基于cdhmm的噪声环境下口令识别方法研究-信号与信息处理专业论文.docxVIP

基于CDHMM的噪声环境下口令识别方法研究摘 基于CDHMM的噪声环境下口令识别方法研究 摘 要 f语音识别系统的噪声鲁棒性是决定语音识别技术从实验室走向实际应用的 关键环节，是目前语音识别领域的研究热点与难点。由于语音识别系统是一种 基于训练的系统，实际应用环境与形成系统参数的训练环境噪声的失配是造成 系统性能下降的主要因素。你文建立了一个基于CDHMM的汉语口令识别系统， 以此为基础，从选择强噪声鲁棒性的语音特征参数，及对模型参数的补偿与修 正等方面，对加性平稳背景噪声环境下的短语音汉语口令识别方法进行了研究。 本文的研究内容包括以下几方面： 1．建立了一个汉语口令短语音识别系统过程，在此过程中研究了HhlM参数 的训练问题。 2． 分析讨论了训练状态数和混合度的最佳选取问题，通过大量实验得到了 适合子汉语短语音(口令)的最佳状态数和混合度。 3．深入研究和分析了参数级的抗噪问题，通过实验分析比较了静态特征参 数以及高阶动态参数之间的抗噪性能，得出了一般噪声环境下性能相对 较好的特征参数形式。 4．在语音特征参数级去噪的基础上，提出了一种基于H删和倒谱特征的噪 声补偿方法，通过对纯净环境下的模型参数的补偿与修正，实现训练环 境与测试环境的匹配。(通过实验验证了该方法的可行性，并将模型级抗 噪与参数级抗噪结合起来，实现了系统较好的噪声鲁棒性。{ 关键词 隐马尔可夫模型；特征参数，、噪声鲁棒性i状态数，、口令识别 STUDY STUDY ON CDHMM．BASED CHINESE PASSWORD RECOGNITION IN NOISY ENVIROMENTS ABSTRACT The noise robustness is one of the crucial factors that have deep influence upon the practicability of the speech recognition system，and then it has become the focus in the research field of automatic speech recognition．Because the speech recognition system is training—based，its performance will degrade drastically when the characteristic of noise in practical environments is far from that of in training environments．In this dissertation，we constitute a Chinese password recognition system based on CDHMM．Serials of techniques like choosing the robust features， amending recognition models and compensating the parameters of models are presented． The main content and results of study involved in this dissertation are divided into four parts： Firstly,we establish a Chinese password recognition system based Oil CDHMM and research into the training problem ofHMM parameters． Secondly,to optimize the system’S seRings，some important issues about the recognition of short-term speech recognition are discussed，such as the state number ofMarkov chains，the scale oftraining-set，the Gauss mixture number,etc． Thirdly,we have deeply studied the noise-restrained parameters．With lots of experiments，the capability of static state parameter and dynamic parameter are compared，and then the better pa