改进的高效动态时间规整算法语音识别系统

动态时间规整算法是结合了动态时间规整(DTW)技术和距离测度计算技术的一种非线性规整算法,在语音识别模板匹配中有重要的应用。为此提出一种改进的高效动态时间规整算法,其能有效加快搜索路径的寻找。基于Matlab实现了隐马尔科夫算法、高效动态时间规整算法和改进的高效动态时间规整算法的语音识别系统,同时进行了算法的仿真实验。实验结果表明,基于改进高效动态时间规整算法的训练速度远大于基于隐马尔可夫算法和高效动态时间规整算法的训练速度,而识别率下降很小,对于小词汇量非连续语音识别中高效动态时间规整算法的识别率为97.56%,隐马尔可夫算法的识别率为97.14%,改进高效动态时间规整算法的识别率为96.43%。     

On split Dynamic Time Warping for robust Automatic Dialogue Replacement

In this article, we present LipSynch, a software tool that can be used for the automatic replacement of speech dialogues in motion pictures, video or television series. The system operates in two steps: during analysis, the timing relationships between the speech segments of the dialogues that serve as a timing reference and the corresponding speech segments in the replacement dialogues are measured by means of a split Dynamic Time Warping algorithm. The obtained warping paths are then processed and used to synthesize high-quality natural-sounding speech dialogues that are precisely time-synchronized with the reference dialogues. Subjective audio-visual listening tests performed within the context of a difficult Automatic Dialogue Replacement task demonstrated that LipSynch achieves a significant improvement compared to the industry-standard benchmark VocALign, both in terms of achieved lip-synchronization accuracy as well as in overall speech quality of the synthesized dialogues.     

应用动态时间规整算法实现雷达辐射源个体识别

雷达辐射源个体识别,即识别同型号同批次的雷达辐射源,是当今电子战研究的重点课题。雷达辐射源的个体差异是由其内部各种元器件的细微差异产生的,瞬时幅度和瞬时频率能够很好地体现雷达辐射源的个体差异。基于这一事实,采用动态时间规整算法实现了雷达辐射源的距离测度。利用数据融合技术,综合考虑了瞬时幅度和瞬时频率的动态时间规整测度值,实现了雷达辐射源个体识别中的目标匹配。最后,通过仿真验证了动态时间规整算法在雷达辐射源个体识别课题中的可行性。      

语音识别中动态时间规整算法的硬件加速实现

动态时间规整算法(Dynamic Time Warping,DTW)是语音识别中常用的技术之一.为了提升因数据量增加以及算法对数据的高度依赖性所导致的计算性能降低,提出一种针对语音帧的动态时间规整算法硬件架构.识别计算过程中,通过使用算法时间复杂度相对低的下界距离函数(Lower Bound Function,LBF)...     

DTW的ASIC实现算法研究

通过分析DTW算法，提出了一种适合ASIC实现的心动阵列结构。仿真结果表明，该并行VLSI处理器阵列系统能够在N M-1个时钟周期内计算出两个模板的匹配加权距离。较之基于通用处理器串行实现的DTW算法需要的3pMN／2个时钟周期，该算法节省了大量的运算时间。     

缺失数据的主曲线恢复方法

介绍了缺失数据属性值的一些处理方法,给出了一种新的基于主曲线的缺失数据属性值的恢复方法,详细地描述了利用该方法对缺失属性值进行恢复的步骤,这种方法能根据数据的特性对缺失属性值进行预测,处理的问题带有一般性,并用具体实验数据验证实验该方法的有效性,通过和其他方法进行比较验证了它的精确性.     

基于动态时间规整和主动外观模型的动态表情识别

针对静态表情特征缺乏时间信息,不能充分体现表情的细微变化,该文提出一种针对非特定人的动态表情识别方法：基于动态时间规整(Dynamic Time Warping, DTW)和主动外观模型(Active Appearance Model, AAM)的动态表情识别。首先采用基于局部梯度DT-CWT(Dual-Tree Complex Wavelet Transform)主方向模式(Dominant Direction Pattern, DDP)特征的DTW对表情序列进行规整。然后采用AAM定位出表情图像的66个特征点并进行跟踪,利用中性脸的特征点构建人脸几何模型,通过人脸几何模型的匹配克服不同人呈现表情的差异,并通过计算表情序列中相邻两帧图像对应特征点的位移获得表情的变化特征。最后采用最近邻分类器进行分类识别。在CK+库和实验室自建库HFUT-FE(HeFei University of Technology-Face Emotion)上的实验结果表明,所提算法具有较高的准确性。     

机群系统上并行计算时间序列的动态弯曲距离

时间序列的相似性度量是衡量两个序列相似性的依据.动态时间弯曲距离计算方法具有较强的健壮性且可以度量不同长度的时间序列间的相似性,但其十分耗时.采用波前式推进方法并行计算动态时间弯曲距离并以流水线并行方式传送局部子结果,提出一个在机群系统上实现的度量两个时间序列相似性的并行算法.PC机群系统上的实验结果表明,该并行算法高效,获得了良好的加速和可扩展性.     

基于动态规整与改进变分自编码器的异常电池在线检测方法

针对电池生产成组过程中,传统异常检测方法对混入的容量及压差异常电池检测精度低及生产结束后离线异常检测方法效率低等问题,该文提出一种集合长短期记忆变分自编码器与动态时间规整评价的锂电池异常在线检测方法(VAE-LSTM-DTW),实现了异常电池的在线检测,避免了离线异常检测所造成的时间和能源的浪费。该方法首先将长短期记忆网络(LSTM)引入变分自编码器(VAE)模型,训练电池时序数据重构模型;其次,在电池异常检测的度量标准中引入动态时间规整值(DTW),并基于贝叶斯寻优获得最优检测阈值,对每个单体电池重构数据的动态规整值进行异常辨别。实验结果表明,相较该领域传统异常检测方法,VAE-LSTM-DTW模型性能优越,查准率和F1值都得到了较大的提升,具有较高的有效性和实用性。     

Detection and Mitigation of Smart Blackhole and Gray Hole Attacks in VANET Using Dynamic Time Warping

Wireless Personal Communications - VANET topology is highly dynamic, wherein the vehicles frequently move across locations. Due to the continually changing topology and lack of security...     

Enhancement and Dynamic Time Warping of Somatosensory Evoked Potential Components Applied to Patients with Multiple Sclerosis

A zero-phase, high-pass digital filter at 300 Hz was used to emphasize the higher frequency, smaller peaks of the somatosensory evoked potential (SEP). Using the digital filter, a consistent pattern of peaks was observed in normals. A dynamic time-warping technique was created to align the peaks of digitally high-pass filtered SEP's. Based on this technique, a clinical test for abnormality of the SEP was developed and applied to 25 multiple sclerosis patients. The results showed that three times as many multiple sclerosis SEP's were identified by the dynamic time warping as by the traditional latency measurement.     

动态时间规正与差别子空间相结合变异语音识别的在线训练方法

应力影响下的变异语音(由于说话人受到重力加速度变化而产生)可以用动态时间规正与差别子空间相结合的方法进行识别,但是该方法空间开销很大,而且训练算法极为复杂。针对该方法提出特征矢量替换法和特征矢量求平均法两种基于聚类思想的简单在线训练方法,取一个较小的初始训练集,然后用在线训练的方法使系统识别率达到最大。实验结果表明,其中特征矢量求平均的在线训练方法非常有效,保证系统整体识别率的同时,大大减小了系统的空间开销,适合于训练数据有限的变异语音识别。     

基于最小二乘曲线拟合的时间配准方法研究

针对单一手段探测低慢小目标能力不足的问题,提出了运用雷达/红外手段联合探测的方法.但在雷达红外数据融合之前,需要解决时间配准的问题.为解决这个问题,提出了一种基于最小二乘曲线拟合的时间配准改进方法,推导出了改进的最小二乘曲线拟合公式,分析了影响拟合精度的因素,通过仿真分析验证了该方法的有效性.     

Space‐Time Warp Curve for Synthesizing Multi‐character Motions

This paper introduces a new motion‐synthesis technique for animating multiple characters. At a high level, we introduce a hub‐sub‐control‐point scheme that automatically generates many different spline curves from a user scribble. Then, each spline curve becomes a trajectory along which a 3D character moves. Based on the given curves, our algorithm synthesizes motions using a cyclic motion. In this process, space‐time warp curves, which are time‐warp curves, are embedded in the 3D environment to control the speed of the motions. Since the space‐time warp curve represents a trajectory over the time domain, it enables us to verify whether the trajectory causes any collisions between characters by simply checking whether two space‐time warp curves intersect. In addition, it is possible to edit space‐time warp curves at run time to change the speed of the characters. We use several experiments to demonstrate that the proposed algorithm can efficiently synthesize a group of character motions. Our method creates collision‐avoiding trajectories ten times faster than those created manually.     

FR—4型覆铜板翘曲与解决措施

自踏入覆铜板行业至今三十余年,深感要做覆铜板很容易,但要做好却很难。说到做覆铜板很容易,以FR-4型覆铜板为例,不管你的树脂配方中DICY的用量是3.5还是2.7;上胶机烤箱的温度是150℃还是230℃,不管你用的是A级粘结片还是B级粘结片甚至是“垃圾料”,     

曲线阵列

在《电声技术》前几期介绍MeyerSound线阵列理论研究及直线阵列M３D的基础上，继续就线阵列中的曲线阵列进行探讨。水平曲线阵列是由已经沿用了几十年的工业标准的梯形箱体组成，该标准是MeyerSound早在８０年代初开发的MSL－１０扬声器系统始创，它们的特性已被人们广泛熟知。这一古老的线阵列在专业扩声领域中展现出新的应用。在这些应用中，阵列为了适应覆盖的要求，通常是弯曲的（在有些例子中是完全弯曲的）。但弯曲的“线阵列”的特性很复杂，会因频率不同而产生改变，为了正确应用垂直曲线阵列就一定要理解它。当代实用的线阵列…     

通过采样和卷绕联系四类傅里叶表示

众所周知,在时域(频域)离散化对应于在频域(时域)周期化,本文把采样和卷绕分别作为离散化和周期化的方式,考察在时域(频域)中相对应的混叠和内积。在这个统一的框架内,四类傅里叶表示被轮流使用,展示了微妙的联系。此外,得到这些结果的推导方法很容易从一种傅里叶表示移植到另一种傅里叶表示,所以易于为学生接受。     

湿法刻蚀应对圆片减薄后翘曲问题的探讨

随着微电子产业的发展,圆片直径越来越大、厚度越来越薄。一些本来不被关注的问题逐渐凸现出来。当150mm、200mm甚至300mm的圆片被减薄到200μm或者200μm以下时,圆片本身的刚性将慢慢变得不足以使其保持原来平整的状态。文章从圆片减薄后产生翘曲的直观表象入手,分析了产生翘曲问题的根本原因,采用湿法刻蚀的方式去除了圆片因减薄形成的背面损伤层,改善了圆片减薄后的翘曲问题。     

A Geometry-Driven Optical Flow Warping for Spatial Normalization of Cortical Surfaces

Spatial normalization is frequently used to map data to a standard coordinate system by removing intersubject morphological differences, thereby allowing for group analysis to be carried out. The work presented in this paper is motivated by the need for an automated cortical surface normalization technique that will automatically identify homologous cortical landmarks and map them to the same coordinates on a standard manifold. The geometry of a cortical surface is analyzed using two shape measures that distinguish the sulcal and gyral regions in a multiscale framework. A multichannel optical flow warping procedure aligns these shape measures between a reference brain and a subject brain, creating the desired normalization. The partial differential equation that carries out the warping is implemented in a Euclidean framework in order to facilitate a multiresolution strategy, thereby permitting large deformations between the two surfaces. The technique is demonstrated by aligning 33 normal cortical surfaces and showing both improved structural alignment in manually labeled sulci and improved functional alignment in positron emission tomography data mapped to the surfaces. A quantitative comparison between our proposed surface-based spatial normalization method and a leading volumetric spatial normalization method is included to show that the surface-based spatial normalization performs better in matching homologous cortical anatomies.      

基于模糊聚类和网格变形的自适应时-空差错掩盖方法

当视频传输中出现不能恢复的误码或丢包时,在接收端就要使用差错掩盖技术对损坏的视频进行掩藏。该文提出了一种基于模糊聚类和网格变形的自适应差错掩盖方法,使得错误恢复效果提高。该方法首先用基于时-空的模糊聚类块匹配方法补偿平移运动场景中的块丢失,然后如果检测出丢失块所在的空间有旋转、缩放等复杂运动,则用基于网格变形的方法进行补偿。实验结果表明其PSNR值比Luigi(2001)的BMA-MBW方法平均提高约1.5dB,比传统的基于块匹配的方法平均提高约3.5dB。