• Speech Sciences
• /
• v.4 no.2
• /
• 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
• /
• v.15 no.4
• /
• 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.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.10
• /
• 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
• /
• v.22 no.2E
• /
• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.94-99
• /
• 1997

This paper describes a technique of probabilistic spectral subtraction which uses the knowledge of both noise and speech so as to reduce automatic speech recognition errors in noisy environments. Spectral subtraction method estimates a noise prototype in non-speech intervals and the spectrum of clean speech is obtained from the spectrum of noisy speech by subtracting this noise prototype. Thus noise can not be suppressed effectively using a single noise prototype in case the characteristics of the noise prototype are different from those of the noise contained in input noisy speech. To modify such a drawback, multiple noise prototypes are used in probabilistic subtraction method. In this paper, the probabilistic characteristics of noise and the knowledge of speech which is embedded in hidden Markov models trained in clean environments are used to suppress noise. Futhermore, dynamic feature parameters are considered as well as static feature parameters for effective noise suppression. The proposed method reduced error rates in the recognition of 50 Korean words. The recognition rate was 86.25% with the probabilistic subtraction, 72.75% without any noise suppression method and 80.25% with spectral subtraction at SNR(Signal-to-Noise Ratio) 10 dB.

• Journal of Ocean Engineering and Technology
• /
• v.25 no.2
• /
• 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.

• Journal of Biomedical Engineering Research
• /
• v.26 no.4
• /
• 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
• /
• v.22 no.2E
• /
• 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.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.4
• /
• pp.555-560
• /
• 2013

This paper first proposes a classification algorithm which detects a voiced, unvoiced, and silence signal using distance measure, logarithm power and root mean square methods at each frame, then a spectrum subtraction algorithm based on a subband filter. The proposed algorithm subtracts spectrums of white noise and street noise from noisy signal based on the subband filter at each frame. In this experiment, experimental results of the proposed spectrum subtraction algorithm demonstrate using the speech and noise data of Aurora-2 database. Based on measuring the speech-to-noise ratio (SNR), experiments confirm that the proposed algorithm is effective for the speech by contaminated the noise. From the experiments, the improvement in the output SNR values was approximately 2.1 dB and 1.91 dB better for white noise and street noise, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.3E
• /
• 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.