System design of a WFST-based Mandarin speech recognizer
碩士 === 國立交通大學 === 電信工程研究所 === 102 === This thesis is mainly focus on improving language model in Automatic Speech Recognition(ASR). The studies normalize the training data including combining synonym, variant word, multi-pronunciation. The words are categorized by word class to choose dictionary. Ra...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2013
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/03540751552342577320 |