一种HMM训练的源程序，调试可以通过，说明比较详细

关于语音识别和语音合成的代码。 可以试试啊-On speech recognition and voice synthesis code. Try ah

基于WINDOWS的SVM的开发工具，特别适合初学者，不需要太了解SVM原理-SVM based on the Windows development tool, especially for beginners, SVM not understand much about Principle

一个VQ语音识别代码 自己写的 十分有用来分享下-A VQ speech recognition to write code themselves have used to share the very next

此文件为martin谱减法的matlab程序以及自己加入的中文注解，希望对研究martin的算法的同学有帮助-This document is for martin s matlab spectral subtraction procedures, as well as adding their own comments in Chinese, I hope the study of algorithms for martin help students

智能玩具语音识别报告-A report of speech recognition of intelligent toy.

MFCC 参数和 LPCC 参数是说话人识别中两种最常用的特征参数，研究了 MFCC 和 LPCC 参数提取的算法原理及差分倒谱参数的提取方法，采用MFCC、LPCC 及其一阶、二阶差分作为特征参数，通过 k 均值算法与三层BP 神经网络来进行说话人识别。实验结果表明，该方法可以有效提高识别率，同时也验证 MFCC 参数的鲁棒性优于 LPCC 参数

一个很不错的语音识别软件，包含了使用前必读，希望对大家有帮助。-a very good voice recognition software includes the mandatory use of the former, and I hope to be helpful.

G.729音频压缩传输协议（ip电话）,ITU的G.729语音压缩编码标准。-G.729 audio compression and transmission protocol (ip phones) The ITU G.729 voice compression standards.

本文主要叙述了语料及其管理系统的研究与设计用最新的开发工具和现有软件达到系统的设计 目标-This paper describes the corpus and its management system research and design using the latest development tools and existing software system to achieve the design goal

非线性量化。读取wav文件，用2到12比特数量化。抽样频率8KHz。