• The Journal of the Acoustical Society of Korea
• /
• v.36 no.3
• /
• pp.179-185
• /
• 2017

The problem that occurred in the design/fabrication/testing of the wideband transmitting power amplifier for an embedded active SONAR (Sound Navigation and Ranging) system operating underwater was analyzed and the solution of the problem was proposed in this paper. Wideband acoustic SONAR systems had been developed in order to improve the underwater detection performance. The underwater acoustic transmission system had been also developed to achieve the wideband SONAR system. In this paper, the wideband acoustic transmission signal was generated using a 2 Level sawtooth type Class D PWM (Pulse Width Modulation) which was not complicated to implement. When the sonar signals having two or more frequencies were simultaneously generated, parasitic frequencies were added to the original signals by integer multiples of the frequency difference of the original signal. To cope with this problem, we proposed a way to remove the parasitic frequency from the source signal through modeling and simulation of the implemented power amplifier and PWM control hardware using MATLAB and Simulink.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.193-204
• /
• 2019

The explosion of data due to the improvement of sensor technology and computing performance has become the basis for analyzing the situation in the industrial fields, and various attempts to detect events based on such data are increasing recently. In particular, sound signals collected from sensors are used as important information to classify events in various application fields as an advantage of efficiently collecting field information at a relatively low cost. However, the performance of sound-event classification in the field cannot be guaranteed if noise can not be removed. That is, in order to implement a system that can be practically applied, robust performance should be guaranteed even in various noise conditions. In this study, we propose a system that can classify the sound event after generating the enhanced sound signal based on the deep learning algorithm. Especially, to remove noise from the sound signal itself, the enhanced sound data against the noise is generated using SEGAN applied to the GAN with a VAE technique. Then, an end-to-end based sound-event classification system is designed to classify the sound events using the enhanced sound signal as input data of CNN structure without a data conversion process. The performance of the proposed method was verified experimentally using sound data obtained from the industrial field, and the f1 score of 99.29% (railway industry) and 97.80% (livestock industry) was confirmed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1450-1451
• /
• 2013

본 논문에서는 음향 확성 환경과 음향신호의 입 출력 조건에 최적화된 음향 시스템을 실시간으로 생성 및 적용 가능한 음향 신호처리용 시스템으로서, 가변형 필터뱅크 기술 및 상황 적응적 필터 재조합 재배열 기술을 음향 신호처리용 DSP에 적용함으로서 Pro-Audio 장비, 방송 음향장비, 산업 음향장비와 같은 다양한 음향관련 장비에서 고품질 음향 서비스를 제공하기위한 핵심 기술인 가변형 필터뱅크 기반 고품질 음향 DSP 시스템 개발을 제안한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1993.06a
• /
• pp.80-83
• /
• 1993

본 논문에서는 양질의 규칙합성을 얻기 위하여, 유성음에 대한 여기신호로 임펄스 스펙트럼과 노이즈 스펙트럼을 다중대역으로 혼합하여 생성한 여기신호를 규칙합성에 적용하는 방법을 제안한다. 이 방법에서는, 분석합성에서 각 프레임별로 요구되었던 혼합여기신호에 대한 정보량 문제를 해결하기 위해 유성음의 정상부분의 한 프레임에 대해 혼합여기신호를 구하여 규칙합성에 적용하였고, 정보량을 더욱 줄이는 방안으로, 켑스트럼 유클리디안 거리를 이용하여 유성음을 분류하여, 각 그룹에 대한 대표 여기신호를 규칙합성의 여기신호로 사용하였다. 제안된 방법으로 음성을 합성한 결과 양질의 합성음을 얻을 수 있음을 확인하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.8
• /
• pp.25-33
• /
• 1998

본 논문에서는 한 쌍의 센서를 이용하여 미지의 수중 음향 신호의 시간지연의 차 (Time Delay Difference)를 추정하고 탐지하는 알고리즘을 다루고 있다. 전형적인 시간지연 차의 최적화 추정 기법은 두 신호의 상관관계(Cross Correlation)에 의한 ML(Maximum likelihood)추정으로 구할 수 있지만, 실제 수중 음향 환경 하에서 시간 지연뿐만 아니라 표 적의 이동에 의하여 발생하는 도플러 효과로 신호의 주파수도 변하게 된다. 이러한 신호 주 파수의 올바른 고려 없이 단순히 두 신호의 시간지연만을 추정하는 방법은 불가피한 에러를 생성하게 된다. 본 논문에서는 시시각각 변하는 시간지연의 차를 구하기 위한 준 최적화 기 법인 확률분포 함수의 Recursive Filter에 시간 지연 차와 도플러효과의 2차원 확률분포 함 수를 적용한 추정 알고리즘을 제안한다. 관측된 신호의 리샘플링(Resampling)을 통하여 도 플러 효과를 보상한 후 2차원 Conditional likelihood를 구하고 Projection과 Correction 과정 을 통하여 시간지연과 도플러 효과에 대한 사후확률을 구한다. 그리고 이러한 알고리즘을 가상 시나리오에 대한 모의실험을 통하여 평가한다.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.161-168
• /
• 2021

In this paper, a Silent Speech Interface (SSI) technology was proposed in which Doppler frequency shifts of the reflected signal were used to synthesize the speech signals when 40kHz ultrasonic signal was incident to speaker's mouth region. In SSI, the mapping rules from the features derived from non-speech signals to those from audible speech signals was constructed, the speech signals are synthesized from non-speech signals using the constructed mapping rules. The mapping rules were built by minimizing the overall errors between the estimated and true speech parameters in the conventional SSI methods. In the present study, the mapping rules were constructed so that the distribution of the estimated parameters is similar to that of the true parameters by using Generative Adversarial Networks (GAN). The experimental result using 60 Korean words showed that, both objectively and subjectively, the performance of the proposed method was superior to that of the conventional neural networks-based methods.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.6
• /
• pp.353-359
• /
• 2011

This paper proposes a vocal enhancement technique for improving the performance of vocal pitch detection in polyphonic music signal. The proposed vocal enhancement technique predicts an accompaniment signal from the input signal and generates an accompaniment replica signal according to the vocal power. Then, it removes the accompaniment replica signal from the input signal, resulting in a vocal-enhanced signal. The performance of the proposed method was measured by applying the same vocal pitch extraction method to the original and the vocal-enhanced signal, and the vocal pitch detection accuracy was increased by 7.1 % point in average.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.357-363
• /
• 2023

In underwater signal processing, separating individual signals from mixed signals has long been a challenge due to low signal quality. The common method using Short-time Fourier transform for spectrogram analysis has faced criticism for its complex parameter optimization and loss of phase data. We propose a Triple-path Recurrent Neural Network, based on the Dual-path Recurrent Neural Network's success in long time series signal processing, to handle three-dimensional tensors from multi-channel sensor input signals. By dividing input signals into short chunks and creating a 3D tensor, the method accounts for relationships within and between chunks and channels, enabling local and global feature learning. The proposed technique demonstrates improved Root Mean Square Error and Scale Invariant Signal to Noise Ratio compared to the existing method.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.670-677
• /
• 2019

As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.194-196
• /
• 2018

본 논문은 가상현실 음향 구현을 위한 심층신경망 기반 사운드 보간 방법에 관한 것으로서, 이를 통해 두 지점에서 취득한 음향 신호들을 사용하여 두 지점 사이의 음향을 생성한다. 산술평균이나 기하평균 같은 통계적 방법으로 사운드 보간을 수행할 수 있지만 이는 실제 비선형 음향 특성을 반영하기에 미흡하다. 이러한 문제를 해결하기 위해서 본 연구에서는 두 지점들과 목표 지점의 음향신호를 기반으로 심층신경망을 훈련하여 사운드 보간을 시도하였으며, 실험결과 통계적 방법에 비해 심층신경망 기반 사운드 보간 방법의 성능이 우수함을 보였다.