Variational Bayesian method for speech enhancement

In this paper, we propose to use variational Bayesian (VB) method to learn the clean speech signal from noisy observation directly. It models the probability distribution of clean signal using a Gaussian mixture model (GMM) and minimizes the misfit between the true probability distributions of hidden variables and model parameters and their approximate distributions. Experimental results demonstrate that the performance of the proposed algorithm is better than that of some other methods.     

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.     

谐波重构先验信噪比估计算法

先验信噪比单通道语音增强算法在信噪比较高时能有效地去除噪声,但在信噪比较低时语音高次谐波失真较为严重。针对此提出了一种基于谐波重构的先验信噪比估计算法,对增强后的信号加权求平方,进行功率谱的二次谱处理,以加强语音信号的周期性;再进行谐波重构,提升谐波分量。实验研究表明,该算法在低信噪比时能够有效地增强语音谐波分量,相对于先验信噪比估计的语音增强算法能够改善语音质量,减少语音失真。     

一种基于线性预测残差的语音增强算法

本文提出了一种基于线性预测残差的语音增强算法,以去除语音中的加性噪声。对不同噪声下语音信号的线性预测分析,不难发现线性预测系数携带有语音的频谱和共振峰信息。多次实验表明,在噪声位置预测系数较小,在语音位置预测系数相对较大,其平方和可以反映带噪语音信号的瞬时信噪比。本文将该平方和用在从维纳滤波导出的一个基于线性预测系数的去噪函数中,将该去噪函数结合B.Yegnanaraynana的提出的基于逆相对预测残差去噪的方法共同作用于线性预测残差信号,可得到增强的语音信号。实验表明这种方法可以得到较好的去噪语音,去噪的同时较好地保留了语音的可懂度,并且运算量较小。     

基于灰色多元线性回归融合模型的故障率预测

为预测在设备使用年份期间的制氧系统故障率,提出灰色多元线性回归融合模型的新方法。该方法首先求出制氧系统各设备故障率的GM(1,1)模型;然后计算出制氧系统故障率、制氧系统各设备故障率与设备使用年份相关关系模型,并且将制氧系统各设备故障率的GM(1,1)模型代入该关系模型中;最后利用最小二乘法求出待定参数。通过对制氧系统故障率的预测分析表明,灰色多元线性回归融合模型在故障率预测精度上优于单一的灰色模型和线性回归模型,且不要求提供的历史数据具有典型的分布规律。该模型的预测结果可为制氧系统的维修工作提供决策依据。     

Multiple statistical models for soft decision in noisy speech enhancement

Most speech enhancement algorithms are based on the assumption that speech and noise are both Gaussian in the discrete cosine transform (DCT) domain. For further enhancement of noisy speech in the DCT domain, we consider multiple statistical distributions (i.e., Gaussian, Laplacian and Gamma) as a set of candidates to model the noise and speech. We first use the goodness-of-fit (GOF) test in order to measure how far the assumed model deviate from the actual distribution for each DCT component of noisy speech. Our evaluations illustrate that the best candidate is assigned to each frequency bin depending on the Signal-to-Noise-Ratio (SNR) and the Power Spectral Flatness Measure (PSFM). In particular, since the PSFM exhibits a strong relation with the best statistical fit we employ a simple recursive estimation of the PSFM in the model selection. The proposed speech enhancement algorithm employs a soft estimate of the speech absence probability (SAP) separately for each frequency bin according to the selected distribution. Both objective and subjective tests are performed for the evaluation of the proposed algorithms on a large speech database, for various SNR values and types of background noise. Our evaluations show that the proposed soft decision scheme based on multiple statistical modeling or the PSFM provides further speech quality enhancement compared with recent methods through a number of subjective and objective tests.     

语音识别中声效模式的分析及检测

针对声效相关的语音识别鲁棒性问题,在分析了声效变化情况下声强、时长、帧能量分布以及频谱倾斜能方面特性的基础上,建立了基于GMM的声效检测器。同时,还研究了声效变化对语音识别精度的影响,并提出了基于多模型框架的语音识别算法。汉语孤立词语音识别实验显示,除正常模式的语音识别精度略有下降外,其它四种声效模式的识别精度均有大幅度的提高。实验结果表明语音信号的声强、时长、帧能量分布以及频谱倾斜等信息能够用于识别声效模式,而多模型框架是解决声效相关的语音识别鲁棒性问题的有效方法。     

麦克风阵列语音增强技术及其应用

本文简要叙述了应用麦克风阵列进行语音增强的原理及方法。且由于麦克风阵列在实际语音处理时具有良好的拾取语音能力及噪声鲁棒性,本文将介绍该技术在车载系统环境、机器人语音识别、大型场所的记录会议、助听装置及声源定位等系统中的应用。     

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.     

Efficient data selection for speech recognition based on prior confidence estimation using speech and monophone models

This paper proposes an efficient speech data selection technique that can identify those data that will be well recognized. Conventional confidence measure techniques can also identify well-recognized speech data. However, those techniques require a lot of computation time for speech recognition processing to estimate confidence scores. Speech data with low confidence should not go through the time-consuming recognition process since they will yield erroneous spoken documents that will eventually be rejected. The proposed technique can select the speech data that will be acceptable for speech recognition applications. It rapidly selects speech data with high prior confidence based on acoustic likelihood values and using only speech and monophone models. Experiments show that the proposed confidence estimation technique is over 50 times faster than the conventional posterior confidence measure while providing equivalent data selection performance for speech recognition and spoken document retrieval.     

Speaker identification based on the frame linear predictive coding spectrum technique

In this paper, a frame linear predictive coding spectrum (FLPCS) technique for speaker identification is presented. Traditionally, linear predictive coding (LPC) was applied in many speech recognition applications, nevertheless, the modification of LPC termed FLPCS is proposed in this study for speaker identification. The analysis procedure consists of feature extraction and voice classification. In the stage of feature extraction, the representative characteristics were extracted using the FLPCS technique. Through the approach, the size of the feature vector of a speaker can be reduced within an acceptable recognition rate. In the stage of classification, general regression neural network (GRNN) and Gaussian mixture model (GMM) were applied because of their rapid response and simplicity in implementation. In the experimental investigation, performances of different order FLPCS coefficients which were induced from the LPC spectrum were compared with one another. Further, the capability analysis on GRNN and GMM was also described. The experimental results showed GMM can achieve a better recognition rate with feature extraction using the FLPCS method. It is also suggested the GMM can complete training and identification in a very short time.     

基于子带无迹粒子滤波的语音增强算法

结合多采样率系统理论中的子带分解技术与贝叶斯估计理论中的无迹粒子滤波技术,提出了一种基于子带无迹粒子滤波的语音增强方法。该方法首先将语音信号分解成子带信号,建立各子带信号的低阶时变自回归模型;然后利用无迹粒子滤波估计模型参数,对子带信号进行滤波处理;最后根据滤波后的子带信号重构语音信号,实现语音增强。仿真结果表明,该方法能明显改善语音信号的信噪比和质量,且易于实现。     

基于多元线性回归模型的锂电池充电SOC预测

在诸多汽车电池中,锂电池因为性能稳定、寿命长、承受力强等优势,成为了电动汽车动力电池的绝佳选择。为了对锂电池进行高效管理,防止过充、过放的情况发生,保证锂电池使用的安全性以及性能,需要对锂电池的荷电状态（state of charge,SOC）进行准确预测。实验基于锂电池充电过程中的实际数据,使用Pyhton语言编程,建立多元线性回归模型,通过模型预测出锂电池开始充电到结束充电过程中准确的SOC值。研究结果表明,锂电池充电SOC的变化过程具有一定的线性规律,多元线性回归模型预测SOC值的误差都能控制得很小,决定系数都高于99%,具有很好的预测效果且有一定的通用性。除此之外,多元线性回归模型参数较少,结构简单,易于实现,更容易在实际应用中推广。     

Combining missing-feature theory, speech enhancement, and speaker-dependent/-independent modeling for speech separation

This paper considers the separation and recognition of overlapped speech sentences assuming single-channel observation. A system based on a combination of several different techniques is proposed. The system uses a missing-feature approach for improving crosstalk/noise robustness, a Wiener filter for speech enhancement, hidden Markov models for speech reconstruction, and speaker-dependent/-independent modeling for speaker and speech recognition. We develop the system on the Speech Separation Challenge database, involving a task of separating and recognizing two mixing sentences without assuming advanced knowledge about the identity of the speakers nor about the signal-to-noise ratio. The paper is an extended version of a previous conference paper submitted for the challenge.     

Neural network and multiple linear regression to predict school children dimensions for ergonomic school furniture design

The current study investigates the possibility of obtaining the anthropometric dimensions, critical to school furniture design, without measuring all of them. The study first selects some anthropometric dimensions that are easy to measure. Two methods are then used to check if these easy-to-measure dimensions can predict the dimensions critical to the furniture design. These methods are multiple linear regression and neural networks. Each dimension that is deemed necessary to ergonomically design school furniture is expressed as a function of some other measured anthropometric dimensions. Results show that out of the five dimensions needed for chair design, four can be related to other dimensions that can be measured while children are standing. Therefore, the method suggested here would definitely save time and effort and avoid the difficulty of dealing with students while measuring these dimensions. In general, it was found that neural networks perform better than multiple linear regression in the current study.     

微粒群算法在改进多元线性回归上的应用

文献[1]利用带约束的非线性规划,将各种改进的多元线性回归方法——主成分回归、岭回归、稳健回归及约束回归统一在一个非线性规划模型中。应用微粒群优化算法(ParticleSwarmOptimization,PSO)对其进行求解,实际算例表明,该方法不但可行,而且得出的结果比其它方法及文献[3]的结果与实际符合得更好。     

一种时间自适应阈值的小波包改进语音增强算法

针对传统小波语音增强算法存在过度周值处理的问题,提出一种改进的时间自适应阈值小波包去噪算法.该方法采用听觉感知小波包对噪声语音进行分解,得到小波包听觉感知节点上的系数,并基于语音存在概率估计按帧自动调节去噪周值,因改进的闲值能更好地避免语音小波包系数被过度阈值处理的情况,从而在抑制噪声的同时保留了更多的原始语音成分,进一步提高了降噪效果,实验结果表明,该算法比常规小波自适应闻值算法能得到更清晰的语音增强信号.     

Fuzzy nonparametric regression based on local linear smoothing technique

In a great deal of literature on fuzzy regression analysis, most of research has focused on some predefined parametric forms of fuzzy regression relationships, especially on the fuzzy linear regression models. In many practical situations, it may be unrealistic to predetermine a fuzzy parametric regression relationship. In this paper, a fuzzy nonparametric model with crisp input and LR fuzzy output is considered and, based on the distance measure for fuzzy numbers suggested by Diamond [P. Diamond, Fuzzy least squares, Information Sciences 46 (1988) 141-157], the local linear smoothing technique in statistics with the cross-validation procedure for selecting the optimal value of the smoothing parameter is fuzzified to fit this model. Some simulation experiments are conducted to examine the performance of the proposed method and three real-world datasets are analyzed to illustrate the application of the proposed method. The results demonstrate that the proposed method works quite well not only in producing satisfactory estimate of the fuzzy regression function, but also in reducing the boundary effect significantly.     

一种新的基于高斯混合模型的线性判别分析

Fisher准则函数的前提条件就是假设每类样本数据满足单峰高斯分布,即各类样本在模式空间的分布近似椭球状,但是当训练样本数据较多且呈多峰分布时,传统的Fisher准则函数并不能准确反映样本数据的分布,显然基于Fisher准则函数的线性判别分析得到的最优判别矢量集也不是最优的。针对这种情况,通过引入高斯混合模型的概念,提出了一种新的基于高斯混合模型的线性判别分析方法,同时也给出了在该模型下的最优判别矢量集的直接求解方法,并通过实验证明了该算法的有效性。