Speaker Recognition

所属分类:语音合成
开发工具:matlab
文件大小:7758KB
下载次数:0
上传日期:2018-12-25 01:32:23
上 传 者gowda123
说明:  Speaker

文件列表:
Speaker Recognition\1.bmp (11382, 2011-12-09)
Speaker Recognition\bleep2.wav (6584, 2012-03-02)
Speaker Recognition\Copy of scom.m (159, 2011-05-20)
Speaker Recognition\disteu.m (850, 2012-01-25)
Speaker Recognition\divim.m (0, 2011-06-14)
Speaker Recognition\Finally_version1.pdf (469974, 2010-12-27)
Speaker Recognition\hs_err_pid2984.log (16518, 2011-01-06)
Speaker Recognition\m1.asv (728, 2011-03-17)
Speaker Recognition\match.m (0, 2013-01-22)
Speaker Recognition\melfb.asv (1898, 2011-02-10)
Speaker Recognition\melfb.m (1889, 2010-12-11)
Speaker Recognition\mfcc(.m (0, 2013-01-16)
Speaker Recognition\mfcc.asv (1458, 2011-05-20)
Speaker Recognition\mfcc.m (1478, 2011-04-22)
Speaker Recognition\MFCC.pdf (198809, 2001-12-31)
Speaker Recognition\Mine.asv (1224, 2011-05-05)
Speaker Recognition\Mine.m (1665, 2011-05-05)
Speaker Recognition\Mine2.asv (1040, 2011-12-09)
Speaker Recognition\Mine2.m (1025, 2011-12-12)
Speaker Recognition\mydistance.m (846, 2009-11-20)
Speaker Recognition\pgm.asv (763, 2012-03-01)
Speaker Recognition\pgm.m (755, 2012-03-01)
Speaker Recognition\s.m (646, 2010-12-31)
Speaker Recognition\s1.wav (25132, 1999-06-09)
Speaker Recognition\scom.m (288, 2017-05-30)
Speaker Recognition\scom11.m (161, 2011-05-20)
Speaker Recognition\sig proc\111.txt (1143, 2012-08-27)
Speaker Recognition\sig proc\222.txt (1005, 2012-08-27)
Speaker Recognition\sig proc\Agarwal Shweta S.pdf (864901, 2012-08-27)
Speaker Recognition\sig proc\ans1.doc (33280, 2012-08-27)
Speaker Recognition\sig proc\ans2.doc (26624, 2012-08-27)
Speaker Recognition\sig proc\digital comm.pdf (1501477, 2012-08-27)
Speaker Recognition\sig proc\functions_by_package.php.htm (1045914, 2012-08-27)
Speaker Recognition\sig proc\functions_by_package.php_files\fixed.js (172, 2012-08-27)
Speaker Recognition\sig proc\functions_by_package.php_files\javascript.js (2545, 2012-08-27)
Speaker Recognition\sig proc\functions_by_package.php_files\oct.png (5578, 2012-08-27)
Speaker Recognition\sig proc\functions_by_package.php_files\octave-forge.css (9815, 2012-08-27)
Speaker Recognition\sig proc\functions_by_package.php_files\sflogo.png (469, 2012-08-27)
Speaker Recognition\sig proc\gauspuls.html (56910, 2012-08-27)
... ...

Copy all files in Matlab current directory and type "speakerrecognition" on Matlab command window. After unzipping the file correctly, you will find two folders, TRAIN and TEST, each contains some files, named: S1.WAV, S2.WAV, …, ; each is labeled after the ID of the speaker. These files were recorded in Microsoft WAV format. In Windows systems, you can listen to the recorded sounds by double clicking into the files. You can use the sound files present in "TRAIN" to create the database of known speakers and use sound files present in "TEST" in order to evaluate the automatic recognizer. Note that sounds should have the same sampling frequency and this value has to be consistent with the size of frame window: 256 samples should have a duration of about 30 ms: this is achieved using a sampling frequency of about 12500. If this condition is not satisfied you have to re-sample input sound (you can use "resample" Matlab command) or, equivalently, change windowing parameters for filtering. This code is based on Amin Koohi's excellent submission available at http://www.mathworks.com/matlabcentral/fileexchange/loadFile.do?objectId=8802&objectType=FILE and improves results using an advanced metric for distance computation. In this way a better recognition rate is achieved. For the complete source code please visit http://www.advancedsourcecode.com/speaker.asp For any question please email me luigi.rosa@tiscali.it Luigi Rosa Via Centrale 35 67042 Civita Di Bagno L'Aquila - ITALY mobile +39 3207214179 email luigi.rosa@tiscali.it website http://www.advancedsourcecode.com

近期下载者

相关文件


收藏者