检索结果-南通市图书馆

Robust Speech Recognition System Using Conventional and Hybrid Features of MFCC,LPCC,PLP,RASTA-PLP and Hidden Markov Model Classifier in noisy conditions

引用

Journal of Computer and Communications 2015年第6期3卷 1-9页

作者： Veton Z.Kepuska Hussien A.Elharati Electrical&Computer Engineering Department Florida Institute of TechnologyMelbourneFLUSA

In recent years, the accuracy of speech recognition (SR) has been one of the most active areas of research. Despite that SR systems are working reasonably well in quiet conditions, they still suffer severe performance degradation in noisy conditions or distorted channels. It is necessary to search for more robust feature extraction methods to gain better performance in adverse conditions. This paper investigates the performance of conventional and new hybrid speech feature extraction algorithms of Mel Frequency Cepstrum Coefficient (MFCC), Linear Prediction Coding Coefficient (LPCC), perceptual linear production (PLP), and RASTA-PLP in noisy conditions through using multivariate Hidden Markov Model (HMM) classifier. The behavior of the proposal system is evaluated using TIDIGIT human voice dataset corpora, recorded from 208 different adult speakers in both training and testing process. The theoretical basis for speech processing and classifier procedures were presented, and the recognition results were obtained based on word recognition rate.

关键词： Speech Recognition noisy conditions Feature Extraction Mel-Frequency Cepstral Coefficients Linear Predictive Coding Coefficients Perceptual Linear Production RASTA-PLP Isolated Speech Hidden Markov Model

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Damage localization for beams based on the wavelet correlation operator

引用

Science China(Technological Sciences) 2017年第10期60卷 1505-1517页

作者： YANG ZhiBo CHEN XueFeng RADZIENSKI Maciej KUDELA Pawel OSTACHOWICZ Wieslaw XIE Yong School of Mechanical Engineering Xi'an Jiaotong UniversityXi'an 710049China Zhejiang Provincial Key Laboratory of Laser Processing Robot/Key Laboratory of Laser Precision Processing&Detection Wenzhou 325035China Institute of Fluid Flow Machinery Polish Academy of SeieneeGdansk 80-231Poland Faculty of Automotive and Construction Machinery Warsaw University of TechnologyWarsaw 02-524Poland School of Aerospace Xi'an Jiaotong UniversityXi'an 710049China

The continuous wavelet transform(CWT) is one of the crucial damage identification tools in the vibration-based damage assessment. Because of the vanishing moment property, the CWT method is capable of featuring damage singularity in the higher scales, and separating the global trends and noise progressively. In the classical investigations about this issue, the localization property of the CWT is usually deemed as the most critical point. The abundant information provided by the scale-domain information and the corresponding effectiveness are, however, neglected to some extent. Ultimately, this neglect restricts the sufficient application of the CWT method in damage localization, especially in noisy conditions. In order to address this problem,the wavelet correlation operator is introduced into the CWT damage detection method as a post-processing. By means of the correlations among different scales, the proposed operator suppresses noise, cancels global trends, and intensifies the damage features for various mode shapes. The proposed method is demonstrated numerically with emphasis on characterizing damage in noisy environments, where the wavelet scale Teager-Kaiser energy operator is taken as the benchmark method for *** validations are conducted based on the benchmark data from composite beam specimens measured by a scanning laser vibrometer. Numerical and experimental validations/comparisons present that the introduction of wavelet correlation operator is effective for damage localization in noisy conditions.

关键词： damage detection continuous wavelet transform wavelet correlation operator beam noisy conditions

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：