A Design of Speech Recognition System for Two-word、Three-word and Four-word Mandarin Phrases
碩士 === 國立中山大學 === 電機工程學系研究所 === 95 === In this thesis, a two-word, three-word and four-word Mandarin phrases speech recognition system is studied and implemented. This system utilizes hidden Markov model, lexicon search strategy and tone recognition to select the initial phrase candidates and make t...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2007
|
Online Access: | http://ndltd.ncl.edu.tw/handle/r93ctz |
id |
ndltd-TW-095NSYS5442102 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-095NSYS54421022019-05-15T19:48:10Z http://ndltd.ncl.edu.tw/handle/r93ctz A Design of Speech Recognition System for Two-word、Three-word and Four-word Mandarin Phrases 中文二、三、四字語詞辨識系統之設計研究 Jung-chun Wu 吳俊榮 碩士 國立中山大學 電機工程學系研究所 95 In this thesis, a two-word, three-word and four-word Mandarin phrases speech recognition system is studied and implemented. This system utilizes hidden Markov model, lexicon search strategy and tone recognition to select the initial phrase candidates and make the final decision. Experimental results indicate that using about one third of the total phrase population, 80%, 92% and 97% correct rates can be achieved for the 70,000 two-word, 24,000 three-word and 22,000 four-word phrases recognition problems respectively. Any spoken phrase can be found within 1 second, using a PC with Intel Celeron 2.4 GHz CPU and Red Hat Linux 9.0 operating system. Chih-Chien Chen 陳志堅 2007 學位論文 ; thesis 37 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中山大學 === 電機工程學系研究所 === 95 === In this thesis, a two-word, three-word and four-word Mandarin phrases speech recognition system is studied and implemented. This system utilizes hidden Markov model, lexicon search strategy and tone recognition to select the initial phrase candidates and make the final decision. Experimental results indicate that using about one third of the total phrase population, 80%, 92% and 97% correct rates can be achieved for the 70,000 two-word, 24,000 three-word and 22,000 four-word phrases recognition problems respectively. Any spoken phrase can be found within 1 second, using a PC with Intel Celeron 2.4 GHz CPU and Red Hat Linux 9.0 operating system.
|
author2 |
Chih-Chien Chen |
author_facet |
Chih-Chien Chen Jung-chun Wu 吳俊榮 |
author |
Jung-chun Wu 吳俊榮 |
spellingShingle |
Jung-chun Wu 吳俊榮 A Design of Speech Recognition System for Two-word、Three-word and Four-word Mandarin Phrases |
author_sort |
Jung-chun Wu |
title |
A Design of Speech Recognition System for Two-word、Three-word and Four-word Mandarin Phrases |
title_short |
A Design of Speech Recognition System for Two-word、Three-word and Four-word Mandarin Phrases |
title_full |
A Design of Speech Recognition System for Two-word、Three-word and Four-word Mandarin Phrases |
title_fullStr |
A Design of Speech Recognition System for Two-word、Three-word and Four-word Mandarin Phrases |
title_full_unstemmed |
A Design of Speech Recognition System for Two-word、Three-word and Four-word Mandarin Phrases |
title_sort |
design of speech recognition system for two-word、three-word and four-word mandarin phrases |
publishDate |
2007 |
url |
http://ndltd.ncl.edu.tw/handle/r93ctz |
work_keys_str_mv |
AT jungchunwu adesignofspeechrecognitionsystemfortwowordthreewordandfourwordmandarinphrases AT wújùnróng adesignofspeechrecognitionsystemfortwowordthreewordandfourwordmandarinphrases AT jungchunwu zhōngwénèrsānsìzìyǔcíbiànshíxìtǒngzhīshèjìyánjiū AT wújùnróng zhōngwénèrsānsìzìyǔcíbiànshíxìtǒngzhīshèjìyánjiū AT jungchunwu designofspeechrecognitionsystemfortwowordthreewordandfourwordmandarinphrases AT wújùnróng designofspeechrecognitionsystemfortwowordthreewordandfourwordmandarinphrases |
_version_ |
1719094517028618240 |