• 대한음성학회지:말소리
• /
• 제57호
• /
• pp.153-164
• /
• 2006

The MMSE-STSA based speech enhancement algorithm is widely used as a preprocessing for noise robust speech recognition. It weighs the gain of each spectral bin of the noisy speech using the estimate of noise and signal power spectrum. In this paper, we investigate the influence of parameters used to estimate the speech signal and noise power in MMSE-STSA upon the recognition performance of noisy speech. For experiments, we use the Aurora2 DB which contains noisy speech with subway, babble, car, and exhibition noises. The HTK-based continuous HMM system is constructed for recognition experiments. Experimental results are presented and discussed with our findings.

• The Journal of the Acoustical Society of Korea
• /
• 제18권2E호
• /
• pp.45-52
• /
• 1999

This paper presents the integrated speech enhancement system for hands-free mobile communication. The proposed integrated system incorporates both acoustic echo cancellation and engine noise reduction device to provide signal enhancement of desired speech signal from the echoed plus noisy environments. To implement the system, a delayless subband adaptive structure is used for acoustic echo cancellation operation. The NLMS based adaptive noise canceller then applied to the residual echo removed noisy signal to achieve the selective engine noise attenuation in dominant frequency component. Two sets of computer simulations are conducted to demonstrate the effectiveness of the system; one for the fixed acoustical environment condition, the other for the robustness of the system in which, more realistic situation, the acoustic transmission environment change. Simulation results confirm the system performance of 20-25dB ERLE in acoustic echo cancellation and 9-19 dB engine noise attenuation in dominant frequency component for both cases.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2000년도 하계종합학술대회논문집
• /
• pp.217-220
• /
• 2000

This paper describes the application of a neural network based adaptive line enhancer (ALE) for enhancement of the weak QRS complex corrupted with background noise. Modified fully-connected recurrent neural network is used as a nonlinear adaptive filter in the ALE. The connecting weights between network nodes as well as the parameters of the node activation function are updated at each iteration using the gradient descent algorithm. The real ECG signal buried with moderate and severe background noise is applied to the ALE. Simulation results show that the neural network based ALE performs well the enhancement of the QRS complex from noisy ECG signals.

• 융합신호처리학회논문지
• /
• 제14권1호
• /
• pp.6-12
• /
• 2013

맘모그램은 유방암의 조기발견을 위해 가장 일반적으로 이용되고 있다 유방암의 정확한 진단과 효율적인 치료를 위하여 많은 영상향상 방법들이 개발되어왔다. 본 논문은 디지털 유방 촬영상의 영상향상을 위하여 새로운 비선형 영상향상 방법을 제안한다. 제안된 방법은 영상의 밝기 정보를 향상시키기 위한 비선형 함수와 경계와 디테일 정보를 개선하기 위한 비선형 필터로 구성된다. 비선형 함수는 영상의 어두운 영역의 밝기를 향상시키고 밝은 영역의 동적범위를 넓혀주며, 비선형 필터는 영상의 특정 영역이나 객체를 효과적으로 개선시킨다. 최종 향상된 영상은 비선형 함수로 처리한 영상과 비선형 필터로 필터된 영상을 더하여 얻어진다. 제안된 비선형 영상향상 방법은 실험에서 기존 방법과 영상향상 결과를 비교하여 우수한 성능을 확인하였다.

• The Journal of the Acoustical Society of Korea
• /
• 제25권4E호
• /
• pp.142-147
• /
• 2006

Blind signal separation is known as a powerful tool for enhancing noisy speech in many real world environments. In this paper, it is demonstrated that the performance of blind signal separation can be further improved by combining with a null beamformer (NBF). Cascading the blind source separation with null beamforming is equivalent to the decomposition of the received signals into the direct parts and reverberant parts. Investigation of beam patterns of the null beamformer and blind signal separation reveals that directional null of NBF reduces mainly direct parts of the unwanted signals whereas blind signal separation reduces reverberant parts. Further, it is shown that the decomposition of received signals can be exploited to solve the local stability problem. Therefore, faster and improved separation can be obtained by removing the direct parts first by null beamforming. Simulation results using real office recordings confirm the expectation.

• 대한전자공학회논문지SP
• /
• 제49권4호
• /
• pp.32-39
• /
• 2012

본 논문에서는 DCT 영역에서 영상 신호의 방향과 변화의 크기에 따라 신호의 에너지를 조절하여 영상의 화질을 안정적으로 개선하는 방법을 개발한다. 이를 위하여 DCT 영역에서 영상 신호의 gradient를 측정하여 gradient의 방향과 크기로 영상의 sharpness, 국부 명암대비, 전역 명암대비에 해당하는 주파수 성분들의 에너지를 조절한다. 제안하는 기법은 기존의 기법들과 비교하여 블록화, 울림화 현상 발생과 잡음 증폭 없이 가장 우수한 화질로 향상시키는 것을 실험으로 보여준다.

• Journal of Electrical Engineering and Technology
• /
• 제8권3호
• /
• pp.638-648
• /
• 2013

Together with the GPS-based approach, geo-location through mobile communication networks is a key technology for location-based service. To save the cost, most geo-location system is implemented on the existed network service, which has a cellular structure. Still, multilateration is limited in cellular structure because it is difficult for the mobile terminal to acquire distance measurements from multiple base stations. This low hearability in the receiver is caused by co-channel interference and multipath environment. Therefore, hearability enhancement is necessary for multilateration under multipath and interference environment. Former time domain based hearability methods were designed for real signals. However, orthogonal frequency division multiplexing (OFDM) signal, which its usage has been increased in digital wireless communication, is a complex signal. Thus, different hearability enhancement method is needed for OFDM signals. This paper proposes a hearability enhancement method for forward-link multilateration using OFDM signals, which employ interference cancellation and multipath mitigation. A novel interference cancellation and multipath mitigation strategy for complex-valued OFDM signals is presented that has an iterative structure. Simulation results show that the proposed multilateration method provides the user's position with an accuracy of less than 80m through the mobile WiMAX cellular network in multipath environment.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2000년도 하계학술발표대회 논문집 제19권 1호
• /
• pp.337-338
• /
• 2000

The perceptual filter for speech enhancement was analytically derived where the frequency content of the input noisy signal was made the same as that of the estimated clean signal in auditory domain. However, the analytical derivation should rely on the deconvolution associated with the spreading function in the psychoacoustic model, which results in an ill-conditioned problem. In order to cope with the problem associated with the deconvolution, we propose a novel psychoacoustic model based speech enhancement filter whose principle is the same as the perceptual filter, however the filter is derived by a constrained optimization which provides solutions to the ill-conditioned problem.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1995년도 추계학술대회
• /
• pp.124-127
• /
• 1995

Due to the self-diffusion of nuclear spins, the edge of phantoms is enhanced in the magnetic resonance imaging (MRI), especially in the case of microscopy [1]. According to several published works, theory has been established that the edge enhancement is caused by the motion narrowing around bounded regions due to diffusions of nuclear spins during data acquisition. It is found, however, that the signal decreases due to the diffusion attenuation and image is distorted as edge of the image is sharpened. In this paper, we wilt investigate this signal loss during data acquisition and its effects on image, i.e., image edge enhancement due to the diffusion phenomenon. This result is new and different from the previously discussed edge enhancement due to the diffusion, namely, by motion narrowing effect or spin bouncing effect at the boundary.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.1098-1102
• /
• 1990

We consider a method for enhancement of speech signal degraded by additive random noise with time-variant and/or colored natures. For enhancement of speech signal with such noise, it is effective to utilize the natures of speech and noise. The objective of enhancement of speech is to improve the overall quality and the articulation of speech degraded by the time-variant and/or colored random noise. In the proposed method the distribution model of speech spectrum is given as information to noise reduction system. The proposed system can improve about lOdB in SNR when the input SNR is 0 dB.