Bayesian marginal statistics for speech enhancement using log Gabor wavelet

This paper deals with single-channel speech enhancement technique. Initially, the suitability of Log Gabor Wavelet (LGW) is investigated in speech enhancement approach and a novel speech enhancer by Bayesian Maximum a Posteriori (MAP) based Marginal Statistical Characterization (MSC) is developed. The LGW filters are traditional choice for obtaining localized frequency information and these offer the best simultaneous localization of time and frequency information. The MSC is applied in each scale of the LGW, that means a level dependent shrinkage rule is taken to suppress the background perturbations. The pdf of the LGW filtered speech coefficient is modeled with Generalized Laplacian Distribution (GLD), which allows a high approximation accuracy for Laplace distributed real and imaginary parts of the speech coefficients. The robustness of the proposed framework is tested on NOIZEUS speech corpus against seven different established speech enhancement algorithms. Experimental results show that the proposed estimator yield a higher improvement in Segmental SNR (S-SNR), lower Log Area Ratio (LAR) and Weighted Spectral Slope (WSS) distortion compared to existing speech enhancement algorithms.     

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.     

一种新阈值函数的小波包语音增强算法

针对传统软、硬阈值函数去噪方法增强的语音存在失真的问题,提出一种新阈值函数的小波包语音增强算法,同时给出了新阈值函数和新的Bark尺度小波包分解结构。新阈值函数在小波包系数绝对值大于给定阈值的区间内,灵活地结合了软、硬阈值函数;在小波包系数绝对值小于给定阈值的区间内,用一种非线性函数代替传统阈值函数中的简单置零,实现了阈值函数的平缓过渡;新的60个频带Bark尺度小波包分解结构能更好地模拟人耳的听觉感知特性。仿真实验结果表明,在高斯白噪声和有色噪声背景下,与传统软、硬阈值函数去噪方法相比,新算法有效提高了增强语音信噪比和分段信噪比,减少了语音失真,具有更好的去噪效果。     

OM-LSA和小波阈值去噪结合的语音增强

针对OM-LSA(optimally modified log-spectral amplitude estimator)算法产生的残留噪声,提出了一种结合OM-LSA和小波阈值去噪的语音增强算法。首先,进行语音对数幅度谱估计;然后,估计残留噪声,利用带噪语音第一级小波系数和语音不存在时的增益函数进行估计,解决了常规方法对增强后语音噪声估计不准确的问题;最后,在小波域利用软阈值法对语音信号进行阈值处理。实验结果表明,提出的算法有效地去除了OM-LSA算法中的残余噪声,在分段信噪比(segmental signal-to-noise ratio,SegSNR)和对数谱失真(log-spectral distortion,LSD)等指标评价上有较大的提高。     

语音分离与HMM相结合的语音增强方法

针对基于隐马尔科夫（HMM,Hidden Markov Model）的MAP和MMSE两种语音增强算法计算量大且前者不能处理非平稳噪声的问题,借鉴语音分离方法,提出了一种语音分离与HMM相结合的语音增强算法。该算法采用适合处理非平稳噪声的多状态多混合单元HMM,对带噪语音在语音模型和噪声模型下的混合状态进行解码,结合语音分离方法中的最大模型理论进行语音估计,避免了迭代过程和计算量特别大的公式计算,减少了计算复杂度。实验表明,该算法能够有效地去除平稳噪声和非平稳噪声,且感知评价指标PESQ 的得分有明显提高,算法时间也得到有效控制。     

Improved A Posteriori Speech Presence Probability Estimation Based on a Likelihood Ratio With Fixed Priors

In this paper, we present an improved estimator for the speech presence probability at each time-frequency point in the short-time Fourier transform domain. In contrast to existing approaches, this estimator does not rely on an adaptively estimated and thus signal-dependent a priori signal-to-noise ratio estimate. It therefore decouples the estimation of the speech presence probability from the estimation of the clean speech spectral coefficients in a speech enhancement task. Using both a fixed a priori signal-to-noise ratio and a fixed prior probability of speech presence, the proposed a posteriori speech presence probability estimator achieves probabilities close to zero for speech absence and probabilities close to one for speech presence. While state-of-the-art speech presence probability estimators use adaptive prior probabilities and signal-to-noise ratio estimates, we argue that these quantities should reflect true a priori information that shall not depend on the observed signal. We present a detection theoretic framework for determining the fixed a priori signal-to-noise ratio. The proposed estimator is conceptually simple and yields a better tradeoff between speech distortion and noise leakage than state-of-the-art estimators.     

Wavelet-based image denoising with the normal inverse Gaussian prior and linear MMSE estimator

A new spatially adaptive wavelet-based method is introduced for reducing noise in images corrupted by additive white Gaussian noise. It is shown that a symmetric normal inverse Gaussian distribution is highly suitable for modelling the wavelet coefficients. In order to estimate the parameters of the distribution, a maximumlikelihood- based technique is proposed, wherein the Gauss?Hermite quadrature approximation is exploited to perform the maximisation in a computationally efficient way. A Bayesian minimum mean-squared error (MMSE) estimator is developed utilising the proposed distribution. The variances corresponding to the noisefree coefficients are obtained from the Bayesian estimates using a local neighbourhood. A modified linear MMSE estimator that incorporates both intra-scale and inter-scale dependencies is proposed. The performance of the proposed method is studied using typical noise-free images corrupted with simulated noise and compared with that of the other state-of-the-art methods. It is shown that the proposed method gives higher values of the peak signal-to-noise ratio compared with most of the other denoising techniques and provides images of good visual quality. Also, the performance of the proposed method is quite close to that of the state-of-the-art Gaussian scale mixture (GSM) method, but with much less complexity.     

Minimum Mean-Square Error Estimation of Discrete Fourier Coefficients With Generalized Gamma Priors

This paper considers techniques for single-channel speech enhancement based on the discrete Fourier transform (DFT). Specifically, we derive minimum mean-square error (MMSE) estimators of speech DFT coefficient magnitudes as well as of complex-valued DFT coefficients based on two classes of generalized gamma distributions, under an additive Gaussian noise assumption. The resulting generalized DFT magnitude estimator has as a special case the existing scheme based on a Rayleigh speech prior, while the complex DFT estimators generalize existing schemes based on Gaussian, Laplacian, and Gamma speech priors. Extensive simulation experiments with speech signals degraded by various additive noise sources verify that significant improvements are possible with the more recent estimators based on super-Gaussian priors. The increase in perceptual evaluation of speech quality (PESQ) over the noisy signals is about 0.5 points for street noise and about 1 point for white noise, nearly independent of input signal-to-noise ratio (SNR). The assumptions made for deriving the complex DFT estimators are less accurate than those for the magnitude estimators, leading to a higher maximum achievable speech quality with the magnitude estimators.     

Enhancement of speech signals separated from their convolutive mixture by FDICA algorithm

This paper presents a novel method for the enhancement of independent components of mixed speech signal segregated by the frequency domain independent component analysis (FDICA) algorithm. The enhancement algorithm proposed here is based on maximum a posteriori (MAP) estimation of the speech spectral components using generalized Gaussian distribution (GGD) function as the statistical model for the time–frequency series of speech (TFSS) signal. The proposed MAP estimator has been used and evaluated as the post-processing stage for the separation of convolutive mixture of speech signals by the fixed-point FDICA algorithm. It has been found that the combination of separation algorithm with the proposed enhancement algorithm provides better separation performance under both the reverberant and non-reverberant conditions.     

Speech enhancement based on undecimated wavelet packet-perceptual filterbanks and MMSE–STSA estimation in various noise environments

In this paper, we proposed a new speech enhancement system, which integrates a perceptual filterbank and minimum mean square error–short time spectral amplitude (MMSE–STSA) estimation, modified according to speech presence uncertainty. The perceptual filterbank was designed by adjusting undecimated wavelet packet decomposition (UWPD) tree, according to critical bands of psycho-acoustic model of human auditory system. The MMSE–STSA estimation (modified according to speech presence uncertainty) was used for estimation of speech in undecimated wavelet packet domain. The perceptual filterbank provides a good auditory representation (sufficient frequency resolution), good perceptual quality of speech and low computational load. The MMSE–STSA estimator is based on a priori SNR estimation. A priori SNR estimation, which is a key parameter in MMSE–STSA estimator, was performed by using “decision directed method.” The “decision directed method” provides a trade off between noise reduction and signal distortion when correctly tuned. The experiments were conducted for various noise types. The results of proposed method were compared with those of other popular methods, Wiener estimation and MMSE–log spectral amplitude (MMSE–LSA) estimation in frequency domain. To test the performance of the proposed speech enhancement system, three objective quality measurement tests (SNR, segSNR and Itakura–Saito distance (ISd)) were conducted for various noise types and SNRs. Experimental results and objective quality measurement test results proved the performance of proposed speech enhancement system. The proposed speech enhancement system provided sufficient noise reduction and good intelligibility and perceptual quality, without causing considerable signal distortion and musical background noise.     

联合优化深度神经网络和约束维纳滤波的单通道语音增强方法

深度神经网络（Deep neural networks,DNNs）依靠其良好的特征提取能力,在语音增强任务中得到了广泛应用。为进一步提高深度神经网络的语音增强效果,提出一种将深度神经网络和约束维纳滤波联合训练优化的新型网络结构。该网络首先对带噪语音幅度谱进行训练并分别得到纯净语音和噪声的幅度谱估计,然后利用语音和噪声的幅度谱估计计算得到一个约束维纳增益函数,最后利用约束维纳增益函数从带噪语音幅度谱中估计出增强语音幅度谱作为网络的训练输出。对不同信噪比下的20种噪声进行的仿真实验表明,无论噪声类型是否在网络的训练集中出现,本文方法都能够在有效去除噪声的同时保持较小的语音失真,增强效果明显优于DNN及NMF增强方法。     

基于声纹嵌入的语音增强算法

频域语音增强算法在高信噪比的条件下有明显的降噪效果,而在低信噪比条件下频域语音增强算法的性能会大幅下降。针对这个问题,将基于声纹的掩码应用到频域语音增强网络,利用声纹的先验信息,提升网络对说话人和噪声的区分度。另外,为了进一步改善频域语音算法在低信噪比条件下的性能,提出基于映射的声纹嵌入语音增强算法,避免了可能因采用掩模方案造成的语音失真问题。实验结果表明,在引入相同声纹信息时,基于映射的声纹嵌入语音增强网络在低信噪比条件下的增强性能表现更好,特别是在改善语音失真方面优势明显。相较于基于掩模的声纹掩码网络,基于映射的声纹嵌入网络在PESQ、STOI和SSNR这三项指标上分别实现了6.40%、1.46%和24.84%的相对提升。     

HMM-Based Gain Modeling for Enhancement of Speech in Noise

Accurate modeling and estimation of speech and noise gains facilitate good performance of speech enhancement methods using data-driven prior models. In this paper, we propose a hidden Markov model (HMM)-based speech enhancement method using explicit gain modeling. Through the introduction of stochastic gain variables, energy variation in both speech and noise is explicitly modeled in a unified framework. The speech gain models the energy variations of the speech phones, typically due to differences in pronunciation and/or different vocalizations of individual speakers. The noise gain helps to improve the tracking of the time-varying energy of nonstationary noise. The expectation-maximization (EM) algorithm is used to perform offline estimation of the time-invariant model parameters. The time-varying model parameters are estimated online using the recursive EM algorithm. The proposed gain modeling techniques are applied to a novel Bayesian speech estimator, and the performance of the proposed enhancement method is evaluated through objective and subjective tests. The experimental results confirm the advantage of explicit gain modeling, particularly for nonstationary noise sources     

基于TF-GSC的多通道后置滤波语音增强算法

针对传统语音增强算法在非平稳噪声,尤其是在噪声为语音的环境下,对噪声的抑制效果急剧下降的情况,提出了一种基于传递函数—广义旁瓣抵消(TF-GSC)和最佳修正测井谱振幅估计量(OM-LSA)的改进型多通道后置滤波语音增强算法.算法在后置滤波时,利用TF-GSC输出信号与参考噪声之间的相互关系求解出语音存在概率,并更新噪声功率谱估计.实验结果表明:算法可以有效地抑制非平稳噪声,提高语音增强算法在语音噪声环境下的鲁棒性.     

Speech enhancement based on stationary bionic wavelet transform and maximum a posterior estimator of magnitude-squared spectrum

Numerous efforts have focused on the problem of reducing the impact of noise on the performance of various speech systems such as speech coding, speech recognition and speaker recognition. These approaches consider alternative speech features, improved speech modeling, or alternative training for acoustic speech models. In this paper, we propose a new speech enhancement technique, which integrates a new proposed wavelet transform which we call stationary bionic wavelet transform (SBWT) and the maximum a posterior estimator of magnitude-squared spectrum (MSS-MAP). The SBWT is introduced in order to solve the problem of the perfect reconstruction associated with the bionic wavelet transform. The MSS-MAP estimation was used for estimation of speech in the SBWT domain. The experiments were conducted for various noise types and different speech signals. The results of the proposed technique were compared with those of other popular methods such as Wiener filtering and MSS-MAP estimation in frequency domain. To test the performance of the proposed speech enhancement system, four objective quality measurement tests [signal to noise ratio (SNR), segmental SNR, Itakura–Saito distance and perceptual evaluation of speech quality] were conducted for various noise types and SNRs. Experimental results and objective quality measurement test results proved the performance of the proposed speech enhancement technique. It provided sufficient noise reduction and good intelligibility and perceptual quality, without causing considerable signal distortion and musical background noise.     

Hybrid inter- and intra-wavelet scale image restoration

This paper exploits both the inter- and intra-scale interdependencies that exist in wavelet coefficients to improve image restoration from noise-corrupted data. Using an over-complete wavelet expansion, we group the wavelet coefficients with the same spatial orientation at several scales. We then apply the linear minimum mean squared-error estimation to smooth noise. This scheme exploits the inter-scale correlation information of wavelet coefficients. To exploit the intra-scale dependencies, we calculate the co-variance matrix of each vector locally using a centered square-shaped window. Experiments show that the proposed hybrid scheme significantly outperforms methods exploiting only the intra- or inter-scale dependencies. The performance of noise removal also depends on wavelet filters. In our experiments a biorthogonal wavelet, which best characterizes the image inter-scale dependencies, achieves the best results.     

Directionlet-based method using the Gaussian mixture prior to SAR image despeckling

In this article, a new denoising algorithm is proposed based on the directionlet transform and the maximum a posteriori (MAP) estimation. The detailed directionlet coefficients of the logarithmically transformed noise-free image are considered to be Gaussian mixture probability density functions (PDFs) with zero means, and the speckle noise in the directionlet domain is modelled as additive noise with a Gaussian distribution. Then, we develop a Bayesian MAP estimator using these assumed prior distributions. Because the estimator that is the solution of the MAP equation is a function of the parameters of the assumed mixture PDF models, the expectation-maximization (EM) algorithm is also utilized to estimate the parameters, including weight factors and variances. Finally, the noise-free SAR image is restored from the estimated coefficients yielded by the MAP estimator. Experimental results show that the directionlet-based MAP method can be successfully applied to images and real synthetic aperture radar images to denoise speckle.     

A wavelet- based transform method for quality improvement in noisy speech patterns of Arabic language

This paper addresses the problem of single-channel speech enhancement of low (negative) SNR of Arabic noisy speech signals. For this aim, a binary mask thresholding function based coiflet5 mother wavelet transform is proposed for Arabic speech enhancement. The effectiveness of binary mask thresholding function based coiflet5 mother wavelet transform is compared with Wiener method, spectral subtraction, log-MMSE, test-PSC and p-mmse in presence of babble, pink, white, f-16 and Volvo car interior noise. The noisy input speech signals are processed at various levels of input SNR range from ?5 to ?25 dB. Performance of the proposed method is evaluated with the help of PESQ, SNR and cepstral distance measure. The results obtained by proposed binary mask thresholding function based coiflet5 wavelet transform method are very encouraging and shows that the proposed method is much helpful in Arabic speech enhancement than other existing methods.     

Speech Enhancement Based on Generalized Minimum Mean Square Error Estimators and Masking Properties of the Auditory System

In this paper, the family of conditional minimum mean square error (MMSE) spectral estimators is studied which take on the form$(E(X_p^alpha/vert X_p+D_pvert))^1/alpha$, where$X_p$is the clean speech spectrum, and$D_p$is the noise spectrum, resulting in a Generalized MMSE estimator (GMMSE). The degree of noise suppression versus musical tone artifacts of these estimators is studied. The tradeoffs in selection of$(alpha)$, across noise spectral structure and signal-to-noise ratio (SNR) level, are also considered. Members of this family of estimators include the Ephraim–Malah (EM) amplitude estimator and, for high SNRs, the Wiener Filter. It is shown that the colorless residual noise observed in the EM estimator is a characteristic of this general family of estimators. An application of these estimators in an auditory enhancement scheme using the masking threshold of the human auditory system is formulated, resulting in the GMMSE-auditory masking threshold (AMT) enhancement method. Finally, a detailed evaluation of the proposed algorithms is performed over the phonetically balanced TIMIT database and the National Gallery of the Spoken Word (NGSW) audio archive using subjective and objective speech quality measures. Results show that the proposed GMMSE-AMT outperforms MMSE and log-MMSE enhancement methods using a detailed phoneme-based objective quality analysis.     

Speech Enhancement, Gain, and Noise Spectrum Adaptation Using Approximate Bayesian Estimation

This paper presents a new approximate Bayesian estimator for enhancing a noisy speech signal. The speech model is assumed to be a Gaussian mixture model (GMM) in the log-spectral domain. This is in contrast to most current models in frequency domain. Exact signal estimation is a computationally intractable problem. We derive three approximations to enhance the efficiency of signal estimation. The Gaussian approximation transforms the log-spectral domain GMM into the frequency domain using minimal Kullback-Leiber (KL)-divergency criterion. The frequency domain Laplace method computes the maximum a posteriori (MAP) estimator for the spectral amplitude. Correspondingly, the log-spectral domain Laplace method computes the MAP estimator for the log-spectral amplitude. Further, the gain and noise spectrum adaptation are implemented using the expectation-maximization (EM) algorithm within the GMM under Gaussian approximation. The proposed algorithms are evaluated by applying them to enhance the speeches corrupted by the speech-shaped noise (SSN). The experimental results demonstrate that the proposed algorithms offer improved signal-to-noise ratio, lower word recognition error rate, and less spectral distortion.