HTK参数对普米语孤立词识别率的影响

普米语是一种无文字的少数民族语言,目前已处于濒危状态,建立语音语料库及开展语音识别研究是保护和传承普米语的重要手段.基于HTK的语音识别中,参数的选取对不同语言的识别率有很大的影响.针对MFCC维数、HMM状态数及GMM个数这3个参数对普米语的识别率进行研究,结果表明:普米语语音识别的最佳MFCC维数为13维,最佳HMM状态数为8个,最佳GMM个数为3个.     

现代教学媒体及其应用的探讨

教学媒体是现代教育技术的重要组成部分，它是人类社会发展的成果之一，文章对各类现代教学媒体进行了探讨。     

A Reliability Analysis of Calculated Results for Odd-Even and Odd-Odd Nuclei in Relativistic Mean-Field Theory

We calculate the binding energies of Ni, Cu, Xe, Cs, Pt, Au, Np, Pu isotope chains using two interaction parameter sets NL-3 and NL-Z, and compared the relative errors of the even-even nuclei with those of odd-even nuclei and odd-odd nuclei. We find that the errors of binding energy of odd-even and odd-odd nuclei are not bigger than the one of even-even nuclei. The result shows that comparing with even-even nuclei, there is no systematic error and approximation in the calculations of the binding energy of odd-even and odd-odd nuclei with relativistic mean-field theory. In addition, the result is explained theoretically.     

对专科综合英语教学的探索与思考

综合英语教学是英语专业学习中的核心内容。文章就如何抓好专科综合英语教学中的语音基础及以学生为中心的教学模式展开探索与思考     

Speech emotion recognition based on statistical pitch model

A modified Parzen-window method, which keep high resolution in low frequencies and keep smoothness in high frequencies, is proposed to obtain statistical model. Then, a gender classification method utilizing the statistical model is proposed, which have a 98% accuracy of gender classification while long sentence is dealt with. By separation the male voice and female voice, the mean and standard deviation of speech training samples with different emotion are used to create the corresponding emotion models. Then the Bhattacharyya distance between the test sample and statistical models of pitch, are utilized for emotion recognition in speech. The normalization of pitch for the male voice and female voice are also considered, in order to illustrate them into a uniform space. Finally, the speech emotion recognition experiment based on K Nearest Neighbor shows that, the correct rate of 81% is achieved, where it is only 73.85% if the traditional parameters are utilized.     

论英语语音含混对语义的影响及解决办法

从音系学的观点入手 ,用实例论证英语口语中连读、不完全爆破和同音异义词等所带来的语音含混 ,从而导致语音信号的受体对主体所发信号不能明确辨别 ,影响正常交际这一自然语言特征 ,并提出了有效的解决方法     

几何直观在线性代数教学中的应用

本文强调了几何直观在线性代数教学中的作用 ,通过例子从代数概念的引入、代数性质的几何解释、代数理论应用的直观分析几个方面加以说明 .     

一种基于段的基音检测算法

作为语音信号处理领域一项基本、关键的技术,基音检测在语音信号处理中扮演着重要的角色,一直是语音信号处理的一个研究热点.首先对传统的基于短时自相关函数法的基音检测进行了研究;在此基础上提出了一种能同时检测一段语音信号基音周期的方法,有效地克服了传统基音检测算法只能检测一帧语音信号基音的缺点.进行了实验仿真,结果表明通过去野点,中值平滑等后处理的基于段的基音检测算法比传统的基于帧的基音检测算法具有更好的抗噪性.     

一种小波域音频信息隐藏方法

提出了一种基于量化的小波域音频隐藏算法，将保密语音隐藏到载体音频中．为提高隐藏重和保密语音传输的安全性，对保密语音进行了小波域压缩编码和m序列的扩频调制，生成待隐藏的比特序列；通过量化方法，将编码和调制后的保密语音隐藏到载体音频的小波系数中；保密语音的恢复过程不需要使用原始音频、仿真结果表明，隐藏有保密语音的载体音频听觉质量没有明显下降，提取的保密语音感知质量较好；该算法对重量化、加噪、低通滤波等攻击均有良好的鲁棒性．     

关于不利解释原则在保险合同中适用的探讨——评《保险法》第三十一条

介绍了保险合同不利解释原则的法理基础,探讨了保险合同中不利解释原则的适用条件,并对《保险法》第三十一条进行了评析。