Performance results of noisy speech enhancement using undecimated wavelets and spectral peak enhancement

In communication medium to satisfy the speech enhancement process by using differents methodologies and algoirthms are the key term in testing the system design well enough to produce the best performance results for the speech system. The Wiener filter is one of the classical algorithm that applied to speech process to avoid the noise attacking the speech signal. In other word, compressive sensing method by randomize measurement matrix are combined with the Wiener filter to analyse the noisy speech signal with less introduce to noise signal and producing high signal to noise ratio. The PESQ is used to measure the quality of the proposed algorithm design. As in the experimental results shows that, attacking of defferent noise environments in speech signal still effectively improve the performance of noisy speech with maintain the high score of the PESQ quality.

Download Full-text

Robustness and Sensitivity Tuning of the Kalman Filter for Speech Enhancement

Signals ◽

10.3390/signals2030027 ◽

2021 ◽

Vol 2 (3) ◽

pp. 434-455

Author(s):

Sujan Kumar Roy ◽

Kuldip K. Paliwal

Keyword(s):

Kalman Filter ◽

Speech Enhancement ◽

Linear Prediction ◽

Real Life ◽

Model Parameters ◽

Noise Variance ◽

Noisy Speech ◽

Kalman Gain ◽

Whitening Filter ◽

Prediction Coefficient

Inaccurate estimates of the linear prediction coefficient (LPC) and noise variance introduce bias in Kalman filter (KF) gain and degrade speech enhancement performance. The existing methods propose a tuning of the biased Kalman gain, particularly in stationary noise conditions. This paper introduces a tuning of the KF gain for speech enhancement in real-life noise conditions. First, we estimate noise from each noisy speech frame using a speech presence probability (SPP) method to compute the noise variance. Then, we construct a whitening filter (with its coefficients computed from the estimated noise) to pre-whiten each noisy speech frame prior to computing the speech LPC parameters. We then construct the KF with the estimated parameters, where the robustness metric offsets the bias in KF gain during speech absence of noisy speech to that of the sensitivity metric during speech presence to achieve better noise reduction. The noise variance and the speech model parameters are adopted as a speech activity detector. The reduced-biased Kalman gain enables the KF to minimize the noise effect significantly, yielding the enhanced speech. Objective and subjective scores on the NOIZEUS corpus demonstrate that the enhanced speech produced by the proposed method exhibits higher quality and intelligibility than some benchmark methods.

Download Full-text

Weighted codebook mapping for noisy speech enhancement using harmonic-noise model

10.21437/interspeech.2006-70 ◽

2006 ◽

Author(s):

Esfandiar Zavarehei ◽

Saeed Vaseghi ◽

Qin Yan

Keyword(s):

Speech Enhancement ◽

Noise Model ◽

Noisy Speech ◽

Harmonic Noise

Download Full-text

Speech Enhancement Using Neuro-Fuzzy Classifier

Advances in Data Mining and Database Management - Handbook of Research on Automated Feature Engineering and Advanced Applications in Data Science ◽

10.4018/978-1-7998-6659-6.ch009 ◽

2021 ◽

pp. 164-181

Author(s):

Judith Justin ◽

Vanithamani R.

Keyword(s):

Feature Extraction ◽

Speech Enhancement ◽

The Other ◽

Objective Measures ◽

Noise Levels ◽

Fuzzy Classifier ◽

Noisy Speech ◽

Enhancement Technique ◽

Time Frequency ◽

Neuro Fuzzy

In this chapter, a speech enhancement technique is implemented using a neuro-fuzzy classifier. Noisy speech sentences from NOIZEUS and AURORA databases are taken for the study. Feature extraction is implemented through modifications in amplitude magnitude spectrograms. A four class neuro-fuzzy classifier splits the noisy speech samples into noise-only part, signal only part, more noise-less signal part, and more signal-less noise part of the time-frequency units. Appropriate weights are applied in the enhancement phase. The enhanced speech sentence is evaluated using objective measures. An analysis of the performance of the Neuro-Fuzzy 4 (NF 4) classifier is done. A comparison of the performance of the classifier with other conventional techniques is done for various noises at different noise levels. It is observed that the numerical values of the measures obtained are better when compared to the others. An overall comparison of the performance of the NF 4 classifier is done and it is inferred that NF4 outperforms the other techniques in speech enhancement.

Download Full-text

Application of the Generic Spectral Formula to Fetch-Limited Seas

Marine Technology Society Journal ◽

10.4031/mtsj.33.3.4 ◽

1999 ◽

Vol 33 (3) ◽

pp. 27-32 ◽

Cited By ~ 5

Author(s):

Michael E. McCormick

Keyword(s):

Probability Distribution ◽

Deep Water ◽

Spectral Peak ◽

Peak Enhancement ◽

Spectral Formula

A deep-water spectral formula, based on the Weibull probability distribution of wave periods, is modified to satisfy fetch-limited conditions for wind-generated seas Results of this generic spectral formula are compared with those obtained using the specific JONSWAP formula, in which the empirical parameters resulting from specific wind and fetch conditions are used. The comparisons are shown to be excellent for three of the five cases studied. For the last two cases, the generic formula is shown to be somewhat nonconservative near the spectral peak. In addition to the comparisons with the specific JONSWAP formula results, the generic formula results are compared with those obtained from the standard JONSWAP expression, where the Pierson-Moskowitz parametric values and averaged peak-enhancement values are used. Except for the greatest fetch length (37 km), the standard JONSWAP formula is shown to significantly under-predict the peak spectra values. The generic spectral formula is found to well-predict the spectra for fetch lengths of 11 km and greater.

Download Full-text

The Energy Distribution of Tire-Road Noise and Noisy Speech Based on Wavelet Packet

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.464.721 ◽

2011 ◽

Vol 464 ◽

pp. 721-724 ◽

Cited By ~ 1

Author(s):

Zhi Yong He ◽

Li Heng Luo

Keyword(s):

Energy Distribution ◽

Speech Enhancement ◽

Mobile Communications ◽

Wavelet Packet ◽

Noise Signal ◽

Wavelet Packets ◽

Road Noise ◽

Noisy Speech ◽

Time Frequency ◽

The Difference

Speech enhancement is very important for mobile communications or some other applications in car. The energy distribution of signal is the basis of algorithms which denoise noisy speech in time-frequency domain. In this work, the noise regarded is the tire-road noise when driving in expressway. Wavelet packets transform is used in the analysis. After decomposing noise signal and noisy speech signal by wavelet packet transform, the analysis for the difference of the energy distribution between noisy speech and noise is finished.

Download Full-text