GMM-apply-for-text-to-speech

这 里主要对LMS算法及一些改进的LMS算法（NLMS算法、变步长LMS算法、变换域LMS算法）之间的不同点进行了比较，在传统的LMS算法的基础上发 展了LMS算法的应用。另一方面又从RLS算法的分析中对其与LMS算法的不同特性进行了比较。(Here mainly on the LMS algorithm and some improvements of the LMS algorithm (NLMS algorithm, variable step size LMS algorithm, transform domain LMS algorithm) between the different points of comparison, in the traditional LMS algorithm developed on the basis of the application of the LMS algorithm. On the other hand from the analysis of RLS algorithm and LMS algorithm for its different characteristics compared.)

做毕设是用到的gmm的matlab程序，测试过的 ，绝对可以用(Complete set is used to do the matlab program gmm, tested, can surely be)

语音增强算法，基于人耳听觉掩蔽的维纳滤波(Subspace speech enhancement algorithm based on human auditory masking Wiener filter)

一种用于语音或者心音去噪和提取包络的预处理方法，对于后面信号处理更加方便(A method for denoising and extract voice or heart sounds envelope pretreatment method, the signal processing is more convenient for the latter)

基于最小均方误差的助听器语音去噪算法, 用于以最大程度消除助听器接受的语音杂音.(Speech denoising algorithm based on the minimum mean square error of a hearing aid for the hearing aid acceptable voice murmur eliminated to the greatest extent.)

基于熵的端点检测算法，比传统的端点检测能更精确的检测出端点(endpoint detection algorithm than the traditional endpoint detection more accurate detection of Endpoint)

求语谱图的matlab程序，非常有用(Spectra for the matlab language program, very useful)

Chapter 2 Low Bit-Rate Speech Coding In this chapter an overview is given of speech coding techniques at several bit rates. Most of them use Linear Prediction. This overview is not meant to be complete its purpose is to make the reader somewhat familiar with Linear Predictive Coding which is necessary for a proper understanding of later chapters. Section 2.1 treats the subject of quantisation and coding. In section 2.2 a description of speech production and speech sounds is given. Coders based on linear prediction can be considered as being based on a simple speech production model. This model is explained in section 2.3. Section 2.4 describes various speech coding algorithms and techniques. Section 2.5 briefly describes some measures for the quality of coded speech.(In this chapter an overview is given of speech coding techniques at several bit rates. Most of them use Linear Prediction. This overview is not meant to be complete its purpose is to make the reader somewhat familiar with Linear Predictive Coding which is necessary for a proper understanding of later chapters. Section 2.1 treats the subject of quantisation and coding. In section 2.2 a description of speech production and speech sounds is given. Coders based on linear prediction can be considered as being based on a simple speech production model. This model is explained in section 2.3. Section 2.4 describes various speech coding algorithms and techniques. Section 2.5 briefly describes some measures for the quality of coded speech.)

在evmdm642平台下的一个语音采集-回放任务，用48K/秒的采样率采集立体声音频输入，用给定的FIR 滤波参数处理数据后再播放出来。注：内附个人整理的详细操作文档。(evmdm642 platform in a speech to the gathering-intervals task with 48 K/s sampling rate Acquisition stereo audio input, used to the FIR filter parameters for data processing later. Note : with a detailed personal finishing operations documentation.)

iLBC Speech Coder ANSI-C Source Code WebRtcIlbcfix_CbSearch.h.