南開科技大學圖書館 |

Language: 繁體中文

說明(常見問題)

南開科技大學

圖書館首頁

編目中圖書申請

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Speaker recognition using parallel n...

Deal, Glen Elliott.

Speaker recognition using parallel neural network modules.

紀錄類型:	書目-電子資源 : 單行本
正題名/作者:	Speaker recognition using parallel neural network modules./
作者:	Deal, Glen Elliott.
面頁冊數:	86 p.
附註:	Source: Dissertation Abstracts International, Volume: 67-02, Section: B, page: 1050.
Contained By:	Dissertation Abstracts International67-02B.
標題:	Engineering, Electronics and Electrical. -
電子資源:	Download PDF (下載PDF全文)
ISBN:	9780542555572

Speaker recognition using parallel neural network modules.
Deal, Glen Elliott.

Speaker recognition using parallel neural network modules. - 86 p.

Source: Dissertation Abstracts International, Volume: 67-02, Section: B, page: 1050.

Thesis (Ph.D.)--Florida Institute of Technology, 2006.

This dissertation presents methods for improving the performance of Artificial Neural Network Speaker Recognition systems based on a novel negative reinforcement training algorithm and selective filtering of training data. A brief background of current speaker recognition technology is presented including various options for feature extraction and feature mapping methods. We then develop and present MATLAB implementations of four separate closed-set speaker recognition systems using wavelet and cepstral vector feature extraction algorithms and using several parallel-architecture neural network mapping algorithms. These systems are used as performance baselines representing the most promising feature extraction and feature mapping algorithms currently in use. The negative reinforcement training algorithm and training data selection concepts are then described and demonstrated as improvements to the baseline systems. The resulting systems are shown to have significantly improved correct recognition rate over the baseline systems.

ISBN: 9780542555572Subjects--Topical Terms:

170927
Engineering, Electronics and Electrical.

Speaker recognition using parallel neural network modules.
LDR:01946nmm 2200265 4500 001 1000004863
005 20070601084707.5
008 070601s2006 eng d
020 $a 9780542555572
035 $a (UnM)AAI3206619
035 $a AAI3206619
040 $a UnM $c UnM{me_controlnum}
100 1 $a Deal, Glen Elliott. $3 1000005988
245 1 0 $a Speaker recognition using parallel neural network modules.
300 $a 86 p.
500 $a Source: Dissertation Abstracts International, Volume: 67-02, Section: B, page: 1050.
500 $a Adviser: Fredric M. Ham.
502 $a Thesis (Ph.D.)--Florida Institute of Technology, 2006.
520 $a This dissertation presents methods for improving the performance of Artificial Neural Network Speaker Recognition systems based on a novel negative reinforcement training algorithm and selective filtering of training data. A brief background of current speaker recognition technology is presented including various options for feature extraction and feature mapping methods. We then develop and present MATLAB implementations of four separate closed-set speaker recognition systems using wavelet and cepstral vector feature extraction algorithms and using several parallel-architecture neural network mapping algorithms. These systems are used as performance baselines representing the most promising feature extraction and feature mapping algorithms currently in use. The negative reinforcement training algorithm and training data selection concepts are then described and demonstrated as improvements to the baseline systems. The resulting systems are shown to have significantly improved correct recognition rate over the baseline systems.
590 $a School code: 0473.
650 4 $a Engineering, Electronics and Electrical. $3 170927
690 $a 0544
710 2 0 $a Florida Institute of Technology. $3 1000005989
773 0 $t Dissertation Abstracts International $g 67-02B.
790 1 0 $a Ham, Fredric M., $e advisor
790 $a 0473
791 $a Ph.D.
792 $a 2006
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3206619 $z Download PDF (下載PDF全文)