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

Code switching speech recognition by...

Li, Ying.

FindBook

Google Book

Amazon

博客來

Code switching speech recognition by language borrowing.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Code switching speech recognition by language borrowing./
作者:	Li, Ying.
面頁冊數:	122 p.
附註:	Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.
Contained By:	Dissertation Abstracts International77-07B(E).
標題:	Electrical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3745715
ISBN:	9781339387697

Code switching speech recognition by language borrowing.
Li, Ying.

Code switching speech recognition by language borrowing. - 122 p.

Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.

Thesis (Ph.D.)--Hong Kong University of Science and Technology (Hong Kong), 2015.

Multilingual people often code switch mixing two languages in the same sentence (intra-sentential code-switching) or between sentences (inter-sentential code-switching). In this thesis, we meet the dual challenge of code switching speech recognition in terms of both acoustic modeling and language modeling.

ISBN: 9781339387697Subjects--Topical Terms:

649834
Electrical engineering.

Code switching speech recognition by language borrowing.
LDR:03425nmm a2200301 4500 001 2078200
005 20161122113938.5
008 170521s2015 ||||||||||||||||| ||eng d
020 $a 9781339387697
035 $a (MiAaPQ)AAI3745715
035 $a AAI3745715
040 $a MiAaPQ $c MiAaPQ
100 1 $a Li, Ying. $3 1036447
245 1 0 $a Code switching speech recognition by language borrowing.
300 $a 122 p.
500 $a Source: Dissertation Abstracts International, Volume: 77-07(E), Section: B.
500 $a Adviser: Pascale Fung.
502 $a Thesis (Ph.D.)--Hong Kong University of Science and Technology (Hong Kong), 2015.
520 $a Multilingual people often code switch mixing two languages in the same sentence (intra-sentential code-switching) or between sentences (inter-sentential code-switching). In this thesis, we meet the dual challenge of code switching speech recognition in terms of both acoustic modeling and language modeling.
520 $a The acoustic modeling challenge is due to the lack of labeled code switching data.We propose a novel asymmetric pronunciation and acoustic modeling approach usinga single set of models trained on a small amount of accented data in the second language and monolingual data in the main language. We tested our proposed asymmetric acoustic models on inter-sentential and intra-sentential code-switching testsets and showed that our approach significantly outperforms previous approaches of using limited amount of code-switched data or using adaptation.
520 $a The challenge for language modeling is predicting the code switching point. Itis generally accepted by linguistics that code switching follows the Inversion Transduction Grammar Constraint under which the switching does not violate grammars of either language. Under another constraint, the Functional Head Constraint, code switching is forbidden between the functional head and its complements. However,none of these linguistic constraints has been previously modeled computationally or incorporated into code switching speech recognition. We propose a first ever computational approach of incorporating these linguistic constraints into a statistical language model for speech recognition. We proposeusing a weighted finite-state transducer (WFST) framework so that linguistic constraints such as Inversion Transduction Grammar Constraint and Functional Head Constraint can be incorporated.
520 $a We propose first ever statistical code switching language modeling that integrates the syntactic Inversion Transduction Grammar Constraint by a chunk segmentation model and a chunk translation model. We also propose a constrained code switching language model with Functional Head Constraint obtained by first expanding the search network with a translation model,and then restrict paths to those permissible using parsing. Experimental resultson lecture speech and lunch conversation datasets show our systems reduce word error rates compared to the previous approaches. Our proposed approaches delay code switching boundary decisions to avoid propagated errors. We address the code switching data scarcity challenge using bilingual data by language borrowing.
590 $a School code: 1223.
650 4 $a Electrical engineering. $3 649834
690 $a 0544
710 2 $a Hong Kong University of Science and Technology (Hong Kong). $b hkust. $3 3182391
773 0 $t Dissertation Abstracts International $g 77-07B(E).
790 $a 1223
791 $a Ph.D.
792 $a 2015
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3745715