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

Acoustic model adaptation for recogn...

Sharma, Harsh Vardhan.

Linked to FindBook

Google Book

Amazon

博客來

Acoustic model adaptation for recognition of dysarthric speech.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Acoustic model adaptation for recognition of dysarthric speech./
Author:	Sharma, Harsh Vardhan.
Description:	94 p.
Notes:	Source: Dissertation Abstracts International, Volume: 74-10(E), Section: B.
Contained By:	Dissertation Abstracts International74-10B(E).
Subject:	Engineering, Electronics and Electrical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3570603
ISBN:	9781303162015

Acoustic model adaptation for recognition of dysarthric speech.
Sharma, Harsh Vardhan.

Acoustic model adaptation for recognition of dysarthric speech. - 94 p.

Source: Dissertation Abstracts International, Volume: 74-10(E), Section: B.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2012.

Speech production errors characteristic of dysarthria are chiefly responsible for the low accuracy of automatic speech recognition (ASR) when used by people diagnosed with the condition. The results of the small number of speech recognition studies, mostly conducted by assistive technology researchers, are a testimony to this statement. In the engineering community, substantial research has been conducted to find algorithms that adapt models of speech acoustics trained on one dataset for use with another. They are mostly mathematically motivated.

ISBN: 9781303162015Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Acoustic model adaptation for recognition of dysarthric speech.
LDR:02889nam a2200301 4500 001 1961815
005 20140722092946.5
008 150210s2012 ||||||||||||||||| ||eng d
020 $a 9781303162015
035 $a (MiAaPQ)AAI3570603
035 $a AAI3570603
040 $a MiAaPQ $c MiAaPQ
100 1 $a Sharma, Harsh Vardhan. $3 2097772
245 1 0 $a Acoustic model adaptation for recognition of dysarthric speech.
300 $a 94 p.
500 $a Source: Dissertation Abstracts International, Volume: 74-10(E), Section: B.
500 $a Adviser: Mark Hasegawa-Johnson.
502 $a Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2012.
520 $a Speech production errors characteristic of dysarthria are chiefly responsible for the low accuracy of automatic speech recognition (ASR) when used by people diagnosed with the condition. The results of the small number of speech recognition studies, mostly conducted by assistive technology researchers, are a testimony to this statement. In the engineering community, substantial research has been conducted to find algorithms that adapt models of speech acoustics trained on one dataset for use with another. They are mostly mathematically motivated.
520 $a A person with dysarthria produces speech in a rather reduced acoustic working space, causing typical measures of speech acoustics to have values in ranges very different from those characterizing unimpaired speech. It is unlikely then that models trained on unimpaired speech will be able to adjust to this mismatch when acted on by one of the above-mentioned adaptation algorithms. The creation of acoustic models trained exclusively on pathological speech too is a task difficult to achieve: members of this population find it tiring to pursue physical activities for sustained periods of time, including speech production. While this makes speaker adaptation an approach worthy of pursuit, almost no research has been conducted so far on acoustic model adaptation methods for recognition of dysarthric speech.
520 $a This dissertation presents a study of acoustic model adaptation for recognition of dysarthric speech. First, it investigates the efficacy of a popular adaptation algorithm for dysarthric speech recognition. It then proposes an additional step in the adaptation process, to separately model 'normal' and pathology-induced variations in speech characteristics, and does so by trying to account for a recently proposed view of the acoustics of motor speech disorders in the clinical research community. Results show that explicitly addressing the population mismatch helps to increase the recognition accuracy.
590 $a School code: 0090.
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Health Sciences, Speech Pathology. $3 1018105
690 $a 0544
690 $a 0460
710 2 $a University of Illinois at Urbana-Champaign. $3 626646
773 0 $t Dissertation Abstracts International $g 74-10B(E).
790 $a 0090
791 $a Ph.D.
792 $a 2012
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3570603