• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.2
• /
• pp.11-18
• /
• 2018

Severe snoring can lead to OSA(Obstructive Sleep Apnea), which can lead to life-threatening cases, and snoring can lead to serious pernicious relationships. In order to solve these snoring problems, several types of smart pillows have recently been released. The core technology is snoring discrimination technology, ie, a technique for determining whether snoring is included in the input sound. In this paper, we propose a snoring detection method to apply to a smart pillow. After extracting the features of the snoring sound from the input signal, we discriminate the snoring using these features and SVM. In order to measure the performance of the proposed method, comparative experiments with the existing methods are performed. The experimental results show about 6% better discrimination performance than the existing method.

• Journal of Sasang Constitutional Medicine
• /
• v.8 no.2
• /
• pp.191-202
• /
• 1996

Sasang constitution classification is very important subject, so many medical men studied the Sasang constitution classification but there is no certain method to classify objectively. And the purpose of this study is to help classifying Sasang constitution through correlation with sound spectrogram. This study was done it under the suppose that Sasang costitution hag correlation with sound spectrogram. The following results were obtained about correlation between sound spectrogram and Sasang constitution by comparison and analysis the pitch and reading speed of Sasang constitutions; 1. There was a similar tendency in the composition reading speed between taeeumin, soeumin and soyangin. 2. Taeeumin's center was lower measured more than soeumin's and soyangin's in the pitch graph and graph by normal curve fit and there was a similar tendency between soeumin and soyangin. 3. There was a similar tendency in the pitch graph's width between all constitutions. 4. There was a significant difference between taeeumin and soeum in the mean of three constitution's pitch, this means that taeeumin uses lower voice more than soeumin. According to the results, it is considered that there is a correlation between pitch of sound spectrogram and Sasang constitution. And method of Sasang constitution classification through sound spectrogram analysis can be one method as assistant for the objectification of Sasang constitution classification.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1606-1613
• /
• 2021

Recently various attempts to control hardware through integration of sensors and artificial intelligence have been made. This paper proposes a smart hazardous sound detection at home. Previous sound recognition methods have problems due to the processing of background sounds and the low recognition accuracy of high-frequency sounds. To get around these problems, a new MFCC(Mel-Frequency Cepstral Coefficient) algorithm using Wiener filter, modified filterbank is proposed. Experiments for comparing the performance of the proposed method and the original MFCC were conducted. For the classification of feature vectors extracted using the proposed MFCC, DNN(Deep Neural Network) was used. Experimental results showed the superiority of the modified MFCC in comparison to the conventional MFCC in terms of 1% higher training accuracy and 6.6% higher recognition rate.

• Journal of Advanced Navigation Technology
• /
• v.20 no.6
• /
• pp.604-611
• /
• 2016

Drone, which refers to unmanned aerial vehicles (UAV), industries are improving rapidly and exceeding existing level of remote controlled aircraft models. Also, they are applying automation and cloud network technology. Recently, the ability of drones can bring serious threats to public safety such as explosives and unmanned aircraft carrying hazardous materials. On the purpose of reducing these kinds of threats, it is necessary to detect these illegal drones, using acoustic feature extraction and classifying technology. In this paper, we introduce sound feature vector extraction method by harmonic feature extraction method (HLA). Feature vector extraction method based on HLA make it possible to distinguish drone sound, extracting features of sound data. In order to assess the performance of distinguishing sounds which exists in outdoor environment, we analyzed various sounds of things and real drones, and classified sounds of drone and others as simulation of each sound source.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.11
• /
• pp.11-21
• /
• 2018

Research is carried out to categorize voices using Deep Learning technology. The study examines neural network-based sound classification studies and suggests improved neural networks for voice classification. Related studies studied urban data classification. However, related studies showed poor performance in shallow neural network. Therefore, in this paper the first preprocess voice data and extract feature value. Next, Categorize the voice by entering the feature value into previous sound classification network and proposed neural network. Finally, compare and evaluate classification performance of the two neural networks. The neural network of this paper is organized deeper and wider so that learning is better done. Performance results showed that 84.8 percent of related studies neural networks and 91.4 percent of the proposed neural networks. The proposed neural network was about 6 percent high.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.4
• /
• pp.220-224
• /
• 2000

A new auscultation system for the detection of breath sound form trachea was developed in house. Small size microphone(panasonic pin microphone) was encapsuled in a housing for resonant effect, and hardware for the sound detection was fabricated. Pulmonary function test results were compared with the parameters extracted from frequency spectrum of breath sound obtained from the developed system. Results showed that the peak frequency and relative ratio of integral values between low(80∼400Hz) and high(400∼800Hz) frequency ranges revealed the significant differences. Developed system could be used for distinguishing normal subject and the patients who have pulmonary disease.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.616-621
• /
• 2006

A began of this study is to verify Spontaneous Acoustic Field Reproduction System(SAFRS), developed as an embodiment of creating agreeable sound environment, with evaluation on the field application. SAFRS is a system to sense changes of surroundings and produce sounds, which can go well with environment elements sensed by the system in to the space. The sound which can go well with environment elements is sound which judged by individual evaluation to be so, the classification of the preferred sounds according to the mood of the space was suggested in the former study. So, SAFRS was applied into the Square of D University to evaluate effectiveness of the system. The executed evaluations were 1) evaluation on sounds perception, frequency, volume and matchability with the space, 2) image evaluation on the square and sound environment and 3) evaluation on sound environment with existing sounds, fountains sound, sound produced by SAFRS, and both fountains sound and sound produced by SAFRS. Verifying SAPRS of field application was deduced from those evaluations. Theresultsofthestudyarefollowing: Though the system was applied into the space, the volume of the sounds shouldn't be too high. And with visual surroundings, the effectiveness of the system would be increased. At the results of four evaluations, the result of day evaluation is; both fountains sound and sound produced by SAFRS>fountains sound>sound produced by SAFRS>existing sounds, the result of night evaluation is; sound produced by SAFRS>both fountains sound and sound produced by SAFRS>fountains sound>existing sounds and these results pointed out that sounds environment produced by the system was highly evaluated due to less background sounds.

• Trans-
• /
• v.8
• /
• pp.1-28
• /
• 2020

This study examines musical characteristics of so-called 'Hongdae Sound' as a historic musical trend by comparing with 'US 8^th Army Sound' and British 'London Punk'. Hongdae Sound refers to the musical trend that was formed with independent bands and musicians who mostly performed live in the club called 'Drug' in Hongdae area, and voluntarily adopted minor musical sensitivity and indie spirit of 'post-punk rock' genre. But as an industrial standpoint the superficial identity of 'indie' interferes with academic approach when analysing musical aspects of Hongdae Sound. Therefore it is necessary to rearrange its characteristics as the musical trend based on regional classification in order to fully appreciate its status in history of Korean popular music. US 8^th Army Sound refers to the musical trend that was played within the live stages in US military bases in Korea. Many hired Korean musicians for those shows were able to learn the current popular musical trend in the States, and to spread those to the general public outside the bases. The industrial system of the Army Sound was very similar to that of K-Pop, but when it comes to leading the newest musical trend of 'rock-n-roll', it had more resemblance to that of Hongdae Sound. London punk was the back-to-basic form of pure rock that was armed with social angst and rebel, indie spirit. Its primal motto was 'do-it-yourself', and Hongdae Sound mostly followed its industrial, musical and spiritual paths. London punk was short-lived because it abandoned its indie spirits and became absorbed to the mainstream. But Hongdae sound maintain its longevity by maintaining the spirit and truthfulness of indie, while endlessly experimenting with new trends.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.11-21
• /
• 2021

The causes of noise generation according to the classification of indoor spaces are very diverse. Individual happiness is infringed by this noise. In this paper, We tried to visualize the spatial sound characteristics of public places using sound color to express them so that anyone can sympathize. The noise inside a conference room of a medical device company was measured for 100 minutes, and the frequency band was divided into three different types of existing sound pressure expression units. Because the size of the noise is expressed differently depending on the situation, There are cases where there is a difference of opinion between the measurer and the researcher. This noise measurement experiment was conducted, and the sound color was applied to classify it on a log scale considering auditory characteristics. As a result of comparing this with the result expression for different loudness expression units, A specific table in different units yielded almost similar results. In addition, the sound source section for 100 minutes was divided into three analysis sections, the analysis sections were different, and the size of the energy ratio for each analysis section was divided in the form of an envelope. The characteristics of the low-frequency region of the space have a high energy ratio, and the decrease in the energy ratio according to the increase in frequency is constant and regular. You can see that conversations are possible.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.395-401
• /
• 2023

Sound Event Detection (SED) aims to identify not only sound category but also time interval for target sounds in an audio waveform. It is a critical technique in field of acoustic surveillance system and monitoring system. Recently, various models have introduced through Detection and Classification of Acoustic Scenes and Events (DCASE) Task 4. This paper explored how to design optimal parameters of DenseNet based model, which has led to outstanding performance in other recognition system. In experiment, DenseRNN as an SED model consists of DensNet-BC and bi-directional Gated Recurrent Units (GRU). This model is trained with Mean teacher model. With an event-based f-score, evaluation is performed depending on parameters, related to model architecture as well as model training, under the assessment protocol of DCASE task4. Experimental result shows that the performance goes up and has been saturated to near the best. Also, DenseRNN would be trained more effectively without dropout technique.