• 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.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.20-27
• /
• 2020

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). In this paper, we proposed a deep learning model that integrates Convolution Neural Network (CNN) with Non-Negative Matrix Factorization (NMF). To improve the separation quality of the NMF, it includes noise update technique that learns and adapts the characteristics of the current noise in real time. The noise update technique analyzes the sparsity and activity of the noise bias at the present time and decides the update training based on the noise candidate group obtained every frame in the previous noise reduction stage. Noise bias ranks selected as candidates for update training are updated in real time with discrimination NMF training. This NMF was applied to CNN and Hidden Markov Model(HMM) to achieve improvement for performance of sound event detection. Since CNN has a more obvious performance improvement effect, it can be widely used in sound source based CNN algorithm.

• ETRI Journal
• /
• v.31 no.4
• /
• pp.451-453
• /
• 2009

This letter proposes the use of vowel sound detection for voice activity detection. Vowels have distinctive spectral peaks. These are likely to remain higher than their surroundings even after severe corruption. Therefore, by developing a method of detecting the spectral peaks of vowel sounds in corrupted signals, voice activity can be detected as well even in low signal-to-noise ratio (SNR) conditions. Experimental results indicate that the proposed algorithm performs reliably under various noise and low SNR conditions. This method is suitable for mobile environments where the characteristics of noise may not be known in advance.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.1
• /
• pp.61-69
• /
• 2007

In this paper, we developed not only a reliable sound localization system including a VAD(Voice Activity Detection) component using three microphones but also a face tracking system using a vision camera. Moreover, we proposed a way to integrate three systems in the human-robot interaction to compensate errors in the localization of a speaker and to reject unnecessary speech or noise signals entering from undesired directions effectively. For the purpose of verifying our system's performances, we installed the proposed audio-visual system in a prototype robot, called IROBAA(Intelligent ROBot for Active Audition), and demonstrated how to integrate the audio-visual system.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.2
• /
• pp.121-128
• /
• 2008

Accurate voice activity detection have a great impact on performance of speech applications including speech recognition, speech coding, and speech communication. In this paper, we propose methods for voice activity detection that can adapt to various car noise situations during driving. Existing voice activity detection used various method such as time energy, frequency energy, zero crossing rate, and spectral entropy that have a weak point of rapid. decline performance in noisy environments. In this paper, the approach is based on existing spectral entropy for VAD that we propose voice activity detection method using MFB(Met-frequency filter banks) spectral entropy, gradient FFT(Fast Fourier Transform) spectral entropy. and gradient MFB spectral entropy. FFT multiplied by Mel-scale is MFB and Mel-scale is non linear scale when human sound perception reflects characteristic of speech. Proposed MFB spectral entropy method clearly improve the ability to discriminate between speech and non-speech for various in noisy car environments that achieves 93.21% accuracy as a result of experiments. Compared to the spectral entropy method, the proposed voice activity detection gives an average improvement in the correct detection rate of more than 3.2%.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.373-377
• /
• 2017

This paper presents a voice-activity detection (VAD) method for sound sequences with various SNRs. For real-time VAD applications, it is inadequate to employ a post-processing for the removal of burst clippings from the VAD output decision. To tackle this problem, building on the bi-level hidden Markov model, for which a state layer is inserted into a typical hidden Markov model (HMM), we formulated a robust method for VAD not requiring any additional post-processing. In the method, a forward-inference-ratio test was devised to detect the speech endpoints and Mel-frequency cepstral coefficients (MFCC) were used as the features. Our experiment results show that, regarding different SNRs, the performance of the proposed approach is more outstanding than those of the conventional methods.

• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.147-156
• /
• 2023

Efforts to employ smart home sensors to monitor the indoor activities of elderly single residents have been made to assess the feasibility of a safe and healthy lifestyle. However, the bathroom remains an area of blind spot. In this study, we have developed and evaluated a new edge computer device that can automatically detect water usage activities in the bathroom and record the activity log on a cloud server. Three kinds of sound as flushing, showering, and washing using wash basin generated during water usage were recorded and cut into 1-second scenes. These sound clips were then converted into a 2-dimensional image using MEL-spectrogram. Sound data augmentation techniques were adopted to obtain better learning effect from smaller number of data sets. These techniques, some of which are applied in time domain and others in frequency domain, increased the number of training data set by 30 times. A deep learning model, called CRNN, combining Convolutional Neural Network and Recurrent Neural Network was employed. The edge device was implemented using Raspberry Pi 4 and was equipped with a condenser microphone and amplifier to run the pre-trained model in real-time. The detected activities were recorded as text-based activity logs on a Firebase server. Performance was evaluated in two bathrooms for the three water usage activities, resulting in an accuracy of 96.1% and 88.2%, and F1 Score of 96.1% and 87.8%, respectively. Most of the classification errors were observed in the water sound from washing. In conclusion, this system demonstrates the potential for use in recording the activities as a lifelog of elderly single residents to a cloud server over the long-term.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.5
• /
• pp.345-352
• /
• 2017

We propose a methods which is reducing direction estimation error of sound source in the reverberant and noisy environments. The proposed algorithm divides speech signal into voice and unvoice using VAD. We estimate the direction of source when current frame is voiced. TDOA (Time-Difference of Arrival) between microphone array using the GCC-PHAT (Generalized Cross Correlation with Phase Transform) method will be estimated in that frame. Then, we compare the peak value of cross-correlation of two signals applied to estimated time-delay with other time-delay in time-table in order to improve the accuracy of source location. If the angle of current frame is far different from before and after frame in successive voiced frame, the angle of current frame is replaced with mean value of the estimated angle in before and after frames.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.39-40
• /
• 2007

For efficient interaction between human and robots, speech interface is a core problem especially in noisy and reverberant conditions. This paper analyzes main issues of spoken language interface for humanoid robots, such as sound source localization, voice activity detection, and speaker recognition.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.872-876
• /
• 2005

We propose a real-time post processing of nonlinear amplified signal to improve voice recognition in remote talk. In the previous research, we have found the nonlinear amplification has unique advantage for both the voice activity detection and the sound localization in remote talk. However, the original signal becomes distorted due to its nonlinear amplification and, as a result, the rest of sequence such as speech recognition show less satisfactorily results. To remedy this problem, we implement a linearization algorithm to recover the voice signal's linear characteristics after the localization has been done.