资源列表
AudioAecDemo
- 音频聊天的源代码,能够实现语音通话,比较流畅-Audio chat source code, to achieve a voice call, more fluid
TTS
- 本人做的一个TTS阅读器,还没完全成功~-~!希望对你们有所帮助!
back10_voice
- 语音检测,判断两个通道的声音是否一样,如果一样,就不切换,不一样切换到备用通道-Voice detection
mfcc
- 语音信号的初始化及MFCC特征提取算法,附带测试用语音信号-Voice signal and the initialization MFCC feature extraction algorithm, with test speech signal
HTS full context label
- HTS full context label
ozi
- b,vjhv hvvubuf jbjb/db jbjhbhvd
subspace_and_noisy_speech
- 文件中包括:1.Yariv Ephraim和Yi Hu分别提出的两种信号子空间语音增强法;2.白噪声带噪语音和粉红噪声带噪语音,可用于子空间语音增强法试验。具体说明见文件中的说明。
mfcc
- 本文件包含语音识别语音识别中一些算法,加框处理的算法,以及进行mfcc和倒谱的算法,用matlab算法实现。另外还包含一个音频文件。-This document contains the speech recognition in a number of speech recognition algorithms, the algorithm deal with framing, as well as cepstrum mfcc and the algorithm implementation
lpc
- LPC系数使用matlab实现的算法,比较经典。-LPC coefficients using the matlab implementation of the algorithm, more classic.
smapi-developers-guide
- ibm 的 smapi 用于语音识别的开发-ibm smapi developers guide
codes
- 基于DTW算法的孤立词语音识别,可识别0-9-DTW-based isolated word speech recognition algorithm can recognize 0-9
myRBF
- 用于语音识别中语音特征的训练网络,其中的输入文件为你的特征存储地址,和训练出的特征的目标位置,其它的不需要改变-for speech recognition voice characteristics of the training network, the input of your document storage feature address, training and the characteristics of the target, the other need not chang