Improved Speech Enhancement Research Articles

An MMSE graph spectral magnitude estimator for speech signals residing on an undirected multiple graph

The paper uses the K-graphs learning method to construct weighted, connected, undirected multiple graphs, aiming to reveal intrinsic relationships of speech samples in the inter-frame and intra-frame. To benefit from the learned multiple graphs’ property and enhance interpretability, we study the spectral property of speech samples in the joint vertex-frequency domain by using the new graph weight matrix. Moreover, we propose the representation of minimum mean-square error (MMSE) graph spectral magnitude estimator for speech signals residing on undirected multiple graphs. We use the MMSE graph spectral magnitude estimator to improve speech enhancement performance. The numerical simulation results show that the proposed method outperforms the existing methods in graph signal processing (GSP) and the baseline methods for speech enhancement in discrete signal processing (DSP) in terms of PESQ, LLR, output SNR, and STOI results. These results also demonstrate the validity of the learned multiple graphs.

Adaptive Weiner filtering with AR-GWO based optimized fuzzy wavelet neural network for enhanced speech enhancement.

Speech signal enhancement is a subject of study in which a large number of researchers are working to improve the quality and perceptibility of speech signals. In the existing Kalman Filter method, the short-time magnitude or power spectrum due to random variations of noise was a serious problem and the signal-to-noise ratio was very low. This issue severely reduced the perceived qualityand intelligibility of enhanced speech. Thus, this paper intent to develop an improved speech enhancement model and it includes"training phase and testing phase". In the training phase, the input noise corrupted signal is initially fed as input to both STFT-based noise estimation and NMF-based spectrum estimation forestimating the noise spectrum and signal spectrum, respectively. The obtained noise spectrum and the signal spectrum are fed as input to the Wiener filter and these filtered signals are subjected to Empirical Mean Decomposition (EMD).Since, tuning factor η plays a key role in Wiener filter, it has to be determined for each signal and from the denoised signal the bark frequency is evaluated. The computed bark frequency is fed as input to the learning algorithm referred as Fuzzy Wavelet Neural Network (FW-NN)for detecting the suited tuning factor η for the entire input signal in Wiener filter.An Adaptive Randomized Grey Wolf Optimization (AR-GWO) is proposed for proper tuning of the tuning factor η referred as tuned tuning factor (η tuned ). The proposed AR-GWO is the improved version of standard Grey wolf optimization (GWO). In the testing phase, the training is accomplished initially and from which the tuning factor is gathered for each of the relevant input signal. Then, the properly tuned tuning factor (η tuned ) from FW-NN is fed as input to EMD via adaptive wiener filter for decomposing the spectral signal and the output of EMD is denoised enhanced speech signal. At last, the performance of the adopted approach is evaluated to the existing approaches in terms of various metrics. In particular, the computation time of the adopted AR-GWO model is 34.07%, 43.57%, 28.86%, 38.88%, and 16.03% better than the existing GA, ABC, PSO, FF, and GWO approaches respectively.

A MATLAB based improved Speech Enhancement and Recognition using Spectral Subraction Method,MFCC,GMM

A MATLAB based improved Speech Enhancement and Recognition using Spectral Subraction Method,MFCC,GMM

Improved Speech Enhancement Considering Speech PSD Uncertainty

Speech enhancement based on statistical models has been studied for several decades. Recently, the speech enhancement adopting a speech power spectral density (PSD) uncertainty model has been proposed. This approach distinguishes the true speech PSD from its estimate and considers both as random variables. It incorporates a prior distribution of speech spectra and speech PSD estimators to derive the PSD uncertainty-aware counterpart to conventional clean speech estimators, which results in performance improvement. However, the speech PSD uncertainty model has not yet been adopted for parameter estimations such as <inline-formula><tex-math notation="LaTeX"><?TeX $\mathit{a posteriori}$?></tex-math></inline-formula> speech presence probability, noise PSD, and speech power spectra estimations in the speech enhancement framework. In this paper, we incorporate the speech PSD uncertainty model to all the components of the statistical model-based speech enhancement framework by deriving PSD uncertainty-aware counterparts to conventional parameter estimators. Specifically, we derive the <inline-formula><tex-math notation="LaTeX"><?TeX $\mathit{a posteriori}$?></tex-math></inline-formula> speech presence probability (SPP) where the likelihood function for each hypothesis is based on the speech PSD uncertainty. With this <inline-formula><tex-math notation="LaTeX"><?TeX $\mathit{a posteriori}$?></tex-math></inline-formula> SPP, a novel SPP-based noise PSD estimator is derived. Also, we derive the minimum mean-square error (MMSE) estimator for the power spectrum of the clean speech in the current frame under speech PSD uncertainty which is exploited to refine the speech PSD estimator. Finally, the refined speech PSD estimator is incorporated into the spectral gain function based on the speech PSD uncertainty model. The proposed approach showed improved noise PSD estimation performance in terms of the averaged logarithmic error distance, and improved speech enhancement performance in terms of the noise reduction, segmental signal-to-noise ratio, perceptual evaluation of speech quality (PESQ) scores and short-time objective intelligibility in our experiments. It also exhibited comparable performance with a real-time deep learning-based speech enhancement system in terms of the PESQ scores and composite measures for the VoiceBank-DEMAND dataset.

A Class of Pareto Optimal Binaural Beamformers

The objective of binaural multi-microphone speech enhancement algorithms can be viewed as a multi-criteria design problem as there are several requirements to be met. The objective is not only to extract the target speaker without distortion, but also to suppress interfering sources (e.g., competing speakers) and ambient background noise, while preserving the auditory impression of the complete acoustic scene. Such a multi-objective problem (MOP) can be solved using a Pareto frontier, which provides a useful trade-off between the different criteria. In this paper, we propose a unified Pareto optimization framework, which is achieved by defining a generalized mean squared error (MSE) cost function, derived from a MOP. The solution to the multi-criteria problem is grounded on a solid mathematical foundation. The MSE cost function consists of a weighted sum of speech distortion (SD), partial interference reduction (IR), and partial noise reduction (NR) terms with scaling parameters that control the amount of IR and NR. The filter minimizing this generalized cost function, denoted Pareto optimal binaural multichannel Wiener filter (Pareto-BMWF), constitutes a generalization of various binaural MWF-based and binaural MVDR-based beamformers. This solution is optimal for any set of parameters. The improved speech enhancement capabilities are experimentally demonstrated using real-signal recordings when estimation errors are present and the binaural cue preservation capabilities are analyzed.

Sdgan: Improve Speech Enhancement Quality by Information Filter

The speech denoising model based on adversarial generative network has achieved better results than the traditional machine learning model. In this paper, for the short cut connection in the generator, we discuss its influence on the information transfer between encoder and decoder, and propose SDGAN at target. SDGAN sets linear and convolution filters in the short cut connection which adaptively learn the optimal information processing. The information filter still enables the generator to solve the gradient vanishing problem, and it can also avoid information redundancy and improve expression ability. In addition, SDGAN replaces the L1 regularization term in loss function with the L2 regularization term, which not only makes the output speech of the generator closer to the clean speech, but also avoids sparsity. In the experiments, SDGAN significantly performs better than other traditional GAN in five performance metrics (such as PESQ), and the effect of convolution filter is better than that of linear filter.

An improved MMSE estimator based modified group delay spectrum for Forensic Automatic Speaker Recognition

This paper presents an improved speech enhancement algorithm called Minimum Mean Square Error (MMSE), based on the MODified Group Delay spectrum (MODGD), for Forensic Automatic Speaker Recognition (FASR) under noisy environments. This algorithm uses the MODGD instead of the amplitude spectrum, to compute the power spectrum of the noise-corrupt signal. In the proposed estimator, the MODGD retains most of the formants information. Therefore, it enhances the noisy speech signal with high quality even at extremely low Signal-to-Noise Ratio (SNR) levels. The evaluation of the improved algorithm in simulated FASR scenarios was performed by adding different noise levels, extracted from the NOISEX-92 database to the clean NIST2000-traces. The results obtained show that the proposed MMSE–MODGD estimator provides greater suppression of noise components in regions of low SNR than the MMSE estimator. In addition, there is a drastic reduction in Equal Proportion Probability (EPP) (the improvements are 1.84% for babble noise and 1.25% for factory and white noises), combining FASR techniques with the proposed MMSE–MODGD estimator than with the conventional estimator.

Improving speech enhancement by focusing on smaller values using relative loss

The task of single-channel speech enhancement is to restore clean speech from noisy speech. Recently, speech enhancement has been greatly improved with the introduction of deep learning. Previous work proved that using ideal ratio mask or phase-sensitive mask as intermediation to recover clean speech can yield better performance. In this case, the mean square error is usually selected as the loss function. However, after conducting experiments, the authors find that the mean square error has a problem. It considers absolute error values, meaning that the gradients of the network depend on absolute differences between estimated values and true values, so the points in magnitude spectra with smaller values contribute little to the gradients. To solve this problem, they propose relative loss, which pays more attention to relative differences between magnitude spectra, rather than the absolute differences, and is more in accordance with human sensory characteristics. The perceptual evaluation of speech quality, the short-time objective intelligibility, the signal-to-distortion ratio, and the segmental signal-to-noise ratio are used to evaluate the performance of the relative loss. Experimental results show that it can greatly improve speech enhancement by focusing on smaller values.

Convolutional Neural Network-based Speech Enhancement for Cochlear Implant Recipients.

Attempts to develop speech enhancement algorithms with improved speech intelligibility for cochlear implant (CI) users have met with limited success. To improve speech enhancement methods for CI users, we propose to perform speech enhancement in a cochlear filter-bank feature space, a feature-set specifically designed for CI users based on CI auditory stimuli. We leverage a convolutional neural network (CNN) to extract both stationary and non-stationary components of environmental acoustics and speech. We propose three CNN architectures: (1) vanilla CNN that directly generates the enhanced signal; (2) spectral-subtraction-style CNN (SS-CNN) that first predicts noise and then generates the enhanced signal by subtracting noise from the noisy signal; (3) Wiener-style CNN (Wiener-CNN) that generates an optimal mask for suppressing noise. An important problem of the proposed networks is that they introduce considerable delays, which limits their real-time application for CI users. To address this, this study also considers causal variations of these networks. Our experiments show that the proposed networks (both causal and non-causal forms) achieve significant improvement over existing baseline systems. We also found that causal Wiener-CNN outperforms other networks, and leads to the best overall envelope coefficient measure (ECM). The proposed algorithms represent a viable option for implementation on the CCi-MOBILE research platform as a pre-processor for CI users in naturalistic environments.

Amended Adaptive Algorithm for Corpus Based Improved Speech Enhancement

Amended Adaptive Algorithm for Corpus Based Improved Speech Enhancement

A novel fast nonstationary noise tracking approach based on MMSE spectral power estimator

Estimating the noise power spectral density (PSD) from the corrupted speech signal is an essential component for speech enhancement algorithms. In this paper, a novel noise PSD estimation algorithm based on minimum mean-square error (MMSE) is proposed. The noise PSD estimate is obtained by recursively smoothing the MMSE estimation of the current noise spectral power. For the noise spectral power estimation, a spectral weighting function is derived, which depends on the a priori signal-to-noise ratio (SNR). Since the speech spectral power is highly important for the a priori SNR estimate, this paper proposes an MMSE spectral power estimator incorporating speech presence uncertainty (SPU) for speech spectral power estimate to improve the a priori SNR estimate. Moreover, a bias correction factor is derived for speech spectral power estimation bias. Then, the estimated speech spectral power is used in “decision-directed” (DD) estimator of the a priori SNR to achieve fast noise tracking. Compared to three state-of-the-art approaches, i.e., minimum statistics (MS), MMSE-based approach, and speech presence probability (SPP)-based approach, it is clear from experimental results that the proposed algorithm exhibits more excellent noise tracking capability under various nonstationary noise environments and SNR conditions. When employed in a speech enhancement system, improved speech enhancement performances in terms of segmental SNR improvements (SSNR+) and perceptual evaluation of speech quality (PESQ) can be observed.

Bone-Conduction Sensor Assisted Noise Estimation for Improved Speech Enhancement.

State-of-the-art noise power spectral density (PSD) estimation techniques for speech enhancement utilize the so-called speech presence probability (SPP). However, in highly non-stationary environments, SPP-based techniques could still suffer from inaccurate estimation, leading to significant amount of residual noise or speech distortion. In this paper, we propose to improve speech enhancement by deploying the bone-conduction (BC) sensor, which is known to be relatively insensitive to the environmental noise compared to the regular air-conduction (AC) microphone. A strategy is suggested to utilized the BC sensor characteristics for assisting the AC microphone in better SPP-based noise estimation. To our knowledge, no previous work has incorporated the BC sensor in this noise estimation aspect. Consequently, the proposed strategy can possibly be combined with other BC sensor assisted speech enhancement techniques. We show the feasibility and potential of the proposed method for improving the enhanced speech quality by both objective and subjective tests.

An improved speech enhancement algorithm for dual-channel mobile phones using wavelet and genetic algorithm

In this paper, a speech enhancement algorithm for dual-microphone mobile phones is improved. The proposed method is based on the exploitation of the coherence function and the quadrature mirror filter banks. This latter is designed by the genetic algorithm as criteria for noise reduction. Thus, the quadrature mirror filter banks are used as a mother wavelet in the speech enhancement algorithm. The adopted algorithm benefits of non-interfering signals statistics prediction. Hence, it can be applied with two closely microphones in small cellular mobile phones. Finally, referred to the objective measures and the time domain waveforms, the proposed method proves its effectiveness in term of speech quality and intelligibility compared with other algorithms when the speech is corrupted by different noise types.

New Generalized Sidelobe Canceller with Denoising Auto-Encoder for Improved Speech Enhancement

New Generalized Sidelobe Canceller with Denoising Auto-Encoder for Improved Speech Enhancement

Improved single channel phase‐aware speech enhancement technique for low signal‐to‐noise ratio signal

In the state-of-the-art single channel speech enhancement techniques, the short-time spectral amplitude is modified while the effect of the phase corruption due to the contamination of additive noise is neglected. This study introduces an improved speech enhancement algorithm based on a phase-aware multi-band spectral subtraction technique which estimates the spectral amplitude of the clean speech signal by considering the phase of the speech and noise signal components, and uses the estimated phase of the clean speech signal for signal reconstruction in the time domain. Experimental results show that the proposed algorithm yields better performance in terms of various objective and composite quality measures and other intelligibility assessment metrics while compared with other existing spectral subtraction methods. Using the composite objective measure quality evaluation technique, it is observed that the overall signal quality of the enhanced speech signal is improved on an average by 70% at 0 dB global input signal-to-noise ratio by using the proposed approach.

An Improved Speech Enhancement Algorithm Based on Wiener-Filtering

This paper proposes an improved speech enhancement algorithm based on Wiener-Filtering, which addresses the problems of speech distortion and musical noise. The proposed algorithm adopts the masking properties of human auditory system on calculating the gain of spectrum point, in order that the signal in the enhanced speech whose energy is lower than the threshold will not be decreased further and the less distortion will be brought to enhanced speech by the trade-off between the noise elimination and speech signal distortion. What’s more, in order to eliminate the “musical noise”, a spectrum-shaping technology using averaging method between adjacent frames is adopted. And to guarantee the real-time application, two-stage moving-average strategy is adopted. The computer simulation results show that the proposed algorithm is superior to the traditional Wiener method in the low CPU cost, real-time statistics, the reduction of the speech distortion and residual musical noise.

A Novel Expectation-Maximization Framework for Speech Enhancement in Non-Stationary Noise Environments

Voiced speeches have a quasi-periodic nature that allows them to be compactly represented in the cepstral domain. It is a distinctive feature compared with noises. Recently, the temporal cepstrum smoothing (TCS) algorithm was proposed and was shown to be effective for speech enhancement in non-stationary noise environments. However, the missing of an automatic parameter updating mechanism limits its adaptability to noisy speeches with abrupt changes in SNR across time frames or frequency components. In this paper, an improved speech enhancement algorithm based on a novel expectation-maximization (EM) framework is proposed. The new algorithm starts with the traditional TCS method which gives the initial guess of the periodogram of the clean speech. It is then applied to an <formula formulatype="inline" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex Notation="TeX">${L_1}$</tex> </formula> norm regularizer in the M-step of the EM framework to estimate the true power spectrum of the original speech. It in turn enables the estimation of the a-priori SNR and is used in the E-step, which is indeed a logmmse gain function, to refine the estimation of the clean speech periodogram. The M-step and E-step iterate alternately until converged. A notable improvement of the proposed algorithm over the traditional TCS method is its adaptability to the changes (even abrupt changes) in SNR of the noisy speech. Performance of the proposed algorithm is evaluated using standard measures based on a large set of speech and noise signals. Evaluation results show that a significant improvement is achieved compared to conventional approaches especially in non-stationary noise environment where most conventional algorithms fail to perform.

Improved Speech Enhancement Algorithm Based on Bark Bands Noise-Estimation for Non-Stationary Environment

The conventional spectrum subtraction algorithm cannot effectively suppress the noise under highly non-stationary environment and results in the remaining music noise is often heard in the enhanced speech. In order to improve the speech enhancement performance, a novel denoising algorithm is proposed, which is based on speech endpoint detection using spectrum variance and the dynamic spectrum subtraction in Bark bands. According to human auditory characteristics, the Bark bands spectrums of the noisy speech signal are firstly calculated, and the noise power spectrum of each Bark band is then tracked and estimated by the improved minima controlled recursive averaging method. This noise estimation is adjustable frame by frame and more accurate for non-stationary environment. The experiment results showed that the proposed method can suppress the noise more efficiently than the conventional spectrum subtraction and the remaining music noise is almost eliminated.

Joint Speech Enhancement and Speaker Identification Using Approximate Bayesian Inference

We present a variational Bayesian algorithm for joint speech enhancement and speaker identification that makes use of speaker dependent speech priors. Our work is built on the intuition that speaker dependent priors would work better than priors that attempt to capture global speech properties. We derive an iterative algorithm that exchanges information between the speech enhancement and speaker identification tasks. With cleaner speech we are able to make better identification decisions and with the speaker dependent priors we are able to improve speech enhancement performance. We present experimental results using the TIMIT data set which confirm the speech enhancement performance of the algorithm by measuring signal-to-noise (SNR) ratio improvement and perceptual quality improvement via the Perceptual Evaluation of Speech Quality (PESQ) score. We also demonstrate the ability of the algorithm to perform voice activity detection (VAD). The experimental results also demonstrate that speaker identification accuracy is improved.

An Improved Speech Enhancement Method based on Teager Energy Operator and Perceptual Wavelet Packet Decomposition

According to the distribution characteristic of noise and clean speech signal in the frequency domain, a new speech enhancement method based on teager energy operator (TEO) and perceptual wavelet packet decomposition (PWPD) is proposed. Firstly, a modified Mask construction method is made to protect the acoustic cues at the low frequencies. Then a level-dependent parameter is introduced to further adjust the thresholds in light of the noise distribution feature. At last the sub-bands which have very little influence are set directly 0 to improve the signal-to-noise ratio (SNR) and reduce the computation load. Simulation results show that, under different kinds of noise environments, this new method not only enhances the signal-to-noise ratio (SNR) and perceptual evaluation of speech quality (PESQ), but also reduces the computation load, which is very advantageous for real-time realizing.