東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Automatic detection and classificati...

Rosenberg, Andrew.

Linked to FindBook

Google Book

Amazon

博客來

Automatic detection and classification of prosodic events.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Automatic detection and classification of prosodic events./
Author:	Rosenberg, Andrew.
Description:	381 p.
Notes:	Source: Dissertation Abstracts International, Volume: 71-02, Section: B, page: 1119.
Contained By:	Dissertation Abstracts International71-02B.
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3393597
ISBN:	9781109604726

Automatic detection and classification of prosodic events.
Rosenberg, Andrew.

Automatic detection and classification of prosodic events. - 381 p.

Source: Dissertation Abstracts International, Volume: 71-02, Section: B, page: 1119.

Thesis (Ph.D.)--Columbia University, 2009.

Prosody, or intonation, is a critically important component of spoken communication. The automatic extraction of prosodic information is necessary for machines to process speech with human levels of proficiency. In this thesis we describe work on the automatic detection and classification of prosodic events---specifically, pitch accents and prosodic phrase boundaries. We present novel techniques, feature representations and state of the art performance in each of these tasks. We also present three proof-of-concept applications---speech summarization, story segmentation and non-native speech assessment---showing that access to hypothesized prosodic event information can be used to improve the performance of downstream spoken language processing tasks. We believe the contributions of this thesis advance the understanding of prosodic events and the use of prosody in spoken language processing towards the goal of human-like processing of speech by machines.

ISBN: 9781109604726Subjects--Topical Terms:

523869
Computer science.

Automatic detection and classification of prosodic events.
LDR:01804nmm a2200265 4500 001 2115470
005 20170313072602.5
008 180830s2009 ||||||||||||||||| ||eng d
020 $a 9781109604726
035 $a (MiAaPQ)AAI3393597
035 $a AAI3393597
040 $a MiAaPQ $c MiAaPQ
100 1 $a Rosenberg, Andrew. $3 3277120
245 1 0 $a Automatic detection and classification of prosodic events.
300 $a 381 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-02, Section: B, page: 1119.
500 $a Adviser: Julia Herschberg.
502 $a Thesis (Ph.D.)--Columbia University, 2009.
520 $a Prosody, or intonation, is a critically important component of spoken communication. The automatic extraction of prosodic information is necessary for machines to process speech with human levels of proficiency. In this thesis we describe work on the automatic detection and classification of prosodic events---specifically, pitch accents and prosodic phrase boundaries. We present novel techniques, feature representations and state of the art performance in each of these tasks. We also present three proof-of-concept applications---speech summarization, story segmentation and non-native speech assessment---showing that access to hypothesized prosodic event information can be used to improve the performance of downstream spoken language processing tasks. We believe the contributions of this thesis advance the understanding of prosodic events and the use of prosody in spoken language processing towards the goal of human-like processing of speech by machines.
590 $a School code: 0054.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a Columbia University. $3 571054
773 0 $t Dissertation Abstracts International $g 71-02B.
790 $a 0054
791 $a Ph.D.
792 $a 2009
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3393597