Using the method of HMM to recognize the mandarin word in the system of dependent speaker
碩士 === 國立中興大學 === 統計學研究所 === 103 === This paper is to investigate the 1391 monosyllable in speaker-dependent system.The hidden of Markov model is a way to account the feature. In each class of the mandarin word, we all use the HMM to estimate the parameter. The advantage is the high recognition. We...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2015
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/10879126930463760456 |
| id |
ndltd-TW-103NCHU5337008 |
|---|---|
| record_format |
oai_dc |
| spelling |
ndltd-TW-103NCHU53370082017-06-17T04:31:36Z http://ndltd.ncl.edu.tw/handle/10879126930463760456 Using the method of HMM to recognize the mandarin word in the system of dependent speaker 利用隱藏式馬可夫模型於特定語者之中文單音辨識 Bo-Yu Ho 何伯魚 碩士 國立中興大學 統計學研究所 103 This paper is to investigate the 1391 monosyllable in speaker-dependent system.The hidden of Markov model is a way to account the feature. In each class of the mandarin word, we all use the HMM to estimate the parameter. The advantage is the high recognition. We can iterative estimation of parameter, that we have ability of training database. The database can be better. In this paper, we also use the MFCC to account the feature of monosyllable. We put the mandarin word to HMM, by this way to test the recognition. The test is spilt in two situation, is the known an unknown. The recognition of known is about 90% and recognition unknown is about 72%. In this paper we will against this part to investigate. 李宗寶 2015 學位論文 ; thesis 42 zh-TW |
| collection |
NDLTD |
| language |
zh-TW |
| format |
Others
|
| sources |
NDLTD |
| description |
碩士 === 國立中興大學 === 統計學研究所 === 103 === This paper is to investigate the 1391 monosyllable in speaker-dependent system.The hidden of Markov model is a way to account the feature. In each class of the mandarin word, we all use the HMM to estimate the parameter. The advantage is the high recognition. We can iterative estimation of parameter, that we have ability of training database. The database can be better. In this paper, we also use the MFCC to account the feature of monosyllable. We put the mandarin word to HMM, by this way to test the recognition. The test is spilt in two situation, is the known an unknown. The recognition of known is about 90% and recognition unknown is about 72%. In this paper we will against this part to investigate.
|
| author2 |
李宗寶 |
| author_facet |
李宗寶 Bo-Yu Ho 何伯魚 |
| author |
Bo-Yu Ho 何伯魚 |
| spellingShingle |
Bo-Yu Ho 何伯魚 Using the method of HMM to recognize the mandarin word in the system of dependent speaker |
| author_sort |
Bo-Yu Ho |
| title |
Using the method of HMM to recognize the mandarin word in the system of dependent speaker |
| title_short |
Using the method of HMM to recognize the mandarin word in the system of dependent speaker |
| title_full |
Using the method of HMM to recognize the mandarin word in the system of dependent speaker |
| title_fullStr |
Using the method of HMM to recognize the mandarin word in the system of dependent speaker |
| title_full_unstemmed |
Using the method of HMM to recognize the mandarin word in the system of dependent speaker |
| title_sort |
using the method of hmm to recognize the mandarin word in the system of dependent speaker |
| publishDate |
2015 |
| url |
http://ndltd.ncl.edu.tw/handle/10879126930463760456 |
| work_keys_str_mv |
AT boyuho usingthemethodofhmmtorecognizethemandarinwordinthesystemofdependentspeaker AT hébóyú usingthemethodofhmmtorecognizethemandarinwordinthesystemofdependentspeaker AT boyuho lìyòngyǐncángshìmǎkěfūmóxíngyútèdìngyǔzhězhīzhōngwéndānyīnbiànshí AT hébóyú lìyòngyǐncángshìmǎkěfūmóxíngyútèdìngyǔzhězhīzhōngwéndānyīnbiànshí |
| _version_ |
1718460092503818240 |