A Speech Input Query System for Chinese Web Page Based on VenusDictate

碩士 === 國立成功大學 === 電機工程學系 === 86 === In this thesis, a Speech Input Query System for Chinese Web Page is described. The user can query data on web page using speech input. This query system includes a network part, a language model part, a speech recogniti...

Full description

Bibliographic Details
Main Authors: Chen, Shih-DA, 陳世達
Other Authors: Jhing-Fa Wang
Format: Others
Language:zh-TW
Published: 1998
Online Access:http://ndltd.ncl.edu.tw/handle/34672832225858800335
id ndltd-TW-086NCKU1442124
record_format oai_dc
spelling ndltd-TW-086NCKU14421242015-10-13T11:06:13Z http://ndltd.ncl.edu.tw/handle/34672832225858800335 A Speech Input Query System for Chinese Web Page Based on VenusDictate 應用音中仙中文聽寫機之全球資訊網語音輸入查詢系統 Chen, Shih-DA 陳世達 碩士 國立成功大學 電機工程學系 86 In this thesis, a Speech Input Query System for Chinese Web Page is described. The user can query data on web page using speech input. This query system includes a network part, a language model part, a speech recognition part and a query part.In network part, the system can get web page dynamically and build keyword model of the web page. The language model part deals with the ambiguity in segmenting sentence by Viterbi algorithm. It caculates unigram and bigram information from vocabularies of web pages, and builds common vocabularies of web pages from query sentence. In the speech recognition part, we use VenusDictate as the recognition kernel.It first builds character-lattice and word-lattice using vocabularies and common vocabularies of web pages, then finds the optimal word sequence using full search and BIGRAM language model. In addition, we propose a grammar rule and modifies part of BIGRAM language model in order to speed up recognition time and increase recognition rate. In query part, the system offers many syntax for query, and the result can be displayed on web brower or output by a TTS system.We use web page on NCKU EE and NCKU IIE for test, and design 100 query sentences and 100 keywords for expriments. The recognition rate and recognition time depends on the size of web page. Experimental results show that the top one recognition rate is 93.1%, top ten recognition rate is 100%, and the average recogniton time is 0.23 second. Jhing-Fa Wang 王駿發 1998 學位論文 ; thesis 59 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立成功大學 === 電機工程學系 === 86 === In this thesis, a Speech Input Query System for Chinese Web Page is described. The user can query data on web page using speech input. This query system includes a network part, a language model part, a speech recognition part and a query part.In network part, the system can get web page dynamically and build keyword model of the web page. The language model part deals with the ambiguity in segmenting sentence by Viterbi algorithm. It caculates unigram and bigram information from vocabularies of web pages, and builds common vocabularies of web pages from query sentence. In the speech recognition part, we use VenusDictate as the recognition kernel.It first builds character-lattice and word-lattice using vocabularies and common vocabularies of web pages, then finds the optimal word sequence using full search and BIGRAM language model. In addition, we propose a grammar rule and modifies part of BIGRAM language model in order to speed up recognition time and increase recognition rate. In query part, the system offers many syntax for query, and the result can be displayed on web brower or output by a TTS system.We use web page on NCKU EE and NCKU IIE for test, and design 100 query sentences and 100 keywords for expriments. The recognition rate and recognition time depends on the size of web page. Experimental results show that the top one recognition rate is 93.1%, top ten recognition rate is 100%, and the average recogniton time is 0.23 second.
author2 Jhing-Fa Wang
author_facet Jhing-Fa Wang
Chen, Shih-DA
陳世達
author Chen, Shih-DA
陳世達
spellingShingle Chen, Shih-DA
陳世達
A Speech Input Query System for Chinese Web Page Based on VenusDictate
author_sort Chen, Shih-DA
title A Speech Input Query System for Chinese Web Page Based on VenusDictate
title_short A Speech Input Query System for Chinese Web Page Based on VenusDictate
title_full A Speech Input Query System for Chinese Web Page Based on VenusDictate
title_fullStr A Speech Input Query System for Chinese Web Page Based on VenusDictate
title_full_unstemmed A Speech Input Query System for Chinese Web Page Based on VenusDictate
title_sort speech input query system for chinese web page based on venusdictate
publishDate 1998
url http://ndltd.ncl.edu.tw/handle/34672832225858800335
work_keys_str_mv AT chenshihda aspeechinputquerysystemforchinesewebpagebasedonvenusdictate
AT chénshìdá aspeechinputquerysystemforchinesewebpagebasedonvenusdictate
AT chenshihda yīngyòngyīnzhōngxiānzhōngwéntīngxiějīzhīquánqiúzīxùnwǎngyǔyīnshūrùcháxúnxìtǒng
AT chénshìdá yīngyòngyīnzhōngxiānzhōngwéntīngxiějīzhīquánqiúzīxùnwǎngyǔyīnshūrùcháxúnxìtǒng
AT chenshihda speechinputquerysystemforchinesewebpagebasedonvenusdictate
AT chénshìdá speechinputquerysystemforchinesewebpagebasedonvenusdictate
_version_ 1716836788112195584