東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Speech recognition in adverse enviro...

Kristjansson, Trausti Thor.

FindBook

Google Book

Amazon

博客來

Speech recognition in adverse environments: A probabilistic approach.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Speech recognition in adverse environments: A probabilistic approach./
作者:	Kristjansson, Trausti Thor.
面頁冊數:	151 p.
附註:	Adviser: Brendan Frey.
Contained By:	Dissertation Abstracts International63-08B
標題:	Computer Science -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NQ70850
ISBN:	0612708500

Speech recognition in adverse environments: A probabilistic approach.
Kristjansson, Trausti Thor.

Speech recognition in adverse environments: A probabilistic approach. - 151 p.

Adviser: Brendan Frey.

Thesis (Ph.D.)--University of Waterloo (Canada), 2002.

In this thesis I advocate a probabilistic view of robust speech recognition. I discuss the classification of distorted features using an optimal classifier, and I show how the generation of noisy speech can be represented as a generative graphical probability model. By doing so, my aim is to build a conceptual framework that provides a unified understanding of robust speech recognition, and to some extent bridges the gap between a purely signal processing viewpoint and the pattern classification or decoding viewpoint.

ISBN: 0612708500Subjects--Topical Terms:

890869
Computer Science

Speech recognition in adverse environments: A probabilistic approach.
LDR:02320nam 2200289 a 45 001 936670
005 20110510
008 110510s2002 eng d
020 $a 0612708500
035 $a (UnM)AAINQ70850
035 $a AAINQ70850
040 $a UnM $c UnM
100 1 $a Kristjansson, Trausti Thor. $3 1260475
245 1 0 $a Speech recognition in adverse environments: A probabilistic approach.
300 $a 151 p.
500 $a Adviser: Brendan Frey.
500 $a Source: Dissertation Abstracts International, Volume: 63-08, Section: B, page: 3789.
502 $a Thesis (Ph.D.)--University of Waterloo (Canada), 2002.
520 $a In this thesis I advocate a probabilistic view of robust speech recognition. I discuss the classification of distorted features using an optimal classifier, and I show how the generation of noisy speech can be represented as a generative graphical probability model. By doing so, my aim is to build a conceptual framework that provides a unified understanding of robust speech recognition, and to some extent bridges the gap between a purely signal processing viewpoint and the pattern classification or decoding viewpoint.
520 $a The most tangible contribution of this thesis is the introduction of the Algonquin method for robust speech recognition. It exemplifies the probabilistic method and encompasses a number of novel ideas. For example, it uses a probability distribution to describe the relationship between clean speech, noise, channel and the resultant noisy speech. It employs a variational approach to find an approximation to the joint posterior distribution which can be used for the purpose of restoring the distorted observations. It also allows us to estimate the parameters of the environment using a Generalized EM method.
520 $a Another important contribution of this thesis is a new paradigm for robust speech recognition, which we call <italic>uncertainty decoding </italic>. This new paradigm follows naturally from the standard way of performing inference in the graphical probability model that describes noisy speech generation
590 $a School code: 1141
650 $a Computer Science $3 890869
690 $a 098
710 2 $a University of Waterloo (Canada) $3 1260476
773 0 $t Dissertation Abstracts International $g 63-08B
790 $a 114
790 1 $a Frey, Brendan, $e adviso
791 $a Ph.D
792 $a 200
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NQ70850