改进的BP神经网络的C++源代码,可用于图象识别

LMS滤波器（最小均方误差滤波器），学习现代数字信号处理理论的人应该用的上。-LMS filter (minimum mean square error filter), learning modern digital signal processing theory should be used on.

一个基于DTW的的孤立词的语音识别系统，采用率为800，可以识别六个字左右的短语，是特定人的识别系统。运行时请更改工作目录：工程->设置->调试->更改工作目录即可-The DTW-based isolated word speech recognition system, using rate of 800, can identify words around the phrase, a specific person

语音识别（Speech Recognition）是让机器通过识别和理解过程把语音信号转变为相应的文本或命令的技术。在课题中，通过采用DTW（Dynamic time warping, 动态时间伸缩）算法，对实现孤立词的识别进行了初步探讨和研究，实现了在MATLAB软件环境下孤立词语的语音识别，并针对DTW的主要特点及不足做出了总结。-Speech Recognition (Speech Recognition) machines is through recognition and understanding of a process which put the voice signal into the corresponding text or command technology. The issue, through the use DTW (Dynamic time warping, dynamic time telescopic) algorithm to achieve an isolated word recognition conducted a preliminary exploration and study, the realization of the MATLAB software environment isolated words of Speech Recognition and DTW against the main features and deficiencies make summarized.

本程序包含语音压缩和语音识别领域所需的LPCC，MFCC特征提取算法以及语音端点检测源码。在对语音数据进行特征提取前，可对语音数据进行16K到8K的降采样率处理，包含180阶FIR滤波器的频率压缩程序

基于声音采集卡的采集源代码,并能显示波形图,做声音采集的可以借鉴.-acquisition card based on the voice of the acquisition source code, and can show that the waveform map, so voices can draw on the acquisition.

这是一个基于C++的语音识别系统,包括语音输入,识别,输出等功能-This is a C-based speech recognition systems, including voice input and recognition, output function

语音识别中提取特征向量和进行特征向量比对的DTW源代码-Speech Recognition feature extraction and feature vectors to the right than the source code DTW

智能玩具语音识别报告-A report of speech recognition of intelligent toy.

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

本文系统的介绍了语音识别的技术及其实现方法-This article introduces the technic and implement method of speech recognise