网站首页

登录

35973510VAD-DTW-HMM

于 2017-12-14 发布文件大小:531KB

 0  294

下载积分: 1 下载次数: 12

我要下载

代码说明：

基于动态时间规整与隐马尔科夫模型的自动语音识别系统(Automatic speech recognition system based on dynamic time warping and hidden Markov model)

文件列表：

ch13
ch13\cdhmm
ch13\cdhmm\baum.m, 1511, 2001-11-12
ch13\cdhmm\getparam.m, 1990, 2002-02-28
ch13\cdhmm\hmm.mat, 63856, 2001-11-12
ch13\cdhmm\inithmm.m, 1266, 2002-02-28
ch13\cdhmm\main.m, 165, 2001-11-13
ch13\cdhmm\mfcc.m, 859, 2001-11-09
ch13\cdhmm\mixture.m, 357, 2001-11-11
ch13\cdhmm\pdf.m, 230, 2001-11-10
ch13\cdhmm\recog.m, 255, 2001-11-13
ch13\cdhmm\samples.mat, 630000, 2001-11-12
ch13\cdhmm\train.m, 839, 2001-11-13
ch13\cdhmm\vad.m, 1855, 2001-11-09
ch13\cdhmm\viterbi.m, 1026, 2001-11-11
ch13\dtw
ch13\dtw\dtw.m, 494, 2001-11-09
ch13\dtw\dtw2.m, 1648, 2001-11-09
ch13\dtw\mfcc.m, 859, 2001-11-09
ch13\dtw\testdtw.m, 647, 2001-11-09
ch13\dtw\vad.m, 1855, 2001-11-09
ch13\record
ch13\record\record.fig, 19008, 2001-11-12
ch13\record\record.m, 3974, 2001-11-12
ch13\record\sample.m, 147, 2001-11-12
www.pudn.com.txt, 218, 2007-01-22

下载说明：请别用迅雷下载，失败请重下，重下不扣分！

发表评论

0 个回复

tibaoluo
基于倒谱短时部分反映了语音的声道特性，先用汉明窗取一帧语音，然后经变换得到语音倒谱，将倒谱短时部分取出，进行正交反变换后将得到声道的对数谱，即得到语音频谱的包络。将频谱包络和频谱画在一张图上，有很好的对比效果。获取的包络效果十分好。(Based Cepstral partly reflects the short channel characteristics of the speech, first take a Hamming window with a frame of speech, and speech cepstrum obtained by converting the cepstrum short segment out inverse orthogonal transform to obtain channel will of the spectrum, i.e. to obtain the envelope of the speech spectrum. The spectral envelope and spectral painted on a chart, there is a good contrast. Get the envelope effect is very good.)

2013-11-01 14:13:17下载

积分：1
EM_init_kmeans
高斯混合模型参数初始化程序，在对高斯混合模型的建立之前采用KMEANS算法进行初始化(Gaussian mixture model parameter initialization procedure, in the Gaussian mixture model is initialized before the algorithm used KMEANS)

2010-11-18 20:28:33下载

积分：1
HHT
HHT变换，经验模态分解，时变频率与阻尼的模式提取(HHT transform, empirical mode decomposition, extraction of time-varying model)

2020-08-18 11:18:23下载

积分：1
ld3320
LD3320 是一颗基于非特定人语音识别（SI-ASR：Speaker-Independent Automatic Speech Recognition）技术的语音识别/声控芯片。提供了真正的单芯片语音识别解决方案。 LD3320 芯片上集成了高精度的A/D 和D/A 接口，不再需要外接辅助的 Flash 和RAM，即可以实现语音识别/声控/人机对话功能。并且，识别的关键词语列表是可以动态编辑的。(Voice Recognition ；Speech Recognition ；Speech recognition technology )

2011-08-19 22:47:10下载

积分：1
OLA
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.)

2012-04-18 10:49:23下载

积分：1
word_to_sound
用c编写的文字转化成声音的程序,可以把该程序移植到单片机和其他嵌入式处理器中.实现应有的功能.(With c prepared text into sound procedures, the program can be transplanted into single-chip and other embedded processors. Realize the function.)

2007-08-08 15:33:04下载

积分：1
quzao
基于谱减法的语音降噪处理，里面有声音文件，可以直接运行观察效果(Based on the spectral subtraction speech denoising processing, there are sound files, can be run directly observed effect)

2020-07-04 19:00:01下载

积分：1
main
对语音信号基频的提取对于语音信号的分析有一定作用(Basic frequency of speech Analysis )

2014-05-22 12:28:43下载

积分：1
35973510VAD-DTW-HMM
基于动态时间规整与隐马尔科夫模型的自动语音识别系统(Automatic speech recognition system based on dynamic time warping and hidden Markov model)

2017-12-14 20:49:03下载

积分：1
programme
一个LMS自适应信号增强。输入信号是一个正弦波将白噪声。详细介绍了程序源代码(An LMS adaptive signal enhancement. The input signal is a sine wave with added white noise. The detailed description is in the program source code)

2010-05-17 16:27:14下载

积分：1

696516资源总数
106914会员总数
0今日下载