic feature. As a result, we found that the inflow speed of the Sweet-Parker reconnect ion is too small to explain the observed converging speed of the feature. On the other hand, the inflow speeds and outflow speeds of the Petschek reconnect ion are well compatible with observations. Moreover, we found that the Sweet-Parker type current sheet is subject to the ion-acoustic instability in the chromosphere, implying the Petschek mechanism may operate there. Our results strongly suggest that chromospheric reconnect ion is of the Petschek type.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1487-1494
• /
• 2011

In this paper, a novel genre classification algorithm is proposed for music recommendation system. Especially, to improve the classification accuracy, the band-pass filter for octave-based spectral contrast (OSC) feature is designed considering the psycho-acoustic model and actual frequency range of musical instruments. The GTZAN database including 10 genres was used for 10-fold cross validation experiments. The proposed multiple-octave based OSC produces better accuracy by 2.26% compared with the conventional OSC. The combined feature vector based on the proposed OSC and mel-frequency cepstral coefficient (MFCC) gives even better accuracy.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1233-1241
• /
• 2019

The goal of the sound-based mechanical fault diagnosis technique is to automatically find abnormal signals in the machine using acoustic emission. Conventional methods of using mathematical models have been found to be inaccurate due to the complexity of industrial mechanical systems and the existence of nonlinear factors such as noise. Therefore, any fault diagnosis issue can be treated as a pattern recognition problem. We propose an automatic fault diagnosis method using discrete wavelet transform and power spectrum density using multi pattern recognition. First, we perform DWT-based filtering analysis for noise cancelling and effective feature extraction. Next, the power spectral density(PSD) is performed on each subband of the DWT in order to effectively extract feature vectors of sound. Finally, each PSD data is extracted with the features of the classifier using multi pattern recognition. The results show that the proposed method can not only be used effectively to detect faults as well as apply to various automatic diagnosis system based on sound.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2002.07b
• /
• pp.894-899
• /
• 2002

In this papers, we proposed the new method in order to diagnosis partial discharge type of transformers. For wavelet transform, Daubechies filter is used, we can obtain wavelet coefficients which is used to extract feature of statistical parameters (maximum value, average value, dispersion, skewness, kurtosis) about high frequency current signal per 3-electrode type (needle-plane electrode, IEC electrode and Void electrode.). Also. these coefficients are used to identify Signal of internal partial discharge in transformer. As a result. from compare of high frequency current signal amplitude and average value. we are obtained results of IEC electrode> Void electrode> Needle-Plane electrode. otherwise. In case of skewness and kurtosis, we are obtained results of Void electrode> IEC electrode > Needle-Plane electrode. As Improved method in order to diagnosis partial discharge type of transformers, we use neural network.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2000.05a
• /
• pp.5-12
• /
• 2000

본 연구에서, Daubechies'Mother Wavelet를 이용한 이산 웨이블렛 변환(Discrete Wavelet Transform)에 기초한 새롭고 효과적인 특정추출방법을 제안하였다. 특정추출을 이용하여 응용방향을 설명하고 또는 통계적 파라메터의 평가를 행하였다. 본 연구에서는 다음과 같은 몇 가지 사실을 알 수 있었다. 1. 시스템에서 발생된 (인가전압이 0[V]) 노이즈라 볼 수 가있는 렌덤노이즈(Random Noise)를 디지털필터인 FIR(Finite Impulse Response)필터를 통하여 상당한 노이즈를 억제할 수가 있었다. 2. 이산 웨이블렛 변환 시 레벨 1~4까지 변환한 결과 최적의 변환상태 Level-3을 기준으로 하였다. 3. 특정추출 파라메터는 음향방출신호의 최대값, 평균값, 분산, 왜도, 첨쇄도를 특정추출파라메터로 이용하였다. 4. 특정추출 결과를 이용하여 전체 열화시간 중 대표적 음향방출신호 중 초기열화신호, 중기열화신호, 말기열화신호를 얻을 수 있었다. 이런 특정추출을 통하여 변압기열화상태를 진단할 수 있는 가능성을 확인 할 수가 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.629-636
• /
• 2022

We present a preprocessing method for an underwater target detection model based on a convolutional neural network. The acoustic characteristics of the ship show ambiguous expression due to the strong signal power of the low frequency. To solve this problem, we combine feature preprocessing methods with various feature scaling methods and spectrogram methods. Define a simple convolutional neural network model and train it to measure preprocessing performance. Through experiment, we found that the combination of log Mel-spectrogram and standardization and robust scaling methods gave the best classification performance.