Language:
繁體中文
English
日文
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
Network training for continuous spee...
~
Alphonso, Issac J.
Network training for continuous speech recognition.
紀錄類型:
書目-電子資源 : 單行本
正題名/作者:
Network training for continuous speech recognition./
作者:
Alphonso, Issac J.
面頁冊數:
80 p.
附註:
Source: Masters Abstracts International, Volume: 42-04, page: 1328.
Contained By:
Masters Abstracts International42-04.
標題:
Engineering, Electronics and Electrical. -
電子資源:
Download fulltext (下載全文)
ISBN:
049623126X
Network training for continuous speech recognition.
Alphonso, Issac J.
Network training for continuous speech recognition.
- 80 p.
Source: Masters Abstracts International, Volume: 42-04, page: 1328.
Thesis (M.S.)--Mississippi State University, 2003.
Spoken language processing is one of the oldest and most natural modes of information exchange between humans beings. For centuries, people have tried to develop machines that can understand and produce speech the way humans do so naturally. The biggest problem in our inability to model speech with computer programs and mathematics results from the fact that language is instinctive, whereas, the vocabulary and dialect used in communication are learned. Human beings are genetically equipped with the ability to learn languages, and culture imprints the vocabulary and dialect on each member of society. This thesis examines the role of pattern classification in the recognition of human speech, i.e., machine learning techniques that are currently being applied to the spoken language processing problem.
ISBN: 049623126XSubjects--Topical Terms:
170927
Engineering, Electronics and Electrical.
Network training for continuous speech recognition.
LDR
:02684nmm 2200301 4500
001
1000004342
005
20051102155248.5
008
141201s2003 eng d
020
$a
049623126X
035
$a
(UnM)AAI1418351
035
$a
AAI1418351
040
$a
UnM
$c
UnM{me_controlnum}
100
1
$a
Alphonso, Issac J.
$3
1000005702
245
1 0
$a
Network training for continuous speech recognition.
300
$a
80 p.
500
$a
Source: Masters Abstracts International, Volume: 42-04, page: 1328.
500
$a
Major Professor: Joseph Picone.
502
$a
Thesis (M.S.)--Mississippi State University, 2003.
520
$a
Spoken language processing is one of the oldest and most natural modes of information exchange between humans beings. For centuries, people have tried to develop machines that can understand and produce speech the way humans do so naturally. The biggest problem in our inability to model speech with computer programs and mathematics results from the fact that language is instinctive, whereas, the vocabulary and dialect used in communication are learned. Human beings are genetically equipped with the ability to learn languages, and culture imprints the vocabulary and dialect on each member of society. This thesis examines the role of pattern classification in the recognition of human speech, i.e., machine learning techniques that are currently being applied to the spoken language processing problem.
520
$a
The primary objective of this thesis is to create a network training paradigm that allows for direct training of multi-path models and alleviates the need for complicated systems and training recipes. A traditional trainer uses an expectation maximization (EM) based supervised training framework to estimate the parameters of a spoken language processing system. EM-based parameter estimation for speech recognition is performed using several complicated stages of iterative reestimation. These stages typically are prone to human error. The network training paradigm reduces the complexity of the training process while retaining the robustness of the EM-based supervised training framework. The hypothesis of this thesis is that the network training paradigm can achieve comparable recognition performance to a traditional trainer while alleviating the need for complicated systems and training recipes for spoken language processing systems.
590
$a
School code: 0132.
650
4
$a
Engineering, Electronics and Electrical.
$3
170927
650
4
$a
Computer Science.
$3
1000005419
650
4
$a
Artificial Intelligence.
$3
165300
690
$a
0544
690
$a
0984
690
$a
0800
710
2 0
$a
Mississippi State University.
$3
1000005703
773
0
$t
Masters Abstracts International
$g
42-04.
790
1 0
$a
Picone, Joseph,
$e
advisor
790
$a
0132
791
$a
M.S.
792
$a
2003
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1418351
$z
Download fulltext (下載全文)
0 筆讀者評論
館藏地:
全部
線上資料庫
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約人數
備註欄
附件
OE0000642
線上資料庫
線上資源
線上電子書
OE c.2
一般(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
建立或儲存個人書籤
書目轉出
取書館別
處理中
...
變更密碼
登入