dnn-0.1

一款语音和成软件,主要是文本转语音，包括英文、普通话等(text change to speak)

本软件在vs2010平台下实现了语音合成（Text to Speech）功能，实现将输入的文字信息转化为声音信息，同时能够选择系统语音库，调节朗读音量以及播放频率等详细参数，同时提供了编译过的exe测试程序，并可以选择测试文本信息。

对于初学者来说是一个很好的用的阅读文件,希望在数据库方面好好的阅读,(It is a good reading document for beginners. I hope to read it well in the database.)

说明：  timit语音库，包含标注文件，可以很好的用于语音识别。(timit speech database that contains annotation files, can be very good for speech recognition.)

本文主要研究普通计算环境下语音自动识别(ASR)技术的软件实时实现，基于语音识别的基本原理和过程。在VC环境下建立了一套语音识别系统及其演示软件。实验表明，该系统对特定人情况有较高的识别率和一定的实时性(In this paper, under the computing environment on general automatic speech recognition (ASR) technology to achieve real-time software, speech recognition based on the basic principles and processes. VC environment in the establishment of a voice recognition system and its presentation software. The experiments show that the systems are in particular have a high recognition rate and a certain degree of real-time)

说明：  用微软的SAPI，实现快速的语音识别。从而实现智能化。(With Microsoft' s SAPI, fast speech recognition. So intelligent.)

是一个语音识别的程序，有LPCC，MFCC等的代码，最后用SVM进行分类(Is a voice recognition program, there LPCC, MFCC and other code, the final classification with SVM)

将wav格式文件转化为txt格式的程序,用于读入语音文件转换TXT格式，便于程序分析(Wav format files into txt format program)

说明：   端点检测是指用数字处理技术来找出语音信号中的各种段落（如音素、音节、词素、词等）的始点和终点的位置。语音段起止端点检测是语音分析、语音合成和语音识别中的一个必要环节。传统的端点检测方法是从wav文件中获取语音采样，将其分帧并计算短时能量和过零率参数，然后进行端点检测。这种工作方式被称为离线处理方法 ，无法实现语音信号的实时处理，对于语音信号分析具有一定的局限性。本文通过开发ActiveX控件，在MATLAB环境下将其嵌入到figure窗口中，以GUI程序的方式使用，实现语音信号端点检测的实时处理。(Endpoint detection is the use of digital processing techniques to identify the speech signals in a variety of paragraphs (such as phoneme, syllable, morpheme, word, etc.) the starting point and the end position. Speech endpoint detection is a paragraph beginning and end speech analysis, speech synthesis and speech recognition of a necessary link. Traditional endpoint detection method is to obtain from the wav file voice sampling, its sub-frame and calculate the short-term energy and zero-crossing rate parameters, and then proceed to endpoint detection. This work is called off-line approach can not achieve real-time speech signal processing, analysis of the speech signal has a certain limitations. In this paper, through the development of ActiveX controls, in the MATLAB environment to embedded figure window to use GUI program, the realization of speech signal processing real-time endpoint detection.)

这是语音信号处理中求倒谱的程序,我自己编的,很简单,实现了一段序列求倒谱的功能(This is the voice signal processing for cepstrum procedures, I developed, is very simple. achieve a sequence for the functional cepstrum)