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 to Text to Semantics: A Seque...

Dodson, John.

FindBook

Google Book

Amazon

博客來

Speech to Text to Semantics: A Sequence-to-sequence System for Spoken Language Understanding.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Speech to Text to Semantics: A Sequence-to-sequence System for Spoken Language Understanding./
作者:	Dodson, John.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	85 p.
附註:	Source: Masters Abstracts International, Volume: 82-02.
Contained By:	Masters Abstracts International82-02.
標題:	Computer science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27831588
ISBN:	9798664706741

Speech to Text to Semantics: A Sequence-to-sequence System for Spoken Language Understanding.
Dodson, John.

Speech to Text to Semantics: A Sequence-to-sequence System for Spoken Language Understanding. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 85 p.

Source: Masters Abstracts International, Volume: 82-02.

Thesis (Master's)--University of Washington, 2020.

This item must not be sold to any third party vendors.

Spoken language understanding entails both the automatic transcription of a speech utterance and the identification of one or more semantic concepts being conveyed by the utterance. Traditionally these systems are domain specific and target industries like travel, entertainment, and home automation. As such, many approaches to spoken language understanding solve the task of filling predefined semantic slots, and cannot generalize to identify arbitrary semantic roles.This thesis addresses the broader question of how to extract predicate-argument frames from a transcribed speech utterance. I describe a sequence-to-sequence system for spoken language understanding through shallow semantic parsing. Built using a modification of the OpenSeq2Seq toolkit, the system is able to perform speech recognition and semantic parsing in a single end-to-end flow. The proposed system is extensible and easy to use, allowing for fast iteration on system parameters and model architectures.The system is evaluated through two experiments. The first experiment performs a speech to text to semantics transformation and uses n-best language model rescoring to generate the best transcription sequence. The second experiment executes the same transformation process, but generates transcriptions through shallow language model fusion. Both experiments evaluate several combinations of speech recognition models and semantic parsers.

ISBN: 9798664706741Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Spoken language understanding

Speech to Text to Semantics: A Sequence-to-sequence System for Spoken Language Understanding.
LDR:02529nmm a2200337 4500 001 2277069
005 20210510094234.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798664706741
035 $a (MiAaPQ)AAI27831588
035 $a AAI27831588
040 $a MiAaPQ $c MiAaPQ
100 1 $a Dodson, John. $3 1244291
245 1 0 $a Speech to Text to Semantics: A Sequence-to-sequence System for Spoken Language Understanding.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 85 p.
500 $a Source: Masters Abstracts International, Volume: 82-02.
500 $a Advisor: Levow, Gina-Anne.
502 $a Thesis (Master's)--University of Washington, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Spoken language understanding entails both the automatic transcription of a speech utterance and the identification of one or more semantic concepts being conveyed by the utterance. Traditionally these systems are domain specific and target industries like travel, entertainment, and home automation. As such, many approaches to spoken language understanding solve the task of filling predefined semantic slots, and cannot generalize to identify arbitrary semantic roles.This thesis addresses the broader question of how to extract predicate-argument frames from a transcribed speech utterance. I describe a sequence-to-sequence system for spoken language understanding through shallow semantic parsing. Built using a modification of the OpenSeq2Seq toolkit, the system is able to perform speech recognition and semantic parsing in a single end-to-end flow. The proposed system is extensible and easy to use, allowing for fast iteration on system parameters and model architectures.The system is evaluated through two experiments. The first experiment performs a speech to text to semantics transformation and uses n-best language model rescoring to generate the best transcription sequence. The second experiment executes the same transformation process, but generates transcriptions through shallow language model fusion. Both experiments evaluate several combinations of speech recognition models and semantic parsers.
590 $a School code: 0250.
650 4 $a Computer science. $3 523869
650 4 $a Linguistics. $3 524476
653 $a Spoken language understanding
653 $a Sequence-to-sequence system
653 $a Automatic transcription
690 $a 0984
690 $a 0290
710 2 $a University of Washington. $b Linguistics. $3 2100714
773 0 $t Masters Abstracts International $g 82-02.
790 $a 0250
791 $a Master's
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27831588