脉冲噪声环境下基于卡尔曼滤波的语音增强

语音增强的目标在于从含噪信号中提取纯净语音,纯净语音在某些环境下会被脉冲噪声所污染,但脉冲噪声的时域分布特征却给语音增强带来困难,使传统方法在脉冲噪声环境下难以取得满意效果。为在平稳脉冲噪声环境下进行语音增强,提出了一种新方法。该方法通过计算确定脉冲噪声样本的能量与含噪信号样本的能量之比最大的频段,利用该频段能量分布情况逐帧判别语音信号是否被脉冲噪声所污染。进一步地,该方法只在被脉冲噪声污染的帧应用卡尔曼滤波算法去噪,并改进了传统算法执行时的自回归(AR)模型参数估计过程。实验中,采用白色脉冲噪声以及有色脉冲噪声污染语音信号,并对低输入信噪比的信号进行语音增强,结果表明所提出的算法能显著地改善信噪比和抑制脉冲噪声。     

基于增益字典查询的语音增强算法

对于基于统计模型的语音增强算法,不同分布模型对应于不同的增益函数,由于语音信号的不确定性,没有一种分布函数能准确对语音和噪声谱的分布建模,因此任何一种固定的统计模型均会存在一定的误差。所以提出一种增益字典查询的语音增强算法,该算法通过采用对数谱失真准则对一个语音噪声库进行增益的训练,得到一个增益的字典,其中输入为先验信噪比和后验信噪比的估计值。最后采用ITU-T P.826 PESQ、分段信噪比、总信噪比和对数谱失真对该算法进行了测试,并与基于高斯分布模型、拉普拉斯分布模型的算法进行了对比。实验结果表明,该算法无论在非平稳噪声还是平稳噪声环境下都比其他几种算法增强效果好,且音乐噪声和残留背景噪声也可以得到很好的抑制。     

Enhancement of noisy speech based on a custom thresholding function with a statistically determined threshold

Performance of the thresholding based speech enhancement methods largely depend on the estimate of the exact threshold value as well as on the choice of the thresholding function. In this paper, a speech enhancement method is presented, in which a custom thresholding function is proposed and employed upon the Wavelet Packet (WP) coefficients of the noisy speech. The thresholding function is capable of switching between modified hard and semisoft thresholding functions depending on a parameter that decides the signal characteristics under consideration. Here, the threshold is determined based on the statistical modeling of the Teager energy operated WP coefficients of the noisy speech. Extensive simulations indicate that the threshold thus obtained in conjunction with the custom thresholding function is very effective in reduction of not only the white noise but also the color noise from the noisy speech thus resulting in an enhanced speech with better quality and intelligibility. Several standard objective measures and subjective evaluations including informal listening tests show that the proposed method outperforms the recent state-of-the-art thresholding based approaches of noisy speech enhancement from high to low levels of SNR.     

一种基于EEMD域统计模型的话音激活检测算法

该文提出了一种基于EEMD域统计模型的话音激活检测算法。算法首先利用总体平均经验模态分解(Ensemble Empirical Mode Decomposition,EEMD)对带噪语音进行分解,得到信号的本征模式函数(Intrinsic Mode Function,IMF)分量,选择与原信号的相关性最高的两个分量相加组成主分量;然后对主分量进行频域分解,引入统计模型,求出EEMD域特征参数;最后利用噪声与语音的EEMD域特征参数的不同来进行语音激活检测。实验结果表明,在不同信噪比情况下,本文算法性能优于目前常用的 VAD算法,特别在噪声强度大时体现出明显的优势。     

基于ＥＥＭＤ域统计模型的话音激活检测算法

提出了一种基于EEMD域统计模型的话音激活检测算法。算法首先利用总体平均经验模态分解(Ensemble empirical mode decomposition,EEMD)对带噪语音进行分解,得到信号的本征模式函数(Intrinsicmode function,IMF)分量,选择与原信号的相关性最高的两个分量相加组成主分量;然后对主分量进行频域分解,引入统计模型,求出EEMD域特征参数;最后利用噪声与语音的EEMD域特征参数的不同来进行语音激活检测。实验结果表明,在不同信噪比情况下,本文算法性能优于目前常用的VAD算法,特别在噪声强度大时体现出明显的优势。     

Adaptive Time Segmentation for Improved Speech Enhancement

Single-channel enhancement algorithms are widely used to overcome the degradation of noisy speech signals. Speech enhancement gain functions are typically computed from two quantities, namely, an estimate of the noise power spectrum and of the noisy speech power spectrum. The variance of these power spectral estimates degrades the quality of the enhanced signal and smoothing techniques are, therefore, often used to decrease the variance. In this paper, we present a method to determine the noisy speech power spectrum based on an adaptive time segmentation. More specifically, the proposed algorithm determines for each noisy frame which of the surrounding frames should contribute to the corresponding noisy power spectral estimate. Further, we demonstrate the potential of our adaptive segmentation in both maximum likelihood and decision direction-based speech enhancement methods by making a better estimate of the a priori signal-to-noise ratio (SNR)$xi$. Objective and subjective experiments show that an adaptive time segmentation leads to significant performance improvements in comparison to the conventionally used fixed segmentations, particularly in transitional regions, where we observe local SNR improvements in the order of 5 dB.     

Estimators of The Magnitude-Squared Spectrum and Methods for Incorporating SNR Uncertainty

Statistical estimators of the magnitude-squared spectrum are derived based on the assumption that the magnitude-squared spectrum of the noisy speech signal can be computed as the sum of the (clean) signal and noise magnitude-squared spectra. Maximum a posterior (MAP) and minimum mean square error (MMSE) estimators are derived based on a Gaussian statistical model. The gain function of the MAP estimator was found to be identical to the gain function used in the ideal binary mask (IdBM) that is widely used in computational auditory scene analysis (CASA). As such, it was binary and assumed the value of 1 if the local SNR exceeded 0 dB, and assumed the value of 0 otherwise. By modeling the local instantaneous SNR as an F-distributed random variable, soft masking methods were derived incorporating SNR uncertainty. The soft masking method, in particular, which weighted the noisy magnitude-squared spectrum by the a priori probability that the local SNR exceeds 0 dB was shown to be identical to the Wiener gain function. Results indicated that the proposed estimators yielded significantly better speech quality than the conventional MMSE spectral power estimators, in terms of yielding lower residual noise and lower speech distortion.     

A perceptually motivated stationary wavelet packet filterbank using improved spectral over-subtraction for enhancement of speech in various noise environments

In this paper, we propose a speech enhancement method where the front-end decomposition of the input speech is performed by temporally processing using a filterbank. The proposed method incorporates a perceptually motivated stationary wavelet packet filterbank (PM-SWPFB) and an improved spectral over-subtraction (I-SOS) algorithm for the enhancement of speech in various noise environments. The stationary wavelet packet transform (SWPT) is a shift invariant transform. The PM-SWPFB is obtained by selecting the stationary wavelet packet tree in such a manner that it matches closely the non-linear resolution of the critical band structure of the psychoacoustic model. After the decomposition of the input speech, the I-SOS algorithm is applied in each subband, separately for the estimation of speech. The I-SOS uses a continuous noise estimation approach and estimate noise power from each subband without the need of explicit speech silence detection. The subband noise power is estimated and updated by adaptively smoothing the noisy signal power. The smoothing parameter in each subband is controlled by a function of the estimated signal-to-noise ratio (SNR). The performance of the proposed speech enhancement method is tested on speech signals degraded by various real-world noises. Using objective speech quality measures (SNR, segmental SNR (SegSNR), perceptual evaluation of speech quality (PESQ) score), and spectrograms with informal listening tests, we show that the proposed speech enhancement method outperforms than the spectral subtractive-type algorithms and improves quality and intelligibility of the enhanced speech.     

Speech Enhancement Using Gaussian Scale Mixture Models

This paper presents a novel probabilistic approach to speech enhancement. Instead of a deterministic logarithmic relationship, we assume a probabilistic relationship between the frequency coefficients and the log-spectra. The speech model in the log-spectral domain is a Gaussian mixture model (GMM). The frequency coefficients obey a zero-mean Gaussian whose covariance equals to the exponential of the log-spectra. This results in a Gaussian scale mixture model (GSMM) for the speech signal in the frequency domain, since the log-spectra can be regarded as scaling factors. The probabilistic relation between frequency coefficients and log-spectra allows these to be treated as two random variables, both to be estimated from the noisy signals. Expectation-maximization (EM) was used to train the GSMM and Bayesian inference was used to compute the posterior signal distribution. Because exact inference of this full probabilistic model is computationally intractable, we developed two approaches to enhance the efficiency: the Laplace method and a variational approximation. The proposed methods were applied to enhance speech corrupted by Gaussian noise and speech-shaped noise (SSN). For both approximations, signals reconstructed from the estimated frequency coefficients provided higher signal-to-noise ratio (SNR) and those reconstructed from the estimated log-spectra produced lower word recognition error rate because the log-spectra fit the inputs to the recognizer better. Our algorithms effectively reduced the SSN, which algorithms based on spectral analysis were not able to suppress.     

基于新阈值函数和自适应阈值的小波包语音增强研究

针对传统的小波包语音增强算法增强后的语音失真严重的问题,本文提出了一种基于自适应阈值和新阈值函数的小波包语音增强算法。该算法在小波包域将带噪语音加窗分帧,基于相邻帧快速傅立叶变换功率谱的互相关值,计算各帧存在语音的概率,然后通过语音存在概率对传统通用小波包阈值进行调整,使得阈值在非语音帧中较大,在语音帧中较小,实现阈值的自适应调整,可以在最大程度消除噪声的同时,尽可能的保留语音,减小语音失真。本文还设计了一种新阈值函数,克服了传统硬阈值函数不连续和软阈值函数会带来恒定偏差的缺点,进一步减小了语音失真。本文采用TIMIT 数据库和NOISEX-92 数据库中的语音和噪声进行了大量的模拟实验,主观评比和客观评比结果均证明本文提出的语音增强算法比现有的两种算法有更好的增强效果,采用本文算法增强后的语音失真更小,听觉效果更好。     

修正的基于广义Gamma语音模型语音增强算法

广义Gamma模型是近年来新提出的一种语音分布模型,相对于传统的高斯或超高斯模型具有更好的普适性和灵活性,提出一种基于广义Gamma语音模型和语音存在概率修正的语音增强算法。在假设语音和噪声的幅度谱系数分别服从广义Gamma分布和Gaussian分布的基础上,推导了语音信号对数谱的最小均方误差估计式;在该模型下进一步推导了语音存在概率,对最小均方误差估计进行修正。仿真结果表明,与传统的短时谱估计算法相比,该算法不仅能够进一步提高增强语音的信噪比,而且可以有效减小增强语音的失真度,提高增强语音的主观感知质量。     

基于先验信噪比估计和增益平滑的语音增强

针对语音增强算法残留“音乐噪声”的问题,分析了基于先验信噪比估计的语音增强算法,并在此基础上提出自适应先验信噪比估计与增益平滑相结合的方法.这种方法先对先验信嗓比进行估计,然后对增益函数进行平滑,减小相邻增益函数的随机跳变,弥补了传统先验信噪比估计的不足.最后对含高斯白噪声的语音信号进行处理,仿真结果表明,该算法在抑制“音乐噪声”的效果上得到一定改善,提高了语音增强的性能.     

Improved Subspace-Based Single-Channel Speech Enhancement Using Generalized Super-Gaussian Priors

Traditional single-channel subspace-based schemes for speech enhancement rely mostly on linear minimum mean-square error estimators, which are globally optimal only if the Karhunen-Loeacuteve transform (KLT) coefficients of the noise and speech processes are Gaussian distributed. We derive in this paper subspace-based nonlinear estimators assuming that the speech KLT coefficients are distributed according to a generalized super-Gaussian distribution which has as special cases the Laplacian and the two-sided Gamma distribution. As with the traditional linear estimators, the derived estimators are functions of the a priori signal-to-noise ratio (SNR) in the subspaces spanned by the KLT transform vectors. We propose a scheme for estimating these a priori SNRs, which is in fact a generalization of the "decision-directed" approach which is well-known from short-time Fourier transform (STFT)-based enhancement schemes. We show that the proposed a priori SNR estimation scheme leads to a significant reduction of the residual noise level, a conclusion which is confirmed in extensive objective speech quality evaluations as well as subjective tests. We also show that the derived estimators based on the super-Gaussian KLT coefficient distribution lead to improvements for different noise sources and levels as compared to when a Gaussian assumption is imposed     

子空间与维纳滤波相结合的语音增强方法

针对复杂背景噪声下语音增强后带有音乐噪声的问题,提出一种子空间与维纳滤波相结合的语音增强方法。对带噪语音进行KL变换,估计出纯净语音的特征值,再利用子空间域中的信噪比计算公式构成一个维纳滤波器,使该特征值通过这个滤波器,从而得到新的纯净语音特征值,由KL逆变换还原出纯净语音。仿真结果表明,在白噪声和火车噪声的背景下,信噪比都比传统子空间方法有明显提高,并有效抑制了增强后产生的音乐噪声。     

Noise Tracking Using DFT Domain Subspace Decompositions

All discrete Fourier transform (DFT) domain-based speech enhancement gain functions rely on knowledge of the noise power spectral density (PSD). Since the noise PSD is unknown in advance, estimation from the noisy speech signal is necessary. An overestimation of the noise PSD will lead to a loss in speech quality, while an underestimation will lead to an unnecessary high level of residual noise. We present a novel approach for noise tracking, which updates the noise PSD for each DFT coefficient in the presence of both speech and noise. This method is based on the eigenvalue decomposition of correlation matrices that are constructed from time series of noisy DFT coefficients. The presented method is very well capable of tracking gradually changing noise types. In comparison to state-of-the-art noise tracking algorithms the proposed method reduces the estimation error between the estimated and the true noise PSD. In combination with an enhancement system the proposed method improves the segmental SNR with several decibels for gradually changing noise types. Listening experiments show that the proposed system is preferred over the state-of-the-art noise tracking algorithm.     

Computational auditory models in predicting noise reduction performance for wideband telephony applications

The performance of several noise reduction algorithms intended for wideband telephony was evaluated both subjectively and objectively. The chosen algorithms were based on statistical modeling, spectral subtraction, Wiener filtering, or subspace modelling principles. A customized wideband noise reduction database containing speech samples corrupted by three types of background noises at three SNR levels, along with their enhanced versions was created. The overall quality of the speech samples in the database was subsequently rated by a group of listeners with normal hearing capabilities. Comprehensive statistical analyses were performed to assess the reliability of the subjective data, and to assess the performance of noise reduction algorithms across varied noisy conditions. The subjective quality ratings were then used to investigate the performance of several auditory model-based objective quality metrics. Key results from these investigations include: (a) there was a high degree of inter- and intra-subject reliability in the subjective ratings, (b) noise reduction algorithms enhance speech quality for only a subset of the noise conditions, and (c) auditory model-based metrics perform similarly in predicting speech quality ratings, when speech quality scores pertaining to a particular noise condition were averaged.     

改进相位谱补偿的语音增强方法

针对传统单通道语音增强方法中用带噪语音相位代替纯净语音相位重建时域信号，使得语音主观感知质量改善受限的情况，提出了一种改进相位谱补偿的语音增强算法。该算法提出了基于每帧语音输入信噪比的Sigmoid型相位谱补偿函数，能够根据噪声的变化来灵活地对带噪语音的相位谱进行补偿；结合改进DD的先验信噪比估计与语音存在概率算法（SPP）来估计噪声功率谱；在维纳滤波中结合新的语音存在概率噪声功率谱估计与相位谱补偿来提高语音的增强效果。相比传统相位谱补偿（PSC）算法而言，改进算法可以有效抑制音频信号中的各类噪声，同时增强语音信号感知质量，提升语音的可懂度。     

Reducing over- and under-estimation of the a priori SNR in speech enhancement techniques

Most speech enhancement methods based on short-time spectral modification are generally expressed as a spectral gain depending on the estimate of the local signal-to-noise ratio (SNR) on each frequency bin. Several studies have analyzed the performance of a priori SNR estimation algorithms to improve speech quality and to reduce speech distortions. In this paper, we concentrate on the analysis of over- and under estimation of the a priori SNR in speech enhancement and noise reduction systems. We first show that conventional approaches such as the decision-directed approach proposed by Ephraïm and Malah lead to a biased estimator for the a priori SNR. To reduce this bias, our strategy relies on the introduction of a correction term in the a priori SNR estimate depending on the current state of both the available a posteriori SNR and the estimated a priori one. The proposed solution leads to a bias-compensated a priori SNR estimate, and allows to finely estimating the output speech signal to be very close to the original one on each frequency bin. Such refinement procedure in the a priori SNR estimate can be inserted in any type of spectral gain function to improve the output speech quality. Objective tests under various environments in terms of the Normalized Covariance Metric (NCM) criterion, the Coherence Speech Intelligibility Index (CSII) criterion, the segmental SNR criterion and the Perceptual Evaluation of Speech Quality (PESQ) measure are presented showing the superiority of the proposed method compared to competitive algorithms.     

Environment-Optimized Speech Enhancement

In this paper, we present a training-based approach to speech enhancement that exploits the spectral statistical characteristics of clean speech and noise in a specific environment. In contrast to many state-of-the-art approaches, we do not model the probability density function (pdf) of the clean speech and the noise spectra. Instead, subband-individual weighting rules for noisy speech spectral amplitudes are separately trained for speech presence and speech absence from noise recordings in the environment of interest. Weighting rules for a variety of cost functions are given; they are parameterized and stored as a table look-up. The speech enhancement system simply works by computing the weighting rules from the table look-up indexed by the a posteriori signal-to-noise ratio (SNR) and the a priori SNR for each subband computed on a Bark scale. Optimized for an automotive environment, our approach outperforms known-environment-independent-speech enhancement techniques, namely the a priori SNR-driven Wiener filter and the minimum mean square error (MMSE) log-spectral amplitude estimator, both in terms of speech distortion and noise attenuation.     

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.