基于神经网络的说话人识别

语音识别专辑六- Speech recognition special edition six

模式识别中的联机字符识别，包括联机手写数字识别和联机数字、英文字符及汉字识别算法实现源代码-pattern recognition of Character Recognition on-line, including on-line handwriting recognition and on-line digital figures English characters and character recognition algorithm source code

基于ADSP TS201S的LMS算法-Based on the LMS algorithm ADSP TS201S

tone encode and decode

Microsoft agent示例源程序，必须安装了Microsoft agent2.0以上 -Microsoft the agent demonstration source program, must install above Microsoft agent2.0

检测语音信号的共振峰 ％ gender = gender_detector(X,Fs) ％ ％ This function will use a pitch detection algorithm to decide if the speaker is MALE(0) or FEMALE (1). ％ It is designed to work with short speech samples (up to or greater than 50 ms). The function returns a ％ 0 if X contains male speech and a 1 if it contains female speech. -the resonance peak gender_detector% gender = (X, Fs)%% This function will use a detection a pitch lgorithm to decide if the speaker is abbreviation (0) or F EMALE (1). % It is designed to work with short spe ech samples (up to or greater than 50 ms). The fun ction returns a 0% if X contains a male speech and if it contains a female speech.

一个HMM的Matlab实现方法，可实现孤立词语音识别-The Matlab realize a HMM method can realize an isolated word speech recognition

本代码为基于windows的语音识别系统的源码。-code for the Windows-based voice recognition system source code.

玩语音，，，， 玩语音，，，， 玩语音，，，，玩语音-play voice, and, playing with voice, and, playing with voice, and, playing with voice, and, playing with voice,,,, play voice, and, playing with voice

自适应量化。读取wav文件，使用2到12比特量化。抽样频率8khz-Adaptive quantization. Read wav files, using 2-12 bit quantify. Sampling frequency of 8kHz