• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.7
• /
• pp.1263-1269
• /
• 2016

Hearing impaired persons are exposed to the danger since they can't be aware of many dangerous situations like fire alarms, car hones and so on. Therefore they need haptic or visual informations when they meet dangerous situations. In this paper, we design a dangerous sound detection engine for hearing impaired. We consider four dangerous indoor situations such as a boiled sound of kettle, a fire alarm, a door bell and a phone ringing. For outdoor, two dangerous situations such as a car horn and a siren of emergency vehicle are considered. For a test, 6 data sets are collected from those six situations. we extract LPC, LPCC and MFCC as feature vectors from the collected data and compare the vectors for feasibility. Finally we design a matching engine using an artificial neural network and perform classification tests. We perform classification tests for 3 times considering the use outdoors and indoors. The test result shows the feasibility for the dangerous sound detection.

• Journal of Korea Multimedia Society
• /
• v.14 no.7
• /
• pp.884-894
• /
• 2011

We proposed a new algorithm for detection of first(S1) and second heart sound(S2). Many researches for detecting primary components and those algorithms have good performance at normal heart sound, but the performance is degraded at abnormal heart sound which is contain murmurs generated by heart disease. Therefore we proposed the S1, S2 detection algorithm using three-order Shannon energy difference. Using S1, S2's character which has large energy difference than murmurs, it is reduced noise and detected S1, S2. According to simulation results, not only normal heart sound but also abnormal heart sound, the proposed algorithm has better performance than former study at abnormal heart sound.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.437-439
• /
• 2006

Actually, The present traffic accident detection system is subsisting limitation of accurate distinction under the crowded condition at intersection because the system defend upon mainly the image information at intersection and digital image processing techniques nearly all. To complement this insufficiency, this article aims to estimate the level of present technology and a realistic possibility by analyzing the acoustic characteristic of crash sound that we have to investigate for improvement of traffic accident detection rate at intersection. The skid sound of traffic accident is showed the special pattern at 1[kHz])${\sim}$3[kHz] bandwidth when vehicles are almost never operated in and around intersection. Also, the frequency bandwidth of vehicle crash sound is showed sound pressure difference oyer 30[dB] higher than when there is no occurrence of traffic accident below 500[Hz].

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.605-607
• /
• 2023

Recent research has highlighted the effectiveness of Deep Learning (DL) techniques in automating the detection of lung sound anomalies. However, the available lung sound datasets often suffer from limitations in both size and balance, prompting DL methods to employ data preprocessing such as augmentation and transfer learning techniques. These strategies, while valuable, contribute to the increased complexity of DL models and necessitate substantial training memory. In this study, we proposed a streamlined and lightweight DL method but effectively detects lung sound anomalies from small and imbalanced dataset. The utilization of 1D dilated convolutional neural networks enhances sensitivity to lung sound anomalies by efficiently capturing deep temporal features and small variations. We conducted a comprehensive evaluation of the ICBHI dataset and achieved a notable improvement over state-of-the-art results, increasing the average score of sensitivity and specificity metrics by 2.7%.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.3
• /
• pp.234-239
• /
• 2015

Non-Negative Matrix Factorization (NMF) is a method for updating dictionary and gain in alternating manner. Due to ease of implementation and intuitive interpretation, NMF is widely used to detect and separate overlapping sound events. However, NMF that utilizes non-negativity constraints generates parts-based representation and this distinct property leads to a dictionary containing fragmented acoustic events. As a result, the presence of shared basis results in performance degradation in both separation and detection tasks of overlapping sound events. In this paper, we propose a new method that utilizes K-Singular Value Decomposition (K-SVD) based dictionary to address and mitigate the part-based representation issue during the dictionary learning step. Subsequently, we calculate the gain using NMF in sound event detection step. We evaluate and confirm that overlapping sound event detection performance of the proposed method is better than the conventional method that utilizes NMF based dictionary.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.1
• /
• pp.24-31
• /
• 2020

In this paper, the deep convolutional neural network for sound event detection is studied. Especially, the end-to-end neural network, which generates the detection results from the input audio waveform, is studied for weakly supervised problem that includes weakly-labeled and unlabeled dataset. The proposed system is based on the network structure that consists of deeply-stacked 1-dimensional convolutional neural networks, and enhanced by the skip connection and gating mechanism. Additionally, the proposed system is enhanced by the sound event detection and post processings, and the training step using the mean-teacher model is added to deal with the weakly supervised data. The proposed system was evaluated by the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 Task 4 dataset, and the result shows that the proposed system has F₁-scores of 54 % (segment-based) and 32 % (event-based).

• Asian-Australasian Journal of Animal Sciences
• /
• v.28 no.4
• /
• pp.592-598
• /
• 2015

Stress adversely affects the wellbeing of commercial chickens, and comes with an economic cost to the industry that cannot be ignored. In this paper, we first develop an inexpensive and non-invasive, automatic online-monitoring prototype that uses sound data to notify producers of a stressful situation in a commercial poultry facility. The proposed system is structured hierarchically with three binary-classifier support vector machines. First, it selects an optimal acoustic feature subset from the sound emitted by the laying hens. The detection and classification module detects the stress from changes in the sound and classifies it into subsidiary sound types, such as physical stress from changes in temperature, and mental stress from fear. Finally, an experimental evaluation was performed using real sound data from an audio-surveillance system. The accuracy in detecting stress approached 96.2%, and the classification model was validated, confirming that the average classification accuracy was 96.7%, and that its recall and precision measures were satisfactory.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.433-440
• /
• 2016

Railway point machines act as actuators that provide different routes to trains by driving switchblades from the current position to the opposite one. Since point failure can significantly affect railway operations with potentially disastrous consequences, early stress detection of point machine is critical for monitoring and managing the condition of rail infrastructure. In this paper, we propose a stress detection method for point machine in railway condition monitoring systems using sound data. The system enables extracting sound feature vector subset from audio data with reduced feature dimensions using feature subset selection, and employs support vector machines (SVMs) for early detection of stress anomalies. Experimental results show that the system enables cost-effective detection of stress using a low-cost microphone, with accuracy exceeding 98%.