语音识别中小波分析的应用

语音信号是一种时变、非平稳的随机信号。现有语音识别系统的适应性比较差,尤其在高噪声环境下的语音识别非常困难,若将语音识别系统商品化,还有识别速度、拒识问题以及关键词／句检测技术等细节问题需要解决。如何把语言学、生理学、心理学方面的研究成果量化、建模并用于语音识别,还需深入研究。本文介绍了语音识别中小波分析的研究现状及几种常见的技术方法,并且分析探讨了语音识别中小波分析的应用和发展前景。     

孤立词语音识别技术及其应用前景分析

孤立词语音识别技术,采用的是模式匹配法,是语音识别技术的核心之一。首先,用户将词汇表中的每一词依次说一遍,并且将其特征矢量作为模板存入棋板库。然后,将输入语音的特征矢量依次与模板库中的每个模板进行相似度比较,将相似度最高者作为识别结果输出。本文介绍了孤立词语音识别技术的研究现状及几种常见的技术方法,并且分析探讨了孤立词语音识别技术的应用和发展前景。     

On adaptive sliding mode control without switching gain overestimation

This paper presents some further results on adaptive sliding mode control (ASMC) for a class of nonlinear systems with bounded uncertain parameters. Given a large initial tracking error, current ASMC design generally produces an unnecessarily large switching gain, consequently leading to a serious chattering problem or a large‐amplitude control jump for the continuous counterpart. To solve such an overadaptation problem, the switching gain adaptation mechanism is first analyzed in this paper, and the adaptation induced by the initial tracking error is suggested to be removed. Then, by exploiting the global sliding mode feature of time‐varying sliding mode control and integral sliding mode control, we present two effective methodologies for ASMC design. The proposed ASMC algorithms ensure that there is no overestimation of the switching gain and the system response is not slowed down when a small switching gain is generated. The validity of the proposed methods is verified by both theoretical analysis and simulation results. Copyright © 2012 John Wiley & Sons, Ltd.     

An expressive framework and efficient algorithms for the analysis of collaborative tagging

The rise of Web 2.0 is signaled by sites such as Flickr, del.icio.us, and YouTube, and social tagging is essential to their success. A typical tagging action involves three components, user, item (e.g., photos in Flickr), and tags (i.e., words or phrases). Analyzing how tags are assigned by certain users to certain items has important implications in helping users search for desired information. In this paper, we develop a dual mining framework to explore tagging behavior. This framework is centered around two opposing measures, similarity and diversity, applied to one or more tagging components, and therefore enables a wide range of analysis scenarios such as characterizing similar users tagging diverse items with similar tags or diverse users tagging similar items with diverse tags. By adopting different concrete measures for similarity and diversity in the framework, we show that a wide range of concrete analysis problems can be defined and they are NP-Complete in general. We design four sets of efficient algorithms for solving many of those problems and demonstrate, through comprehensive experiments over real data, that our algorithms significantly out-perform the exact brute-force approach without compromising analysis result quality.     

Corner forming of AZ61A magnesium alloy tube within warm hydroforming

The corners with small radii on cross sections are crucial for forming hydroformed components with polygonal sections.In this paper,warm hydroforming experiments of AZ61A magnesium alloy tubes were carried out to study the forming regularity of round corners by using a demonstration part with square sections.Effects of temperature on radius forming,thinning ratio distribution and microstructure were revealed and a component with relative outer corner radius of 3.0 was obtained by warm hydroforming at 240℃.The minimum thickness of the formed square section was located in the transition position between the corner and the straight wall.The thinning ratio of the round corner increased with the increase of forming temperature.Formability of the magnesium tube was improved by raising temperature under the effect of dynamic recrystallization at 240℃.     

海底管线防冲刷技术试验研究

海底冲刷现象严重威胁着海底管线的安全运营.该文从海底管线冲刷机理入手,根据海底管线防冲刷技术的基本原理,提出了仿生防护措施--"人工草"固定法,并结合现有工程项目进行了试验研究,结果表明该方法可以有效地解决海底冲刷造成的管道悬空问题,为海底管线工程的设计、施工和维护提供了指导性的参考.     

基于改进选择性BPSO算法的配电网降损重构研究

为了降低配电网的有功功率损耗以及提高开关利用率,利用Sigmoid函数对二进制粒子群优化(BPSO)算法中的粒子位置更新进行改进,并通过添加修改曲线的参数对函数进行选择,提出了一种改进选择性二进制粒子群优化(IS-BPSO)算法来求解配电网降损重构问题.该算法以降低配电网的功率损耗为目标,有效地控制粒子的变化速率并提高种群的收敛性.通过33母线和94母线的配电网测试系统进行仿真模拟,结果表明,该算法具有很强的鲁棒性和全局寻优能力.     

Reaction mechanism and microstructure evolution of reaction sintered <Emphasis Type="Italic">h</Emphasis>-BN

Hexagonal boron nitride ceramic (h-BN) based on the nitridation of B powders was obtained by reaction sintering method. The effects of sintering temperature on the mechanical properties and microstructure of the resultant products were investigated and the reaction mechanism was discussed. Results showed that the reaction between B and N₂ occurred vigorously at temperatures ranging from 1 000 °C to 1 300 °C, which resulted in the generation of t-BN. When the temperature exceeded 1 450 °C, transformation from t-BN to h-BN began to occur. As the sintering temperature increased, the spherical particles of t-BN gradually transformed into fine sheet particles of h-BN. These particles subsequently displayed a compact arrangement to achieve a more uniform microstructure, thereby increasing the strength.     

Modal Identification of Linear Time-varying Systems Using Continuous Wavelet Transform

A wavelet based identification method for linear time-varying systems is presented,and the ridge and skeleton of the continuous wavelet transform of free response is used to extract time-varying parameters. The stiffness and damping coefficients of single-degree-of—freedom systems,frequencies and damping ratios of multi-degree-of-freedom systems are estimated without any prior information of systems. The proposed method is applied to linear time-varying systems with both abrupt and smooth variation parameters. Gaussian white noise is added to the response to test the anti-noise performance of the algorithm. The simulation results show that the proposed method is capable of accurately tracking the variation of the systems.