9.2 基于广义互相关的声源定位

短时平均能量和平均幅度差函数进行基音检测的方法(Short-term average energy and average magnitude difference function pitch detection method)

基于HMM的语音识别算法和毕设例程，包括数据。(HMM-based speech recognition algorithm and complete routine, including data.)

提取语音信号的lpc参数并进行时间归整，需要将wav语音文件放在指定目录下‘e:yyzl’(voice signal from the lpc parameters and time consolidation, need to wav sound files on the specified directory 'e : yyzl')

说明：  基于CRF的中文机构名识别系统。使用北京大学1998年的人民日报语料库作为训练语料。除常用的特征模板，已经词性特征外，使用词语的最后一个字作为特征，提高了机构名识别的准确率, 调用了CRF++程序包训练模型。(CRF-based name recognition system of Chinese institutions. People' s Daily, Peking University in 1998 with corpus as training data. In addition to the characteristics of commonly used templates, has been part of speech features, the last word to use words as features and improve the organization name recognition accuracy, call the CRF++ package training model.)

利用GMM训练模型，并用于说话人识别等相关领域，有不错的效果(GMM apply for text to speech)

自制DMX512控制台,很不错的一个软件,他对灯光的控制,非常出色.(Homemade DMX512 console, a very good one software, he lighting control, very good.)

语音压缩感知，观测矩阵采用混沌序列，稀疏字典采用KSVD训练得到。(compressed sensing with chaotic sequence and K-SVD )

一款语音和成软件,主要是文本转语音，包括英文、普通话等(text change to speak)

编写一Matlab函数，用30ms三角窗和15ms帧移计算语音信号的STFT。并用OLA法重建原始信号。设计一种基于OLA的综合方法，以通过重复每帧对语音信号以因子2进行时域扩展。(Write a Matlab function, STFT and 30ms triangular window and 15ms frame-shift calculation of the speech signal. And the OLA method to reconstruct the original signal. Design an integrated approach based on OLA, by repeating each frame of the speech signal by a factor of 2 when the domain extension.)

speaker recognition using MFCC GMM EM