资源列表
taShift
- 语音合成 利用miscrosoft sdk 实现语音合成的程序源码-Speech synthesis miscrosoft sdk speech synthesis program source code
yuyinshiyutezheng
- 对语音信号进行处理时需要提取各种特征参数,本程序时对语音信号各种时域特征的描述。-Need to extract the characteristic parameters of the speech signal processing, a descr iption of the voice signal a variety of time-domain characteristics of this program.
project2005
- array processing for speech enhancement
DOA
- array processing for speech enhancement
p3
- noise ration in speech detection
Program
- 语音识别,使用单片机对非特定人的声音进行语音识别。-Speech recognition
Speech-Test
- 通过speech sdk 5.1实现语音识别,根据说明文档中的例子编写,应该会有点帮助-Speech recognition through speech the sdk 5.1, prepared according to the examples in the documentation, should be a little help
MFCC_VQ
- 基于非特定人的语言识别算法,采用矢量量化的方法能够较简单的实现语音的识别。-Based on the non specific human speech recognition algorithm, using vector quantization method is a simple implementation of speech recognition.
TextToVoice
- 改程序演示了利用windows的语音系统,将文本转化成语音-this pro show the method how the text can be translate the voice
yuyinshibiejishuyanjiu
- 有关语音特征提取的一篇博士论文,讲的十分详细-mvdr mfcc lpc
HwAudioRec
- 一种实时语音录音装置代码,课调用系统安排api也可调用声卡驱动函数来进行语音的采集和编码-A real-time voice recording device code, the class call the system arrangements APIs can also call the sound card driver function to the acquisition and encoding of the voice
yuyinxinpian
- 实现洗衣机的语音录放功能 已经实际验证 可以运行-xiyiji sound lufang