辅助变量粒子滤波的声道共振特性轨迹跟踪

提出了一种基于辅助变量粒子滤波技术的连续语音声道共振特性(VTRs)轨迹跟踪方法。该方法基于描述语音信号特征的状态空间模型,采用粒子滤波技术跟踪VTRs的轨迹。语音模型由具有目标导向特性的动态方程和VTRs至倒谱系数(LPCC)的非线性映射构成。该方法有两个特点:首先,采用粒子滤波技术来处理语音模型的非线性问题;其次,在语音模型的状态方程中嵌入辅助变量用于标示VTRs在频域中的分布信息,并为粒子滤波过程中的粒子抽取提供目标导向。实验结果表明,该方法只需少量粒子即可正确跟踪连续语音的VTRs轨迹,而且可以在跟踪过程中避免虚假峰和合并峰的干扰。      

恒虚警率采样粒子滤波技术及其应用研究

粒子滤波是一种基于蒙特卡洛思想的非线性、非高斯滤波器,其一般采用重要性采样进行粒子采样。但重要性采样容易出现粒子退化现象。解决粒子样本退化问题一般采用重采样。重采样虽然解决了样本的退化问题,同时又引入了采样贫瘠问题。本文根据海洋混响的统计特性和混响中目标的恒虚警率检测原理,提出了恒虚警率采样粒子滤波技术,恒虚警率采样粒子滤波技术使采样粒子尽可能集中在目标附近,有效地描述目标后验概率,降低了粒子数,减小了计算量。本文将此技术应用到海洋混响中的声纳目标跟踪中,既解决了传统卡尔曼滤波在声纳目标跟踪中的非线性、非高斯问题,又解决了粒子滤波的粒子退化及采样贫瘠问题。文中对高分辨率声纳目标数据进行了滤波跟踪,结果验证了本文方法的有效性。     

Modified particle filter-based infrared pedestrian tracking

Tracking infrared pedestrian targets is a crucial part in video surveillance. Many factors make this problem decidedly non-linear and non-Gaussian, and the appropriate solution at present is based on the particle filter technique which is powerful and simple to implement. But in many cases, the traditional particle filter tracking algorithm fails to track the targets robustly and accurately. To solve these problems, a modified particle filter algorithm that combines intensity and edge cues is proposed. The algorithm firstly extracts the intensity cue and edge cue of the target based on the visual models which are originally learnt from the first frame and will be updated during the tracking process according to an automatic model updating strategy. Secondly, these two cues are combined into the particle filter framework by an adaptive integration scheme. Furthermore, its performance is evaluated with real-world infrared pedestrian sequences and extensive experimental results show that the presented method can track the infrared pedestrian more effectively and reliably than the traditional particle filter algorithm.     

Robust tracking of moving sound source using scaled unscented particle filter

Tracking an active sound source involves the modeling of non-linear non-Gaussian systems. To address this problem, this paper proposed scaled unscented particle filter (SUPF) algorithm for tracking moving sound source. The particle filter part of the SUPF provides the general probabilistic framework to handle non-linear non-Gaussian systems, and the scaled unscented Kalman filter (SUKF) part of the SUPF generates better proposal distributions by taking into account the most recent observation. Meanwhile, models used in SUPF algorithm were also explored for the sound source motion, observation and the likelihood of the sound source location in the light of the Langevin process. Compared with the conventional PF approach, the simulated results demonstrated that the SUPF algorithm had superior tracking performance.     

扩散噪声下协方差矩阵重构的语音分离与降噪

针对传统多通道语音分离算法在扩散噪声下性能下降的问题,提出了一种用于语音分离及降噪的空间协方差模型及参数估计方法.该方法将扩散噪声视为独立声源,利用由导向矢量重构的空间协方差矩阵建模目标声源的空间特性,并通过空间协方差分析方法估计用于语音分离的多通道维纳滤波器.同时,还提出了一种联合该方法的后置滤波器参数框架,为输出信...     

基于Stiefel流形的粒子滤波器研究

为了解决粒子滤波的粒子退化和粒子多样性丧失问题,提出了一种基于Stiefel流形的粒子滤波算法.该算法将系统模型置于Stiefel流形上,用朗之万分布描述过程转移概率分布,用矩阵正态分布表示似然函数分布,在流形分布上进行粒子采样.在计算加权粒子的均值时,将流形嵌入到欧氏空间中,先计算欧氏空间中的粒子均值,再将计算结果投影到嵌套流形上,这就排除了噪声统计特性对粒子权重方差的影响,得到了一种受系统状态模型限制较少的重要性概率密度函数通用选择方案.仿真时选取单变量非静态增长模型,仿真结果验证了该算法的实时性、鲁棒性,滤波精度和滤波效率均比无味粒子滤波算法更好.     

语音信号序列的Volterra预测模型

对给定的英语音素、单词和语句进行了采集并完成预处理. 分别应用互信息法和Cao 氏法确定了实际采集的语音信号序列的延迟时间和嵌入维数, 以完成语音序列的相空间重构. 通过计算实际采集的语音信号序列的最大Lyapunov指数, 完成了语音信号的混沌特性识别, 判定其具有混沌特性. 引入Volterra级数, 提出了一种具有显式结构的语音信号非线性预测模型. 为克服最小均方误差算法在Volterra模型系数更新时固有的缺点, 在最小二乘法基础上, 应用基于后验误差假设的可变收敛因子技术, 构建了一种基于Davidon-Fletcher-Powell算法的二阶Volterra 模型(DFPSOVF), 并将其应用于具有混沌特性的语音信号序列预测. 仿真结果表明: DFPSOVF非线性预测模型对于单帧和多帧语音信号均具有更好的预测精度, 优于线性预测模型, 并且能够很好地反映语音序列变化的趋势和规律, 完全可以满足语音预测的要求; 可以根据语音信号序列的嵌入维数选取预测模型的记忆长度. 所提出模型可以为语音信号重构和压缩编码开辟一条新途径, 以改善语音信号处理方法的复杂度和处理效果.     

Noise reduction of speech signals using time-varying and multi-band adaptive gain control for smart digital hearing protectors

In this paper, a single-channel speech enhancement algorithm based on non-linear and multi-band Adaptive Gain Control (AGC) is proposed. The algorithm requires neither Signal-to-Noise Ratio (SNR) nor noise parameters estimation. It reduces the background noise in the temporal domain rather than the spectral domain using a non-linear and automatically adjustable gain function for multi-band AGC. The gain function varies in time and is deduced from the temporal envelope of each frequency band to highly compress the frequency regions where noise is present and lightly compress the frequency regions where speech is present. Objective evaluation using the PESQ (Perceptual Evaluation of Speech Quality) metric shows that the proposed algorithm performs better than three benchmarks, namely: the spectral subtraction, the Wiener filter based on a priori SNR estimation and a band-pass modulation filtering algorithm. In addition, blind subjective tests show that the proposed algorithm introduces less musical noise compared to the benchmark algorithms and was preferred 78.8% of the time in terms of signal quality. The proposed algorithm is implemented in a miniature low power digital signal processor to validate its feasibility and complexity for smart hearing protection in noisy environments.     

A genetic resampling particle filter for freeway traffic-state estimation

On-line estimation of the state of traffic based on data sampled by electronic detectors is important for intelligent traffic management and control.Because a nonlinear feature exists in the traffic state,and because particle filters have good characteristics when it comes to solving the nonlinear problem,a genetic resampling particle filter is proposed to estimate the state of freeway traffic.In this paper,a freeway section of the northern third ring road in the city of Beijing in China is considered as the experimental object.By analysing the traffic-state characteristics of the freeway,the traffic is modeled based on the second-order validated macroscopic traffic flow model.In order to solve the particle degeneration issue in the performance of the particle filter,a genetic mechanism is introduced into the resampling process.The realization of a genetic particle filter for freeway traffic-state estimation is discussed in detail,and the filter estimation performance is validated and evaluated by the achieved experimental data.     

混合退火粒子滤波器

针对非线性、非高斯系统状态的在线估计问题，提出一种新的基于序贯重要性抽样的粒子滤波算法. 在滤波算法中，用状态参数分解和退火系数来产生重要性概率密度函数，此概率密度函数综合考虑了转移先验、似然、噪声的统计特性以及最新的观察数据，因此更接近于系统状态的后验概率. 理论分析与仿真实验表明该粒子滤波器的性能明显优于标准的粒子滤波器和扩展卡尔曼滤波器. 关键词： 非线性 非高斯 粒子滤波 序贯重要性抽样     

Particle filtering with path sampling and an application to a bimodal ocean current model

This paper introduces a recursive particle filtering algorithm designed to filter high dimensional systems with complicated non-linear and non-Gaussian effects. The method incorporates a parallel marginalization (PMMC) step in conjunction with the hybrid Monte Carlo (HMC) scheme to improve samples generated by standard particle filters. Parallel marginalization is an efficient Markov chain Monte Carlo (MCMC) strategy that uses lower dimensional approximate marginal distributions of the target distribution to accelerate equilibration. As a validation the algorithm is tested on a 2516 dimensional, bimodal, stochastic model motivated by the Kuroshio current that runs along the Japanese coast. The results of this test indicate that the method is an attractive alternative for problems that require the generality of a particle filter but have been inaccessible due to the limitations of standard particle filtering strategies.     

考虑帧间信息的语音带宽扩展

语音带宽扩展是为了提高语音质量,利用语音低频和高频之间的相关性重构语音高频的一种技术。高斯混合模型法是语音带宽技术中被广泛应用的一种方法,但是,该方法的映射函数是分段线性函数,且没有考虑语音前后帧的相关信息。因此,提出了一种基于条件受限玻尔兹曼机的方法。该方法利用条件受限玻尔兹曼机提取了语音信号的帧间信息,同时将语音低频、高频特征参数映射为高阶统计特性,深层发掘和模拟了语音低频和高频之间的非线性关系。客观和主观对比测试结果都表明,该方法性能优于传统的高斯混合模型方法。      

基于独立分量分析和粒子群算法的太阳能电池表面缺陷红外热成像检测

根据红外成像特性及太阳能电池电致发光原理,研究一种基于限制式独立分量分析(ICA)模型和粒子群优化(PSO)方法的太阳能电池组件表面缺陷检测方法。利用太阳能电池红外图像的结构特点,首先设计一种ICA滤波器,并使用具有多方向搜索特性的PSO算法来求解ICA的分离矩阵,求解中加入限制式,使图像正常区域经滤波后有一致的反应值并有效凸显缺陷区域。然后使用ICA滤波器对图像进行旋积运算,最后使用阈值分割得到检测结果。实验结果表明,提出的ICA滤波检测方法对太阳能电池组件表面缺陷检测效果显著,检测精度高,能很好地区分背景和缺陷。     

Dim moving target tracking algorithm based on particle discriminative sparse representation

The small dim moving target usually submerged in strong noise, and its motion observability is debased by numerous false alarms for low signal-to-noise ratio (SNR). A target tracking algorithm based on particle filter and discriminative sparse representation is proposed in this paper to cope with the uncertainty of dim moving target tracking. The weight of every particle is the crucial factor to ensuring the accuracy of dim target tracking for particle filter (PF) that can achieve excellent performance even under the situation of non-linear and non-Gaussian motion. In discriminative over-complete dictionary constructed according to image sequence, the target dictionary describes target signal and the background dictionary embeds background clutter. The difference between target particle and background particle is enhanced to a great extent, and the weight of every particle is then measured by means of the residual after reconstruction using the prescribed number of target atoms and their corresponding coefficients. The movement state of dim moving target is then estimated and finally tracked by these weighted particles. Meanwhile, the subspace of over-complete dictionary is updated online by the stochastic estimation algorithm. Some experiments are induced and the experimental results show the proposed algorithm could improve the performance of moving target tracking by enhancing the consistency between the posteriori probability distribution and the moving target state.     

自调整平滑区间粒子滤波平滑算法

针对非线性系统的状态估计问题, 提出了一种自调整平滑区间粒子滤波平滑算法. 该算法的显著特点是根据采样粒子观测值与系统状态观测值之间的偏差动态修正滤波平滑区间的长度, 有效抑制了传统的粒子滤波平滑算法中因区间长度固定可能造成粒子权重重新赋值带来误差增大的问题. 该算法的原理是依据粒子滤波器的工作机理, 把系统状态信息和热槽组成一个抽象的整体, 将粒子滤波平滑过程类比为观测信息和热槽交互的统计力学系统. 在无新的观测信息时, 整个系统遵循热力学第二定律, 即无论从任何初始状态出发, 整个力学系统的熵是非减的; 而当出现新的观测信息时, 粒子滤波器像麦克斯韦妖从新的观测信息中抽取能量传送给热槽, 使整个抽象系统的熵减少, 根据系统熵的递变规律变化对滤波平滑区间的长度加以动态修正, 优化粒子的权重赋值, 进而提高系统状态的估计精度. 利用matlab进行了仿真分析, 验证了该算法的有效性.     

基于多速率交互式多模型的快速光电跟踪算法

针对交互式多模型粒子滤波算法运算量大的问题,提出了一种基于多速率跟踪思想的交互式多模型算法.该算法根据各模型假定的机动性,采用不同的数据更新速率,实现了模式空间和测量空间的混合滤波.同时,多模型综合选配了不同的滤波算法,其中,弱机动模型匹配卡尔曼滤波器,强机动模型匹配粒子滤波器.仿真结果表明,与传统的交互式多模型粒子滤波算法相比,本文算法在保证滤波精度的基础上,具有较低的计算复杂度,降低了约38.9%,能够有效地改善光电目标跟踪系统的可靠性和实时性.     

Single-channel dereverberation using a non-causal minimum variance distortionless response filter

This letter presents a single-channel speech dereverberation approach using a non-causal minimum variance distortionless response (MVDR) filter. The non-causal filter is adopted to utilize the additional information of the desired signal that lies in subsequent frames. Note that the desired signal output has minimal distortion due to the introduction of the MVDR criterion. The proposed system further suppresses the late reverberation by employing a statistical reverberant model. Experimental results demonstrate the superiority of the proposed algorithm to conventional approaches.     

An adaptive speech enhancement method for siren noise cancellation

Siren noises usually severely disturb the intelligibility of voice communication inside the cabs of police, paramedic and fire vehicles. It is often desired that such unwanted noise can be removed from the speech signal. In this paper, a new method is proposed to adaptively cancel siren noises and enhance speech signals. Based on the characteristics of siren noises, an anti-speech filter and a time delayer are employed in the single and dual channel noise cancellation systems to reduce the siren noises. Experiment results demonstrate that the effectiveness of the proposed method for canceling the siren noises and the performance of the enhanced speech signal is satisfying.     

Analysis of voice source characteristics using a constrained polynomial representation of voice source signals

To analyze the characteristics of voice source signals from speech, a model is presented in the form of polynomial function by expanding the definition of the Rosenberg model. In combination with the all-pole assumption of the vocal-tract filter, methods are described for the pitch-synchronous speech analysis and temporal search of the glottal opening and closing instants. Because the source and filter models are both linear, the parameter estimation problem can be conveniently solved. In addition, the temporal search method can refine the locations of the glottal events and improve the accuracy of the parameter estimation. Analyses of non-nasalized voiced speech are conducted using an electroglottographic device from which the initial estimate of the temporal information is given.     

一种改进的DNN-HMM的语音识别方法*

针对深度神经网络与隐马尔可夫模型(DNN-HMM)结合的声学模型在语音识别过程中建模能力有限等问题,提出了一种改进的DNN-HMM模型语音识别算法。首先根据深度置信网络(DBN)结合深度玻尔兹曼机(DBM),建立深度神经网络声学模型,然后提取梅尔频率倒谱系数(MFCC)和对数域的Mel滤波器组系数(Fbank)作为声学特征参数,通过TIMIT语音数据集进行实验。实验结果表明:结合了DBM的DNN-HMM模型相比DNN-HMM模型更具优势,其中,使用MFCC声学特征在词错误率与句错误率方面分别下降了1.26%和0.20%。此外,使用默认滤波器组的Fbank特征在词错误率与句错误率方面分别下降了0.48%和0.82%,并且适量增加滤波器组可以降低错误率。总之,研究取得句错误率与词错误率分别降低到21.06%和3.12%的好成绩。