基于LPC的藏语语音基音周期的检测分析

基音周期是语音信号的重要参数,提取藏语语音基音周期为藏语语音识别和藏语语音合成奠定很重要的基础。这里在分析藏语发音特点的基础上进行基于LPC的藏语语音基音周期提取算法的分析,实践表明,该方法更加符合小信噪比藏语音信号基音周期和提取。在传统LPC分析方法的基础上结合自相关法和倒谱法,分析计算平均相对误差,总结出了符合藏语语音特点的特征提取算法。     

基于Praat的藏语连续语音参数提取仿真和分析

藏语语音信号处理是藏语语音实现人工智能化的关键技术之一。自然人的语音发音和直观判断与实际的发音规则存在一定的差异。客观地量化分析藏语连续语音中的特征参数,能够更客观更精确的反应语音的发音规律。介绍了Praat语音分析软件及其在语音处理研究和语音教学中的应用;用Praat语音处理软件平台仿真和分析了藏语连续语音录音句子中的语音强度、语调、频谱特征、基音轨迹等声学参数,为藏语连续语音信号处理、藏语发音和听力教学提供参考依据。     

改进型LPC声码器语音编码算法

本文给出了一种改进的ＬＰＣ语音编码算法，用于实现低速率声码器。与传统ＬＰＣ声码器算法相比，本算法在参数提取及合成等方面采取了一些改进措施，使得合成语音质量有很大的提高。本文在引言后概述了编码算法改进的考虑，然后给出编译码器的算法，重点讨论了本文提出的用动态规划法进行基音提取和平滑的新算法，以及合成端混合激励算法。本算法已经用ＴＭＳ３２０Ｃ２５实现单片编解码。     

基于LPC倒谱的语音特征参数提取

语音识别指利用计算机识别语音信号所表达的内容,其目的是要准确地理解语音所蕴含的含义。本文着重研究了语音识别实现过程的特征提取,针对特征提取的多种方法,选用LPC倒谱系数作为特征参数提取,较彻底地去除了语音信号产生过程的激励信息,主要反映了声道模型,而且只需十几个倒谱系数就较好地描述了语音的共振峰特性。通过对语音信号进行预加重、分帧、加窗、自相关分析,而后提取出LPC倒谱系数。根据流程编写VC程序,对语音信号进行分析处理,去除对语音识别无关紧要的冗余信息,从而获得用于语音识别的重要信息。     

藏语语音处理中对MFCC参数提取的研究

本文在掌握了MFCC参数提取的理论基础上,对基元的选择、HMM建模进行了深入学习与探索,在HTK工具的帮助下完成了MFCC参数的提取,为藏语语音识别系统、藏语语音合成系统的实现奠定了一定的基础。     

用于分布式识别的语音参数的提取和性能分析

主要研究用于分布式语音识别(DSR)的语音参数的提取方法以及参数性能分析。以前所用到的语音参数大部分是LPC例谱参数，但其抗噪声性能较差。文中主要讨论了MEL倒谱参数。并在移动通信环境下，比较了两者的性能。     

基于Matlab的藏语语音基音检测算法研究

目前藏语语音基音检测算法相关研究较少,藏语语音基音检测是藏语语音处理过程中的重要环节,其准确性直接影响到系统的性能。介绍中心消波和自相关函数的算法原理及基音检测算法,设计藏语语音基音检测流程,利用Matlab进行编程和仿真。通过实验表明该算法结构简单、运算量小,结果较准确,可用于信噪比较低环境下藏语语音辅音的基音估值检测。     

基于LPC模型的DTW语音转换系统设计

文章重点研究了基于LPC模型的DTW语音转换方法.采用DTW技术进行模型特征参数对齐的优势是:经过数据对齐后,使得人工神经网络算法更好的训练特征参数,得到的映射规则能很好规范要转换的特征参数,使得语音转换质量更高.论文的仿真结果和数据分析表明,基于LPC模型的DTW语音转换系统转换出的语音自然度较高.该研究结论对于语音...     

基于VMD的智能机器人语音信号特征参数提取方法

提取智能机器人语音信号特征对于确保机器人正常运行有关键性意义。为了有效缩短特征参数提取时间,提高提取准确率,提出了基于VMD的智能机器人语音信号特征参数提取方法。利用VMD技术建立语音信号的脉冲数字模型,分析实时性系统频率,确定信号传递函数。采用VMD特有的分子程序化模式,将智能机器人作为大型生物分子来进行语音信号的特征参数分析,建立分子可视化程序,将不稳定的语音信号拆散开进行分析处理。生成自相关系数,进而通过傅里叶变换将自相关系数转变为LPC系数,通过数据分析处理生成线性预测倒谱系数,经过VMD分子可视化进行提取,得到了智能机器人的语音信号特征参数。实验结果表明,基于VMD的智能机器人语音信号特征参数提取方法能够通过加窗处理解决外部冲击问题,提高检测准确率,缩短特征参数提取时间,确保机器人正常工作。     

语音识别中的统计语言模型研究

就语音识别中所用到的语言模型进行了详细阐述,对语言模型中涉及到的N-gram模型进行了解析,以及对在训练语言模型过程中遇到的零概率问题相应的平滑处理方法进行了讲解。利用N-gram训练的语言模型运用到语音识别中,取得了相当好的效果。     

JND's in the LPC poles of speech and their application toquantization of the LPC filter

For the purpose of guiding a pole quantization scheme, a psychophysical experiment was performed to measure just-noticeable differences (JND) in the frequency and radius of the poles. The frequency JNDs, measured up to a formant frequency of 4 kHz, are quantified as distributions with means that are increasing functions of formant frequency and bandwidth. An example of a pole quantization scheme, based on the JND data, is presented and found to be significantly superior to common scalar quantization methods of the LPC-PARCOR coefficients. The pole quantization scheme is found to be almost comparable, both in quality and bit consumption, to vector quantization     

Adaptive block transform coding of speech based on LPC vectorquantization

The authors describe several adaptive block transform speech coding systems based on vector quantization of linear predictive coding (LPC) parameters. Specifically, the authors vector quantize the LPC parameters (LPCVQ) associated with each speech block and transmit the index of the code vector as overhead information. This code vector will determine the short-term spectrum of the block and, in turn, can be used for optimal bit allocation among the transform coefficients. In order to get a better estimate of the speech spectrum, the authors also consider the possibility of incorporating pitch information in the coder. In addition, entropy-coded zero-memory quantization of the transform coefficients is considered as an alternative to Lloyd-Max quantization. An adaptive BTC scheme based on LPCVQ and using entropy-coded quantizers is developed. Extensive simulations are used to evaluate the performance of this scheme     

语音信号线性预测模型中的激励源

本文主要阐述了语音线性预测编码中描述声道特性的全极点预测滤波器的几种激励方式,即残余信号激励,多脉冲激励及音调激励的原理和有关性能。对基带提取—高频再生残余信号的激励方式亦作了相应的介绍。     

Multilinguality in speech and spoken language systems

Building modern speech and language systems currently requires large data resources such as texts, voice recordings, pronunciation lexicons, morphological decomposition information and parsing grammars. Based on a study of the most important differences between language groups, we introduce approaches to efficiently deal with the enormous task of covering even a small percentage of the world's languages. For speech recognition, we have reduced the resource requirements by applying acoustic model combination, bootstrapping and adaption techniques. Similar algorithms have been applied to improve the recognition of foreign accents. Segmenting language into appropriate units reduces the amount of data required to robustly estimate statistical models. The underlying morphological principles are also used to automatically adapt the coverage of our speech recognition dictionaries with the Hypothesis-Driven Lexical Adaptation (HDLA) algorithm. This reduces the out-of-vocabulary problems encountered in agglutinative languages. Speech recognition results are reported for the read GlobalPhone database and some broadcast news data. For speech translation, using a task-oriented Interlingua allows to build a system with N languages with linear, rather than quadratic effort. We have introduced a modular grammar design to maximize reusability and portability. End-to-end translation results are reported on a travel-domain task in the framework of C-STAR     

Robust LPC parameter estimation in standard CELP 4800 bit/s speechcoder

In order to decrease LPC spectral degradation in the USA FED STD 1016 4.8 kbit/s CELP speech coder, application of a robust LPC parameter estimation is proposed. Robust LPC methods, based on Huber's M-estimation theory and a heuristic sample-selective two-stage robust procedure, are considered. Comparative experimental analysis is carried out based on the cepstral distance, as an objective spectral measure. Presented experimental analyses justify the use of the robust LPC methods in the standard CELP 4800 bit/s speech coder, showing that the best results are obtained by using the combined sample-selective robust LPC procedure     

LPC与LSF转换算法的比较研究

线性预测法是语音信号处理中的核心技术。在语音信号的处理中,常常需要将线性预测的LPC系数与LSF参数相互转换。本文根据Chebyshev多项式求根法,研究了几种由LPC求解LSF的算法,分析了它们各自的特点及相互关系。分析并推导了由LSF求解LPC的算法。     

氮化镓功率器件小信号模型参数提取算法研究

针对氮化镓高电子迁移率晶体管(GaN High Electron Mobility Transistor,GaN HEMT)小信号等效电路模型参数提取和优化过程中存在的误差累计问题,基于GaN HEMT 19元件小信号模型,提出了一种扫参与迭代相结合的参数提取算法.该算法在迭代过程中,每次使用比前一次更准确的元件值进行计算,可使结果趋向最优解.通过Mat-lab编程实现后计算结果表明,仿真与实测S参数在0.1～40 GHz频率范围内吻合良好.