Speech Recognition and Language Models
碩士 === 國立雲林科技大學 === 電子與資訊工程研究所碩士班 === 90 === In this thesis, we combine the technique of digital signal processing and language model to do speech recognition. Voice signal recognition uses VQ-HMM to build the voice model at the signal level. During testing, the codebook is computed first and then H...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2002
|
Online Access: | http://ndltd.ncl.edu.tw/handle/65147132889234300283 |
id |
ndltd-TW-090YUNTE393023 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-090YUNTE3930232016-06-24T04:15:13Z http://ndltd.ncl.edu.tw/handle/65147132889234300283 Speech Recognition and Language Models 語音辨識與語言模型 Chen Chih-Tsun 陳智聰 碩士 國立雲林科技大學 電子與資訊工程研究所碩士班 90 In this thesis, we combine the technique of digital signal processing and language model to do speech recognition. Voice signal recognition uses VQ-HMM to build the voice model at the signal level. During testing, the codebook is computed first and then HMM is used to find the closest sample voice. After the voice recognition stage, we use 3 different language models, namely context-free grammar, bigram and HMM to increase the recognition rate. Wing-Kwong Wong 黃永廣 2002 學位論文 ; thesis 50 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立雲林科技大學 === 電子與資訊工程研究所碩士班 === 90 === In this thesis, we combine the technique of digital signal processing and language model to do speech recognition. Voice signal recognition uses VQ-HMM to build the voice model at the signal level. During testing, the codebook is computed first and then HMM is used to find the closest sample voice. After the voice recognition stage, we use 3 different language models, namely context-free grammar, bigram and HMM to increase the recognition rate.
|
author2 |
Wing-Kwong Wong |
author_facet |
Wing-Kwong Wong Chen Chih-Tsun 陳智聰 |
author |
Chen Chih-Tsun 陳智聰 |
spellingShingle |
Chen Chih-Tsun 陳智聰 Speech Recognition and Language Models |
author_sort |
Chen Chih-Tsun |
title |
Speech Recognition and Language Models |
title_short |
Speech Recognition and Language Models |
title_full |
Speech Recognition and Language Models |
title_fullStr |
Speech Recognition and Language Models |
title_full_unstemmed |
Speech Recognition and Language Models |
title_sort |
speech recognition and language models |
publishDate |
2002 |
url |
http://ndltd.ncl.edu.tw/handle/65147132889234300283 |
work_keys_str_mv |
AT chenchihtsun speechrecognitionandlanguagemodels AT chénzhìcōng speechrecognitionandlanguagemodels AT chenchihtsun yǔyīnbiànshíyǔyǔyánmóxíng AT chénzhìcōng yǔyīnbiànshíyǔyǔyánmóxíng |
_version_ |
1718321976797298688 |