國立虎尾科技大學 |

登入

回首頁

Convolutional Neural Networks for Sp...

The Cooper Union for the Advancement of Science and Art.

Convolutional Neural Networks for Speaker-Independent Speech Recognition.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Convolutional Neural Networks for Speaker-Independent Speech Recognition./
作者:	Belilovsky, Eugene.
面頁冊數:	68 p.
附註:	Source: Masters Abstracts International, Volume: 49-06, page: 3957.
Contained By:	Masters Abstracts International49-06.
標題:	Engineering, Electronics and Electrical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1496027
ISBN:	9781124720838

Convolutional Neural Networks for Speaker-Independent Speech Recognition.
Belilovsky, Eugene.

Convolutional Neural Networks for Speaker-Independent Speech Recognition. - 68 p.

Source: Masters Abstracts International, Volume: 49-06, page: 3957.

Thesis (M.E.)--The Cooper Union for the Advancement of Science and Art, 2011.

In this work we analyze a neural network structure capable of achieving a degree of invariance to speaker vocal tracts for speech recognition applications. It will be shown that invariance to a speaker's pitch can be built into the classification stage of the speech recognition process using convolutional neural networks, whereas in the past attempts have been made to achieve invariance on the feature set used in the classification stage. We conduct experiments for the segment-level phoneme classification task using convolutional neural networks and compare them to neural network structures previously used in speech recognition, primarily the time-delayed neural network and the standard multilayer perceptron. The results show that convolutional neural networks can in many cases achieve superior performance than the classical structures.

ISBN: 9781124720838Subjects--Topical Terms:

845382
Engineering, Electronics and Electrical.

Convolutional Neural Networks for Speaker-Independent Speech Recognition.
LDR:01752nam 2200289 4500 001 713030
005 20121003100348.5
008 121101s2011 ||||||||||||||||| ||eng d
020 $a 9781124720838
035 $a (UMI)AAI1496027
035 $a AAI1496027
040 $a UMI $c UMI
100 1 $a Belilovsky, Eugene. $3 845630
245 1 0 $a Convolutional Neural Networks for Speaker-Independent Speech Recognition.
300 $a 68 p.
500 $a Source: Masters Abstracts International, Volume: 49-06, page: 3957.
500 $a Adviser: Carl Sable.
502 $a Thesis (M.E.)--The Cooper Union for the Advancement of Science and Art, 2011.
520 $a In this work we analyze a neural network structure capable of achieving a degree of invariance to speaker vocal tracts for speech recognition applications. It will be shown that invariance to a speaker's pitch can be built into the classification stage of the speech recognition process using convolutional neural networks, whereas in the past attempts have been made to achieve invariance on the feature set used in the classification stage. We conduct experiments for the segment-level phoneme classification task using convolutional neural networks and compare them to neural network structures previously used in speech recognition, primarily the time-delayed neural network and the standard multilayer perceptron. The results show that convolutional neural networks can in many cases achieve superior performance than the classical structures.
590 $a School code: 0057.
650 4 $a Engineering, Electronics and Electrical. $3 845382
650 4 $a Artificial Intelligence. $3 646849
650 4 $a Computer Science. $3 593922
690 $a 0544
690 $a 0800
690 $a 0984
710 2 $a The Cooper Union for the Advancement of Science and Art. $3 845631
773 0 $t Masters Abstracts International $g 49-06.
790 1 0 $a Sable, Carl, $e advisor
790 $a 0057
791 $a M.E.
792 $a 2011
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1496027

筆 0 讀者評論

多媒體

評論

新增評論分享你的心得

Export

取書館別