共查询到19条相似文献，搜索用时 266 毫秒
1.
由于实际环境中各种噪声的干扰 ,语音识别的准确率会受到不同程度的影响 ,因此 ,鲁棒性技术已成为语音识别的一个研究热点。其中 ,并行模型组合方法 (PMC)在提高模型对环境的适应性方面发挥着重要作用。分析了PMC中如何解决其技术难点的一些方法 ,并作了相应的优化改进 ,从而使PMC方法能适用于较为复杂的实际情况。实验利用了剑桥大学的HTK语音识别工具包 ,并加入自行开发的算法 ,可用于对 0～ 91 0个中文数字组成的数字串进行连续语音识别。结果表明 ,在不同的噪声环境下 ,新的PMC技术能显著提高识别率 相似文献
2.
3.
针对一类非线性模糊脉冲系统,提出了一种鲁棒控制器设计的方案.采用并行分布补偿(PDC)的基本思想设计状态反馈控制器.利用Lyapunov稳定性方法,给出了闭环系统全局指数稳定且具有性能的充分条件. 相似文献
4.
《科技通报》2016,(2)
将攻击图与并行遗传算法相结合,提出了一种基于并行遗传算法的网络最优弥补模型PGA-ONHM(optimal network hardening model based on parallel genetic algorithm),该模型能得到目标网络系统的近似解。为了验证该模型的可行性、有效性和可扩展性,本文从不同的分析角度进行仿真验证,实验结果表明:并行遗传算法的CPU消耗时间随着初始属性节点数量的增加呈多项式增加,随着子群体数量的增加呈减小趋势;无论是平均迭代次数还是单次迭代的平均计算时间,并行遗传算法比经典遗传算法都要优越;并行遗传算法可以得到较好的加速比;能够克服局部最优解的问题,可以适用于大规模复杂的网络系统。 相似文献
5.
在语音识别中鲁棒性是一个很关键的因素,文章提出了一种关于0～9数字语音识别算法,采用递归最小二乘法(RLS)来消除噪声,系统使用过零率和能量参数作为端点检测方法,用美尔倒普系数(MFCC)矢量作为声道估计的滤波器,同时,采用动态时间弯折算法来识别语音。结果显示,未加RLS消噪系统前系统的识别率为72%,在处理过程中加入RLS消噪后识别率提高到98.7%。 相似文献
6.
基于PC机群的并行信息检索系统 总被引：1，自引：0，他引：1
在分析传统信息检索优缺点的基础上，提出一种新的信息检索模型，充分利用现有的廉价的PC机群来实现并行检索，提出在PC机群间分解倒排索引文件的算法，并对该模型进行了分析和评价，说明该模型可以有效地提高检索性能。 相似文献
7.
对并行组合扩频通信系统抗加性高斯白噪声的性能进行分析,提出了一种全新的方案,即将解相关多用户检测技术用于接收端进行联合检测。通过MATL AB仿真,验证了采用解相关多用户检测技术的并行组合扩频通信系统较传统并行组合扩频通信可以有效抑制加性高斯白噪声,降低了系统误码率,接收性能有所改善。 相似文献
8.
为了适应强噪声环境下的语音识别,进行了基于美尔倒谱系数特征及隐马尔可夫模型的识别算法研究,主要对提取语音信号的线性预测系数、端点检测、语音特征参数提取、语音算法识别流程等进行了初步研究,并进行了说话人识别系统的仿真验证。 相似文献
9.
不同舰船目标辐射噪声的噪声平均功率谱具有差异性特征,能在一定程度上反映舰船目标的吨位、航速、类型等。研究舰船辐射噪声信号的特征提取和频谱分解方法,对提高舰船目标的识别能力具有重要意义。传统的舰船辐射噪声关联特征提取采用的是基于定量递归分析的关联维特征提取方法,当在关联特征提取中舰船辐射噪声信号出现奇异吸引子特征时,提取的舰船目标特征产生混迭谱,导致频谱畸变,影响目标识别性能。针对这一问题,提出一种基于预畸变趋化关联特征提取的舰船噪声信号混迭谱分解方法,设计舰船辐射噪声产生与信号源系统模型,进行声传感器布置研究,进行特征提取和混迭谱分解算法改进分析。仿真实验得出,采用该方法进行舰船辐射噪声信号的预畸变趋化关联特征提取,能有效展示舰船辐射噪声信号的内部规律特征,提高对舰船辐射噪声信号的特征提取性能和目标识别精度。 相似文献
10.
分布式空间查询优化是提高分布式空间数据库性能的关键问题之一。本文针对区域分片的数据分布特征,在已有的跨边界连接转化及优化规则基础上,依据片段连接的分配规则将全局查询映射为局部片段连接,提出不同站点上交矩形大面积优先的任务排序策略以及基于子任务的代价模型的分布式并行查询动态任务调整方法。经过实验表明,该方法不仅进一步提高了分布式空间查询的效率,有效解决分布式空间并行查询的负载平衡问题。 相似文献
11.
Using an acoustic vector sensor (AVS), an efficient method has been presented recently for direction of arrival (DOA) estimation of multiple speech sources via the clustering of the inter-sensor data ratio (AVS-ISDR). Through extensive experiments on simulated and recorded data, we observed that the performance of the AVS-DOA method is largely dependent on the reliable extraction of the target speech dominated time–frequency points (TD-TFPs) which, however, may be degraded with the increase in the level of additive noise and room reverberation in the background. In this paper, inspired by the great success of deep learning in speech recognition, we design two new soft mask learners, namely deep neural network (DNN) and DNN cascaded with a support vector machine (DNN-SVM), for multi-source DOA estimation, where a novel feature, namely, the tandem local spectrogram block (TLSB) is used as the input to the system. Using our proposed soft mask learners, the TD-TFPs can be accurately extracted under different noisy and reverberant conditions. Additionally, the generated soft masks can be used to calculate the weighted centers of the ISDR-clusters for better DOA estimation as compared to the original center used in our previously proposed AVS-ISDR. Extensive experiments on simulated and recorded data have been presented to show the improved performance of our proposed methods over two baseline AVS-DOA methods in presence of noise and reverberation. 相似文献
12.
Emotional expression and understanding are normal instincts of human beings, but automatical emotion recognition from speech without referring any language or linguistic information remains an unclosed problem. The limited size of existing emotional data samples, and the relative higher dimensionality have outstripped many dimensionality reduction and feature selection algorithms. This paper focuses on the data preprocessing techniques which aim to extract the most effective acoustic features to improve the performance of the emotion recognition. A novel algorithm is presented in this paper, which can be applied on a small sized data set with a high number of features. The presented algorithm integrates the advantages from a decision tree method and the random forest ensemble. Experiment results on a series of Chinese emotional speech data sets indicate that the presented algorithm can achieve improved results on emotional recognition, and outperform the commonly used Principle Component Analysis (PCA)/Multi-Dimensional Scaling (MDS) methods, and the more recently developed ISOMap dimensionality reduction method. 相似文献
13.
14.
目标噪声特征提取是被动声纳目标识别系统的关键技术。首先提出了一种利用从噪声极限环中提取的非线性特征来分析舰船噪声信号的新方法,然后采用基于自适应遗传BP算法的神经网络对提取的特征进行分类。实验结果表明,该系统具有较好的分类效果。 相似文献
15.
Recently the Wigner distribution has been shown to be a potentially useful tool for analysing the time varying frequency domain phenomenon. In this paper, some of the salient features of the Wigner distribution are presented; properties of this important discrete distribution are derived, and an efficient digital implementation is presented. Effective Wigner throughput rates, in excess of those obtainable with an equivalent length FFT, are shown to be feasible. In particular, the Wigner distribution is studied in the context of enhancing speech analysis and recognition systems. It is suggested that this class of distribution is consistent with the mechanics of human speech and, using experimentation, produces a very robust spectral signature. This enriched data space can be used to uncover some frequency domain attributes of human speech which may be lost using a discrete Fourier transform. 相似文献
16.
Language modeling (LM), providing a principled mechanism to associate quantitative scores to sequences of words or tokens, has long been an interesting yet challenging problem in the field of speech and language processing. The n-gram model is still the predominant method, while a number of disparate LM methods, exploring either lexical co-occurrence or topic cues, have been developed to complement the n-gram model with some success. In this paper, we explore a novel language modeling framework built on top of the notion of relevance for speech recognition, where the relationship between a search history and the word being predicted is discovered through different granularities of semantic context for relevance modeling. Empirical experiments on a large vocabulary continuous speech recognition (LVCSR) task seem to demonstrate that the various language models deduced from our framework are very comparable to existing language models both in terms of perplexity and recognition error rate reductions. 相似文献
17.
In this paper, a new robust adaptive prescribed performance control (PPC, for short) scheme is proposed for quadrotor UAVs (QUAVs, for short) with unknown time-varying payloads and wind gust disturbances. Under the presented framework, the overall control system is decoupled into translational subsystem and rotational subsystem. These two subsystems are connected to each other through common attitude extraction algorithms. For translational subsystem, a novel robust adaptive PPC strategy is designed based on the sliding mode control technique to provide better trajectory tracking performance and well robustness. For rotational subsystem, a new robust adaptive controller is constructed based on backstepping technique to track the desired attitudes. Finally, the overall system is proved to be stable in the sense of uniform ultimate boundedness, and numerical simulation results are presented to validate the effectiveness of the proposed control scheme. 相似文献
18.
《Journal of The Franklin Institute》2022,359(6):2737-2754
The robust fault estimation problem for linear discrete time-varying (LDTV) systems subject to multiplicative noise is investigated by means of finite impulse response (FIR) filter. A novel analytical redundancy, expressed via all states of the previous time window, is originally established to construct the fault estimator. To ensure the satisfactory fault estimation accuracy in stochastic sense under the interference of random uncertainty, a new performance index in forms of matrix trace function is proposed. An easy-to-check necessary and sufficient condition is presented to obtain the optimal filter gain via minimizing the performance index at each time instant. It is analytically demonstrated that, the newly proposed fault estimation algorithm enjoys obvious computational advantages in updating the filter gain, especially as the length of the time window increases for time-varying systems. Simulation results are finally provided to verify its feasibility and superiority. 相似文献
19.
Named entity recognition (NER) is mostly formalized as a sequence labeling problem in which segments of named entities are represented by label sequences. Although a considerable effort has been made to investigate sophisticated features that encode textual characteristics of named entities (e.g. PEOPLE, LOCATION, etc.), little attention has been paid to segment representations (SRs) for multi-token named entities (e.g. the IOB2 notation). In this paper, we investigate the effects of different SRs on NER tasks, and propose a feature generation method using multiple SRs. The proposed method allows a model to exploit not only highly discriminative features of complex SRs but also robust features of simple SRs against the data sparseness problem. Since it incorporates different SRs as feature functions of Conditional Random Fields (CRFs), we can use the well-established procedure for training. In addition, the tagging speed of a model integrating multiple SRs can be accelerated equivalent to that of a model using only the most complex SR of the integrated model. Experimental results demonstrate that incorporating multiple SRs into a single model improves the performance and the stability of NER. We also provide the detailed analysis of the results. 相似文献