在语音信号处理中,基本上都采用短时声学参数。所谓短时声学参数,就是把语音按照 20~40 毫秒一帧分段处理后,通过傅立叶变换等手段,然后经过离散余弦变换降维之后的一种特征。这种特征一般输入是几百个语音采样点(20ms*8K=160),输出是 39~57 维的固定维数的特征参数,便于用于模式识别。MFCC 是一种听觉感知频域倒谱参数, 该参数从人耳对声音频率高低的非线性心理感...">
Home » Source Code » Voice MFCC feature extraction (voice recognition)

Voice MFCC feature extraction (voice recognition)

novel_foster
2015-04-07 04:28:19
The author
View(s):
Download(s): 8
Point (s): 1 
Category Category:
语音识别语音识别 CPlusPlus, C-C++C++

Description

size:16px;">在语音信号处理中,基本上都采用短时声学参数。所谓短时声学参数,就是把语音按照 20~40 毫秒一帧分段处理后,通过傅立叶变换等手段,然后经过离散余弦变换降维之后的一种特征。这种特征一般输入是几百个语音采样点(20ms*8K=160),输出是 39~57 维的固定维数的特征参数,便于用于模式识别。MFCC 是一种听觉感知频域倒谱参数, 该参数从人耳对声音频率高低的非线性心理感觉角度反映了语音短时幅度谱的特征,因此无论在语音识别还是说话人识别中都得到了极为广泛的应用。
本程序用于提取语音文件的MFCC特征参数,输入语音的sph格式文件,输出后缀名为mfc的特征参数文件。taaa.sph 为原始语音文件,taaa.mfc为输出的MFCC特征参数文件。本程序除了提取特征参数外,还包括活动端点检测( Voice Activity Detection, VAD)、 倒谱平均消去( Cepstral Mean Subtraction, CMS)、 RASTA
( RelAtive SpecTrAl)滤波、 高阶差分参数等处理过程。
 
 
 
 
 

 
Sponsored links

File list

Tips: You can preview the content of files by clicking file names^_^
Name Size Date
01.97 kB
config.txt32.00 B2013-09-04|16:29
01.97 kB
MFCC1.exe52.00 kB2015-04-07|14:51
MFCC1.ilk277.55 kB2015-04-07|14:51
MFCC1.pdb403.00 kB2015-04-07|14:51
dsrFeVad.c14.98 kB2005-10-15|11:06
dsrFeVad.h1.51 kB2005-09-13|13:14
HList.exe268.00 kB2005-08-02|10:18
01.97 kB
MFCC1.sdf2.38 MB2015-04-07|15:07
MFCC1.sln961.00 B2015-04-07|14:38
MFCC1.v12.suo16.50 kB2015-04-07|15:07
01.97 kB
dsrFeVad.obj19.05 kB2015-04-07|14:51
MFCC1.log7.46 kB2015-04-07|14:51
01.97 kB
cl.command.1.tlog1,002.00 B2015-04-07|14:51
CL.read.1.tlog3.42 kB2015-04-07|14:51
CL.write.1.tlog664.00 B2015-04-07|14:51
link.command.1.tlog1.03 kB2015-04-07|14:51
link.read.1.tlog2.73 kB2015-04-07|14:51
link.write.1.tlog308.00 B2015-04-07|14:51
MFCC1.lastbuildstate142.00 B2015-04-07|14:51
mfcc_OB_batch.obj43.56 kB2015-04-07|14:51
vc120.idb51.00 kB2015-04-07|14:51
vc120.pdb76.00 kB2015-04-07|14:51
MFCC1.vcxproj4.11 kB2015-04-07|14:51
MFCC1.vcxproj.filters1.14 kB2015-04-07|14:43
MFCC1.vcxproj.user371.00 B2015-04-07|14:44
mfcc_OB_batch.c19.32 kB2015-03-17|14:31
taaa.mfc344.00 kB2015-04-07|14:51
taaa.sph738.19 kB2009-09-02|23:00
taaa.txt758.72 kB2015-03-12|08:36
zero.txt0.00 B2015-04-07|14:51
...
Sponsored links

Comments

(Add your comment, get 0.1 Point)
Minimum:15 words, Maximum:160 words
1621202510
2016-01-21

最近在研究MFCC的特征提取,希望能够从这个代码中获得高于39维的特征。

1741768868@qq.com
2016-03-12

最近在研究MFCC的特征提取,希望能够从这个代码中获得高于39维的特征

Ann_li
2016-03-20

在做声纹特征提取,做说话人识别,cross_li@qq.com,谢谢!

yiqiu521
2016-03-31

我的总是打不开,mvcr120d。dll丢失,安装了也还是用不了,点击的不是debug里的那个mfcc么?hlist点了没用呀

zjyzjy1
2017-03-27

我也先下一个试试看,不知道能不能用

  • 1
  • Page 1
  • Total 1

Voice MFCC feature extraction (voice recognition) (1.68 MB)

Need 1 Point(s)
Your Point (s)

Your Point isn't enough.

Get 22 Point immediately by PayPal

Point will be added to your account automatically after the transaction.

More(Debit card / Credit card / PayPal Credit / Online Banking)

Submit your source codes. Get more Points

LOGIN

Don't have an account? Register now
Need any help?
Mail to: support@codeforge.com

切换到中文版?

CodeForge Chinese Version
CodeForge English Version

Where are you going?

^_^"Oops ...

Sorry!This guy is mysterious, its blog hasn't been opened, try another, please!
OK

Warm tip!

CodeForge to FavoriteFavorite by Ctrl+D