HTK3.4（HTK最新版)源码 + 可执行文件 + HTK book + 其他少量HTK资料（含中文）...

VoiceAge 公司的g729编解码库-VoiceAge

用DSP进行语音压缩的经典开发实例（PCI总线)-A typical sample of developing which use DSP to compress speech signal

Demo script for testing for block-diagonalizability of real matrices

经TLV320AIC23音频编解码器，一方面送入DSP存储器，另一方面方便用户实现录音和播音-By TLV320AIC23 audio codec, on the one hand into the DSP memory, on the other hand, realize user-friendly recording and broadcasting

此文件是好将声音发送到 dsk 6700 和处理的任何声音。您可以配置此代码由 dsk 海缆无源探测格式然后通过调整可以将声音发送到 dsk 的 aic23 编解码器寄存器的端口处理它，然后回 aic23 和 dsk 的输出中听到它。它是任何一个想要使用 dsk 来学习如何初始化 dsk 的好榜样。

语音识别中的两种特征提取方法lpcc和mfcc，还有一个是文本无关的识别算法dtw，另外还有一个是预处理消噪部分的。共享一下，这些都是我调试过的，好用。-Speech Recognition two feature extraction methods and mfcc lpcc. There is a text-independent recognition algorithm dtw, in addition to a pretreatment is part of the noise source. Sharing that those are off the debugging and ease of use.

凌阳61做的语音报站，已经通过调试。-do voice stations, has passed testing. Haha

用三层小波神经网络实现的与文本无关说话人识别。（识别部分）。输入的是语音特征，输出的是识别结果。训练用的语音特征要事先提取出。-with three wavelet neural network has nothing to do with the text of Speaker Recognition. (Recognition). The admission of voice features, the output is the result of recognition. Training voice features prior to extract.

语音合成软件，包括Freephone两个模块和Mbrora

语音识别的经典文献，学习语音识别的朋友抓紧了！-Speech Recognition classic literature, studying voice recognition by grasping a friend!