科大讯飞语音识别引擎

直接对语音信号进行频谱搬移，得到转换后的语音，男声发生了变化。-Directly to the voice signal spectrum move, to be converted voice, male voice has changed.

语音识别与合成系统. 里面有详细的介绍与程序-Speech Recognition and Synthesis System. There are a detailed introduction and procedures

语音识别与合成入门3，word或压缩包中内有matlab源码-speech recognition and synthesis 3 entry, word or compressed packages within Matlab FOSS

实现了语音回放功能，很不错的-Realized the voice playback, it is good

语音信号处理方面的源代码，简单的语音合成软件（text to speech）-voice signal processing of the source code, a simple speech synthesis software (text to speech)

MPEG4音频编码器的源码，主要供从事音频/语音编/解码工作的朋友参考

语音信号处理中基音检测源程序，用matlab实现的。主要应用了改进的自相关技术。-Pitch detection in speech signal processing source code, using matlab be achieved. Major applications to improve the self-related technologies.

有趣的语音识别程序，可以利用这个程序实现语音防盗门。是根据每个人不同的声调来实现的-interesting voice identification procedures, we can use this procedure voice security doors. Everyone is different tone to achieve the

该程序是非特定人语音识别程序，原来在SPCE500A下运行，能识别并应答16个命令，存储空间为128K字节。 //我们将其进行了修改，使其能在SPCE061A下运行，由于存储空间为32K字，只能识别并应答9个命令。 //在这个例程当中，我们示范了如何使用语音识别引擎对8个已经经过训练的命令进行识别。 //第一个命令 "Snoopy"，可以作为使能命令，也就是说使用者只能在该命令之后发出其他命令。 //例如，用户只有在发出 "Snoopy"命令并且听到响应"Snoopy here"之后才能继续下达其他命令 //如"How are you", "I love you",等等。 //当"Snoopy"命令响应之后，程序将等待8秒钟，如果没有其他命令发出， //系统将跳回到第0组，并且再次等待触发命令"Snoopy"。当用户的命令无法被识别时， //程序将响应为"Execuse me?", "I can t hear you!"或 "Say again!"这时用户可以再一次下达语音命令。-the procedures were non-specific voice recognition procedure, the original run in SPCE500A can identify and Response 16 orders, storage space for 128K bytes.// We had to amending it so that it can run in SPCE061A, storage space for 32K words, recognize only nine responses and orders.// This routine, we have demonstrated how to use voice recognition engine has eight pairs of trained orders for identification.// The first order "Jack Champion", as it can make an order, users can only say in the order issued after other orders.// For exampl

This code is used to remove silence from a voice signal so that the recognition in voice recognition will give good result. The method is Scale on threshold applied to the envelope for detecting scilence periods. The actual threshold is computed by multiplying threshin" by the median value of the envelope samples. The default is (.25), whichis 25 of the median envelope value over input signal .-This code is used to remove silence from a voice signal so that the recognition in voice recognition will give good result. The method is Scale on threshold applied to the envelope for detecting scilence periods. The actual threshold is computed by multiplying threshin" by the median value of the envelope samples. The default is (.25), whichis 25 of the median envelope value over input signal .