• 음성과학
• /
• 제4권2호
• /
• pp.5-15
• /
• 1998

This paper proposes a speech state-dependent spectral subtraction method to regulate the blind spectral subtraction for improved enhancement. In the proposed method, a modified subtraction rule is applied over the speech selectively contingent to the speech state being voiced or unvoiced, in an effort to incorporate the acoustic characteristics of phonemes. In particular, the objective of the proposed method is to remedy the subtraction induced signal distortion attained by two state-dependent procedures, spectrum sharpening and minimum spectral bound. In order to remove the residual noise, the proposed method employs a procedure utilizing the masking effect. Proposed spectral subtraction including state-dependent subtraction and residual noise reduction using the masking threshold shows effectiveness in compensation of spectral distortion in the unvoiced region and residual noise reduction.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.748-764
• /
• 2019

In order to deal with the filtering delay problem of least mean square adaptive filter noise reduction algorithm and music noise problem of spectral subtraction algorithm during the speech signal processing, we combine these two algorithms and propose one novel noise reduction method, showing a strong performance on par or even better than state of the art methods. We first use the least mean square algorithm to reduce the average intensity of noise, and then add spectral subtraction algorithm to reduce remaining noise again. Experiments prove that using the spectral subtraction again after the least mean square adaptive filter algorithm overcomes shortcomings which come from the former two algorithms. Also the novel method increases the signal-to-noise ratio of original speech data and improves the final noise reduction performance.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권10호
• /
• pp.606-610
• /
• 2003

Noise subtraction using reference channel data has been used to improve signal-to-noise ratio in magnetoencephalography. In this paper, an adaptive noise subtraction model is proposed and parameters for the model are optimized. A criterion to determine an optimal update period for the filter coefficients is proposed based on the ratio of peak amplitude of evoked field (N100m) divided by the output standard deviation. Experiments are carried out using a 40 channel MEG system. From the experiments, the proposed noise subtraction method shows superior performances over existing non-adaptive methods. Two-dimensional topographic map is shown for a diagnosis with a cubic spline interpolation.

• The Journal of the Acoustical Society of Korea
• /
• 제22권2E호
• /
• pp.87-92
• /
• 2003

In this paper, a new speech enhancement method using level adapted wavelet packet is presented. First, we propose a level adapted wavelet packet to alleviate a drawback of the conventional node adapted one in noisy environment. Next, we suggest an adaptive noise estimation method at each node on level adapted wavelet packet tree. Then, for more accurate noise component subtraction, we propose a new estimation method of spectral subtraction weight. Finally, we present a modified spectral subtraction method. The proposed method is evaluated on various noise conditions: speech babble noise, F-l6 cockpit noise, factory noise, pink noise, and Volvo car interior noise. For an objective evaluation, the SNR test was performed. Also, spectrogram test and a very simple listening test as a subjective evaluation were performed.

• 한국음향학회지
• /
• 제16권6호
• /
• pp.94-99
• /
• 1997

본 논문에서는 잡음환경에서의 음성인식을 위하여 잡음의 확률적 특성과 음성모델을 이용하는 확률적 스펙트럼 차감법을 제안한다. 기존의 스펙트럼 차감법은 음성이 존재하지 않는 구간에서 추정한 잡음을 잡음음성에서 차감하여 잡음을 제거함로, 추정한 잡음의 형태가 음성인식기에 입력되는 잡음음성에 포함된 잡음과 상이한 특성을 나타낼 경우에는 효과적인 잡음의 제거가 불가능하다. 이러한 단점을 보완하기 위해서 여러 가지 형태를 가지는 잡음의 원형을 사용하여, 잡음음성에서 잡음을 제거하는 방법을 사용하였다. 잡음의 확률적인 특성을 여러 개의 잡음원형으로 나타내므로, 스펙트럼 차감법은 입력음성에 대해서 확률적으로 수행되어 잡음이 제거된 다중의 스펙트럼을 출력하게 되고, 인식시에는 조용한 환경의 음성으로 학습된 음성모델에 따른 최적의 스펙트럼을 이용하여 인식을 수행한다. 또한 정적인 파라미터와 동적인 특징파라미터를 동시에 고려하여 잡음을 영향을 최소화하므로 보다 효과적인 잡음처리가 가능하다. 제안한 방법의 타당성을 실험적으로 검증하기 위해서, 잡음환경의 음성인식에 적용하였다. SNR 10 dB인 50개의 고립단어에 대한 실험결과, 잡음처리를 하지 않았을 경우 72.75%, 스펙트럼 차감법은 80.25%, 제안한 방법을 사용하였을 경우는 86.25%의 인식률을 얻음으로써, 효과적인 잡음처리 방법임을 확인할 수 있었다.

• 한국해양공학회지
• /
• 제25권2호
• /
• pp.1-6
• /
• 2011

Vibration-based Structural Health Monitoring (SHM) systems use field measurements of operational signals, which are distorted by noise from many sources. Reducing this noise allows a more accurate assessment of the original "clean" signal and improves analysis results. The implementation of a noise reduction methodology for the Modal Distribution Method (MDM) is reported here. The spectral subtraction method is a popular broadband noise reduction technique used in speech signal processing. Its basic principle is to subtract the magnitude of the noise from the total noisy signal in the frequency domain. The underlying assumption of the method is that noise is additive and uncorrelated with the signal. In speech signal processing, noise can be measured when there is no signal. In the MDM, however, the magnitude of the noise profile can be estimated only from the magnitude of the Power Spectral Density (PSD) at higher frequencies than the frequency range of the true signal associated with structural vibrations under the additional assumption of white noise. The implementation of the spectral subtraction method to MDM may decrease the energy of the individual mode. In this work, a modification of the spectral subtraction method is introduced that enables the conservation of the energies of individual modes. The main difference is that any (negative) bars with a height below zero after subtraction are set to the absolute value of their height. Both noise reduction methods are implemented in the MDM, and an application example is presented that demonstrates its effectiveness when used with a signal corrupted by noise.

• 대한의용생체공학회:의공학회지
• /
• 제26권4호
• /
• pp.199-205
• /
• 2005

When recording single-unit responses from neural systems, a common problem is the accurate detection of spikes (action potentials) in the presence of competing unwanted (noise) signals. While some sources of noise can be readily dealt with through filtering or 'template subtraction' techniques, other sources present a more difficult problem. In particular, noise components introduced by power supplies, which contain harmonics of the power-line frequency, can be particularly troublesome in that they can mimic the shape of the desired spikes. Thus, standard 'template subtraction' techniques or notch-filtering approaches are not appropriate. In this study, we propose the use of a novel template-subtraction scheme that involves estimating the power-line noise waveform and using cross-correlation techniques to subtract them from the recordings. This technique requires two key steps: (1) cross-correlation analysis of each recorded waveform extracts a robust representation of the power-line noise waveform and (2) a second level of cross-correlation to successfully subtract that representation from each recorded waveform. This paper describes this algorithm and provides examples of its implementation using actual recorded waveforms that are contaminated with these noise signals. An improvement (reduction) in the noise level is reported, as are suggestions for future implementation of this strategy.

• The Journal of the Acoustical Society of Korea
• /
• 제22권2E호
• /
• pp.62-68
• /
• 2003

This paper addresses a novel noise-compensation scheme to solve the mismatch problem between training and testing condition for the automatic speech recognition (ASR) system, specifically in car environment. The conventional spectral subtraction schemes rely on the signal-to-noise ratio (SNR) such that attenuation is imposed on that part of the spectrum that appears to have low SNR, and accentuation is made on that part of high SNR. However, these schemes are based on the postulation that the power spectrum of noise is in general at the lower level in magnitude than that of speech. Therefore, while such postulation is adequate for high SNR environment, it is grossly inadequate for low SNR scenarios such as that of car environment. This paper proposes an efficient spectral subtraction scheme focused specifically to low SNR noisy environment by extracting harmonics distinctively in speech spectrum. Representative experiments confirm the superior performance of the proposed method over conventional methods. The experiments are conducted using car noise-corrupted utterances of Aurora2 corpus.

• 한국전자통신학회논문지
• /
• 제8권4호
• /
• pp.555-560
• /
• 2013

본 논문에서는 거리측정, 로그전력, 실효치 방법에 의하여 유성음, 무성음, 묵음 구간을 검출하여, 서브밴드 필터에 의한 잡음제거 알고리즘을 제안한다. 제안한 알고리즘은 각 프레임에서 서브밴드 필터를 사용하여 잡음으로 오염된 음성신호로부터 백색잡음 및 도로잡음의 스펙트럼을 차감하는 방법이다. 본 실험에서는 Aurora-2 데이터베이스에 포함된 음성신호와 잡음신호를 사용하여 스펙트럼 차감 알고리즘의 결과를 나타낸다. 잡음에 의하여 오염된 음성신호에 대하여 신호대잡음비를 사용하여 본 알고리즘이 유효하다는 것을 확인한다. 실험으로부터 백색잡음에 대하여 평균 2.1 dB, 도로잡음에 대하여 평균 1.91 dB의 출력 신호대잡음비가 개선된 것을 확인할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• 제18권3E호
• /
• pp.3-8
• /
• 1999

In speech recognition for real-world applications, the performance degradation due to the mismatch introduced between training and testing environments should be overcome. In this paper, to reduce this mismatch, we provide a hybrid method of spectral subtraction and residual noise masking. We also employ multiple model approach to obtain improved robustness over various noise environments. In this approach, multiple model sets are made according to several noise masking levels and then a model set appropriate for the estimated noise level is selected automatically in recognition phase. According to speaker independent isolated word recognition experiments in car noise environments, the proposed method using model sets with only two masking levels reduced average word error rate by 60% in comparison with spectral subtraction method.