基于二次相关的语音信号时延估计改进算法

目前语音信号的时延估计研究,大部分采用的是广义互相关算法。然而,广义互相关时延估计算法易受噪声和混响环境影响。为此,本文提出了一种基于二次相关的语音信号时延估计改进算法,该算法对语音信号进行二次互相关运算,并结合Hilbert变换,对二次互相关峰值进行进一步的锐化处理,使得反映时延的峰值点检测更为准确。实验结果表明,改进的时延估计方法在非平稳的语音信号中能够有效地抑制噪声干扰,且在不同混响条件下时延估计具有更好的性能。     

复杂噪声环境中的语音端点检测

提出了一种适用于复杂加性噪声环境的语音端点检测方法。通过对噪声类型的归纳,建立自适应的平稳噪声模型,并根据模型搜索信号能量非平稳的区域。然后基于浊音在频域上的谐波结构,在此区域内检测浊音,从而排除非平稳噪声的干扰。最后根据信号能量精确搜索语音起止点。与目前典型端点检测算法的对比实验表明,在大多数复杂噪声环境下,该算法具有较好的准确率。     

基于双向搜索方法的最小值控制递归平均语音增强算法

语音增强效果的提高,有赖于对噪声的准确估计和对噪声变化的及时跟踪与更新。为了提高对非平稳噪声的估计和更新能力,本文基于"改进的最小值控制递归平均"（IMCRA）算法,提出了噪声谱最小值双向搜索的改进算法。该算法结合前向搜索和后向搜索谱最小值方法的特点,有效提高噪声估计的准确性、减小非平稳噪声跟踪的延迟。实验仿真表明:在非平稳噪声环境和低信噪比条件的语音信号增强处理中,本文提出的改进算法非常有效,与IMCRA算法相比,它可以获得更好的分段信噪比的提高。      

改进谐波组织规则的单通道浊语音分离系统

针对以往单通道噪声和浊语音分离算法的不足,改进了谐波组织算法。算法利用载波包络能量比将时频单元分为确定和非确定。提取基频作为组织线索。组织阶段分别使用谐波原理和最小幅度原理对确定时频单元组织;使用改进包络自相关函数度量幅度调制率对非确定时频单元组织。对比以往算法的处理结果,改进算法平均信噪比(SNR)提高0.96 dB。通过对谐波组织规则的改进,提高了分离性能。     

改进的自适应衰减卡尔曼滤波算法

SINS/GPS组合导航系统的融合算法主要是卡尔曼滤波,卡尔曼滤波实现最优估计的前提是系统的模型和随机噪声信息必须准确已知。实际情况下,大部分系统的模型和随机噪声信息不完全可知,这可能会导致滤波器估计精度下降。针对这一问题,根据求解遗传因子的方法不同对传统的自适应衰减卡尔曼滤波进行改进,提出一种改进的自适应衰减卡尔曼滤波。改进后的算法分别适用于系统噪声统计模型不准确可知和量测噪声统计模型不准确可知两种情况,分别对应于两种滤波算法,并且二者具有统一的滤波框架。仿真结果表明,改进的自适应衰减卡尔曼滤波比卡尔曼滤波精度较高,有效解决了因为噪声模型不准确导致的精度下降问题。     

联合深度神经网络和凸优化的单通道语音增强算法

噪声估计的准确性直接影响语音增强算法的好坏,为提升当前语音增强算法的噪声抑制效果,有效求解无约束优化问题,提出一种联合深度神经网络(DNN)和凸优化的时频掩蔽优化算法进行单通道语音增强。首先,提取带噪语音的能量谱作为DNN的输入特征;接着,将噪声与带噪语音的频带内互相关系数(ICC Factor)作为DNN的训练目标;然后,利用DNN模型得到的互相关系数构造凸优化的目标函数;最后,联合DNN和凸优化,利用新混合共轭梯度法迭代处理初始掩蔽,通过新的掩蔽合成增强语音。仿真实验表明,在不同背景噪声的低信噪比下,相比改进前,新的掩蔽使增强语音获得了更好的对数谱距离(LSD)、主观语音质量(PESQ)、短时客观可懂度(STOI)和分段信噪比(segSNR)指标,提升了语音的整体质量并且可以有效抑制噪声。      

采用性别相关的深度神经网络及非负矩阵分解模型用于单通道语音增强

为了从带噪信号中得到纯净的语音信号,提出了一种采用性别相关模型的单通道语音增强算法。具体而言,在训练阶段,分别训练了与性别相关的深度神经网络-非负矩阵分解模型用于估计非负矩阵分解中的权重参数;在测试阶段,提出了一种基于非负矩阵分解和组稀疏惩罚的算法用于判断测试语音中说话人的性别信息,然后再采用对应的模型估计权重,并结合已训练好的字典进行语音增强。实验结果表明所提算法在噪声抑制量及语音质量上,均优于一些基于非负矩阵分解的算法和基于深度神经网络的算法。      

一种对加性噪声和信道函数联合补偿的模型估计方法

语音识别系统在面对实际环境中多变的加性噪声和信道差异的影响时性能急剧下降,抑制这些噪声和差异所造成的性能下降具有重要意义.作者提出了一种模型补偿算法,使用句子中的非语音段估计加性噪声,然后利用EM算法估计信道函数,从而在倒谱域上对失配的声学模型进行联合补偿.实验表明,相比基线系统,采用该算法的系统的平均性能相对提升幅度超过50%.算法可以动态跟踪环境的变化,性能表现优于一些传统的语音识别稳健性处理算法.     

基于噪声追踪的二值时频掩蔽到浮值掩蔽的泛化算法

虽然浮值掩蔽比二值掩蔽有更好的语音分离效果,但是由于理想浮值掩蔽难以直接估计,现有的语音分离系统通常以理想二值掩蔽估计作为计算目标。我们提出了一个二值掩蔽到浮值掩蔽的泛化算法。由于实现浮值掩蔽估计的关键在于噪声能量追踪,我们首先采用指数分布刻画以混合谱和噪声能量以混合能量及二值掩蔽为观测的条件分布。其次,采用高斯马尔柯夫条件随机场刻画噪声估计在连续几帧内的关联。最后,采用马尔柯夫链-蒙特卡洛计算噪声能量最小均方误差估计并进一步计算浮值掩蔽。实验表明,相比于基于二值掩蔽估计的常规算法,我们所提出的算法在信噪比增益和客观感知质量两方面都有显著提高。      

基于高斯-拉普拉斯-伽玛模型和人耳听觉掩蔽效应的信号子空间语音增强算法

针对信号子空间语音增强算法中的子空间选择和线性滤波器中噪声功率谱和拉格朗日乘子的估计问题,用高斯、拉普拉斯和伽玛模型描述了语音的分布,提出了利用目标语音概率最大化来确定信号子空间维度的方法。在噪声子空间上,利用条件概率估计出噪声功率谱。接着,为了合理地折中增强语音中的残余噪声和语音畸变,提出了一种基于人耳听觉掩蔽效应的拉格朗日乘子估计方法。实验证明,在多项语音质量评价指标上,所提算法都取得了更好的结果。所提的信号子空间算法比传统的信号子空间算法更有效地消除了噪声,使得恢复的语音具有更好的质量。      

Single-channel speech enhancement method using reconstructive NMF with spectrotemporal speech presence probabilities

In this paper, a novel single microphone channel-based speech enhancement technique is presented. While most of the conventional nonnegative matrix factorization-based approaches focus on generating a basis matrix of speech and noise for enhancement, the proposed algorithm performs an additional process to reconstruct speech from noisy speech when these two elements are highly overlapped in selected spectral bands. This process involves a log-spectral amplitude based estimator, which provides the spectrotemporal speech presence probability to obtain a more accurate reconstruction. Moreover, the proposed algorithm applies an unsupervised learning method to the input noise, so it is adaptable to any type of environmental noise without a pre-trained dictionary. The experimental results demonstrate that the proposed algorithm obtains improved speech enhancement performance compared with conventional single channel-based approaches.     

Synthesis and modification of the whistles of the bottlenose dolphin, Tursiops truncatus

A signal-processing algorithm was developed to analyze harmonic frequency-modulated sounds, to modify the parameters of the analyzed signal, and to synthesize a new analytically specified signal that resembles the original signal in specified features. This algorithm was used with dolphin whistles, a frequency-modulated harmonic signal that has typically been described in terms of its contour, or pattern of modulation of the fundamental frequency. In order to test whether other features may also be salient to dolphins, the whistle analysis calculates the energies at the harmonics as well as the fundamental frequency of the whistle. The modification part of the algorithm can set all of these energies to a constant, can shift the whistle frequency, and can expand or compress the time base or the frequency of the whistle. The synthesis part of the algorithm then synthesizes a waveform based upon the energies and frequencies of the fundamental and first two harmonics. These synthetic whistles will be useful for evaluating what acoustic features dolphins use in discriminating different whistles.     

Enhancing Chinese tone recognition by manipulating amplitude envelope: implications for cochlear implants

Tone recognition is important for speech understanding in tonal languages such as Mandarin Chinese. Cochlear implant patients are able to perceive some tonal information by using temporal cues such as periodicity-related amplitude fluctuations and similarities between the fundamental frequency (F0) contour and the amplitude envelope. The present study investigates whether modifying the amplitude envelope to better resemble the F0 contour can further improve tone recognition in multichannel cochlear implants. Chinese tone and vowel recognition were measured for six native Chinese normal-hearing subjects listening to a simulation of a four-channel cochlear implant speech processor with and without amplitude envelope enhancement. Two algorithms were proposed to modify the amplitude envelope to more closely resemble the F0 contour. In the first algorithm, the amplitude envelope as well as the modulation depth of periodicity fluctuations was adjusted for each spectral channel. In the second algorithm, the overall amplitude envelope was adjusted before multichannel speech processing, thus reducing any local distortions to the speech spectral envelope. The results showed that both algorithms significantly improved Chinese tone recognition. By adjusting the overall amplitude envelope to match the F0 contour before multichannel processing, vowel recognition was better preserved and less speech-processing computation was required. The results suggest that modifying the amplitude envelope to more closely resemble the F0 contour may be a useful approach toward improving Chinese-speaking cochlear implant patients' tone recognition.     

Spectral characterization of jitter, shimmer, and additive noise in synthetically generated voice signals

Alteration of the harmonic structure in voice source spectra, taken over at least two periods of the waveform, may occur due to the presence of fundamental frequency (f0) perturbation, amplitude perturbation, additive noise, or changes within the glottal source signal itself. In order to make accurate inferences regarding glottal-flow dynamics or perceptual evaluations based on spectral measurements taken from the acoustic speech waveform, investigation of the spectral features of each aperiodic component is required. Based on a heuristic development involving a consideration of the partial sum of the Fourier series taken for two periods of a jittered, shimmered, and (additive, random) noise-contaminated signal, the corresponding spectral characteristics are hypothesized. Subsequent to this, the Fourier series coefficients are calculated for the two periods in order to test the hypotheses. Definite spectral differences are found for each aperiodic component; based on these findings differential quantitative spectral measurements are suggested. Further supportive evidence is obtained through use of Fourier transform and periodogram-averaged calculations. The analysis is carried out on synthetically generated glottal-pulse waveforms and on radiated speech waveforms. A discussion of the results is given in terms of voice aperiodicity in general and in terms of their implication for future studies involving human voice signals.     

近似窄带假设下的最小方差无失真响应波束形成

最小方差无失真响应波束形成算法在应用于语音等宽带信号时,依赖窄带假设可以在频域各个子带分别进行滤波。窄带假设下语音信号协方差矩阵是秩-1矩阵,而实际中窄带信号模型只是实际信号模型的一种近似,同时由于存在统计量估计误差,估计的语音信号协方差矩阵的秩一般大于1。提出利用语音协方差矩阵和噪声协方差矩阵的广义主特征向量来估计相对传递函数,用于重构语音信号协方差矩阵为秩-1矩阵。在REVERB数据集以及CHiME-4数据集上进行实验验证,最小方差无失真响应波束形成算法经过语音协方差矩阵低秩近似后,对估计误差的鲁棒性提高,输出信噪比分别提升平均0.8 dB和1.4 dB,同时提升了语音识别准确率。      

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,为输出信号降噪和失真的折中提供了更多选择。在扩散噪声下的单目标和多目标实验中,所提方法的语音提取和分离性能都优于对比算法,联合参数的后置滤波器可提供更为符合人们要求的降噪语音,验证了所提模型与参数估计方法的有效性。      

支持向量学习并行区域增长结合活动轮廓模型的图像分割算法

为克服经典区域增长算法门限设置困难和图像分割精度不高的问题,提出了基于支持向量机学习的区域增长与活动轮廓模型结合的高精度图像分割算法。首先交互式选择属于目标区域的子块和背景区域的子块形成支持向量机的训练样本;并利用这些已知的训练样本训练支持向量分类器。在目标与背景的并行竞争增长过程中,利用训练好的支持向量分类器(SVC)进行分类判决,得到目标对象的初始轮廓。为提高分割对象的精度,采用活动轮廓模型获得准确的边缘。仿真实验获得了较好的分割效果,表明该提出的算法是合理可行的。     

基于矢量水听器阵列空域预滤波处理的多重信号分类算法研究

矢量水听器能同时拾取声压和振速信息,在相同的信噪比、阵元数及阵列孔径下,矢量阵定向性能优于声压阵列。目前,以多重信号分类算法(Multiple signal classification,MUSIC)为代表的高分辨定向算法已经广泛应用于矢量水听器阵列中。但是随着信噪比降低、信号源方位间隔减小,传统MUSIC算法定向精度及分辨概率显著下降。本文采用最小二乘法设计适用于矢量水听器水平阵列的矩阵空域滤波器,用于阵列数据的空间滤波预处理,可以对阻带扇面噪声进行有效抑制。由滤波后的数据协方差矩阵可以得到新的噪声子空间,在传统MUSIC算法基础上修正通带扇面内阵列流型的畸变后即可得到滤波后MUSIC算法的方位谱。仿真结果表明,当信噪比较低时,改进算法有效提高了通带扇面内目标方位分辨性能。最后本文对四基元矢量水平阵列海试数据进行了处理,改进算法对窄带信号定向较常规算法-3 dB束宽减小了13°,旁瓣级降低约8 dB。对有一定带宽的行船辐射噪声定向处理得到了更加精确的航迹图,海试数据处理结果证明了该算法的可行性和有效性。     

采用骨导语音自适应的语句分割方法*

为了解决含噪语句分割问题,也为了解决某些低信噪比环境下传统气导语句分割算法分割效果差、分割准确度低且算法自适应性弱等问题,提出一种基于骨导语音自适应的分段双门限语音分割方法。将骨导语音和气导语音同步采集,获取抗噪性能更好的骨导语音,然后在融合过零率与短时能量中引入随机动态阈值的自适应方法进行端点检测,最后利用分段双门限和语音聚类等手段实现语音分割,提高语音分割算法的鲁棒性。通过实验验证了所提算法的有效性和可行性,同时与其他语音分割算法进行了对比,证明该文所提分割算法精度更高,效果更好。