hammerstein

G.723语音编码 The source code has been modified by simplifying the ADPCM algorithm to increase running speed. Here, the quantizer scale factor, y(k), is determined by "unlocked" factor yu(k) only. The factor yl(k) and speed-contral factor al(k) are ignored.-G.723 speech coding The source code has been modified by simplifying the ADPCM algorithm to increase running speed. Here, the Quantizer scale factor, y (k), is determined by "unlocked" factor yu (k) only. The factor yl (k) and speed-contral factor al (k) are ignored.

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）-HTK3.4 (HTK latest version) source+ Executable file+ HTK book+ Other HTK a small amount of information (including Chinese)

基于语音合成法的汉语人名语音库的设计应用-Speech synthesis method based on the names of Chinese Speech Database Design and Application

使用划分注意到原来的 50 兆赫频率的脉冲发生器

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

录制音频功能，病可以对语音自动分频以及识别语音的浊音清音-Audio recording function, disease can be automatic voice recognition and voice-band voiced voiceless

基于GMM的概率神经网络PNN具有良好的泛化能力，快速的学习能力，易于在线更新,并具有统计学的贝叶斯估计理论基础，已成为一种解决像说话人识别、文字识别、医疗图像识别、卫星云图识别等许多实际困难分类问题的很有效的工具。而且PNN不但具有GMM的大部分优点，还具有许多GMM没有的优点，如强鲁棒性，需要更少的训练语料，可以和其他网络其他理论无缝整合等。-GMM based probabilistic neural network PNN good generalization ability, the ability to learn fast, easy online updates, and with the Bayesian statistical theory based on estimates, and has become a solution as speaker recognition, text recognition, medical image recognition, satellite images and other real recognition when difficulties classification of very effective tool. But GMM PNN is not only the most advantages, but also has many advantages GMM not as strong robustness, require less training corpus, and other networks to other theories, such as seamless integration.

这里主要我自己成果，是关于语音编码的，个人认为还可以，里面程序上传前经本人调试确认完全可用．有对多级矢量量化的程序（这个网上很少有），还有就是对MELP多帧参数的提取（这些网上也少见），还有就是统计子带清浊音概率的，还有一个我搜集的认为比较好的关于语音编码的英文文档．-Here the main results of my own, on the speech coding, and personally think that can also be inside the procedure before From my debugging can be used to confirm complete. There are of multi-stage vector quantization process (the online few), there is a multi-frame MELP parameters of the extraction (which are online also rare), there is statistical subband audio Qingzhuo probability, there is one I have collected think of a better speech coding on the document in English.

基于HMM的语音识别matlab软件，可防止数据溢出等错误-This speech recognition software based on HMM algorithm.It can prevent many errors such as data overflow effectively.

语音增量调制编码。deltamodulation 语音增量调制编码。deltamodulation 语音增量调制编码。deltamodulation-Voice delta modulation encoding. Voice deltamodulation delta modulation encoding. Voice deltamodulation delta modulation encoding. deltamodulation