Large-Vocabulary Mandarin Speech Recognition using Hierarchical Language Model
碩士 === 國立交通大學 === 電信工程研究所 === 99 === It’s difficult to list all words in recognizer’s vocabulary for large-vocabulary speech recognition, so we present an approach for modeling out of vocabulary (OOV) words. In this thesis, we choose three types of word in Mandarin such as determinative-measure...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2010
|
Online Access: | http://ndltd.ncl.edu.tw/handle/76476966608462857598 |
id |
ndltd-TW-099NCTU5435032 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-099NCTU54350322016-04-18T04:21:46Z http://ndltd.ncl.edu.tw/handle/76476966608462857598 Large-Vocabulary Mandarin Speech Recognition using Hierarchical Language Model 使用階層式語言模型之大詞彙國語辨認系統 Yang, Yun-Shu 楊雲舒 碩士 國立交通大學 電信工程研究所 99 It’s difficult to list all words in recognizer’s vocabulary for large-vocabulary speech recognition, so we present an approach for modeling out of vocabulary (OOV) words. In this thesis, we choose three types of word in Mandarin such as determinative-measure compound word, person name and affixation to deal with this OOV problem. Words are converted to the sub-word units and searched for in the hypotheses to cover more new words through the use of flexible sub-word units. The main focus of this study is to use the grammar and semantic information to construct a hierarchical language model for these three types of word. The language model will be added to promote the recognition performance and hope to recognize more meaningful long-term units such as word and word-chunk. Wang, Yih-Ru 王逸如 2010 學位論文 ; thesis 50 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立交通大學 === 電信工程研究所 === 99 === It’s difficult to list all words in recognizer’s vocabulary for large-vocabulary speech recognition, so we present an approach for modeling out of vocabulary (OOV) words. In this thesis, we choose three types of word in Mandarin such as determinative-measure compound word, person name and affixation to deal with this OOV problem. Words are converted to the sub-word units and searched for in the hypotheses to cover more new words through the use of flexible sub-word units.
The main focus of this study is to use the grammar and semantic information to construct a hierarchical language model for these three types of word. The language model will be added to promote the recognition performance and hope to recognize more meaningful long-term units such as word and word-chunk.
|
author2 |
Wang, Yih-Ru |
author_facet |
Wang, Yih-Ru Yang, Yun-Shu 楊雲舒 |
author |
Yang, Yun-Shu 楊雲舒 |
spellingShingle |
Yang, Yun-Shu 楊雲舒 Large-Vocabulary Mandarin Speech Recognition using Hierarchical Language Model |
author_sort |
Yang, Yun-Shu |
title |
Large-Vocabulary Mandarin Speech Recognition using Hierarchical Language Model |
title_short |
Large-Vocabulary Mandarin Speech Recognition using Hierarchical Language Model |
title_full |
Large-Vocabulary Mandarin Speech Recognition using Hierarchical Language Model |
title_fullStr |
Large-Vocabulary Mandarin Speech Recognition using Hierarchical Language Model |
title_full_unstemmed |
Large-Vocabulary Mandarin Speech Recognition using Hierarchical Language Model |
title_sort |
large-vocabulary mandarin speech recognition using hierarchical language model |
publishDate |
2010 |
url |
http://ndltd.ncl.edu.tw/handle/76476966608462857598 |
work_keys_str_mv |
AT yangyunshu largevocabularymandarinspeechrecognitionusinghierarchicallanguagemodel AT yángyúnshū largevocabularymandarinspeechrecognitionusinghierarchicallanguagemodel AT yangyunshu shǐyòngjiēcéngshìyǔyánmóxíngzhīdàcíhuìguóyǔbiànrènxìtǒng AT yángyúnshū shǐyòngjiēcéngshìyǔyánmóxíngzhīdàcíhuìguóyǔbiànrènxìtǒng |
_version_ |
1718227101889331200 |