Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lin, Ang-Hsing | en_US |
dc.contributor.author | Wang, Yih-Ru | en_US |
dc.contributor.author | Chen, Sin-Horng | en_US |
dc.date.accessioned | 2015-07-21T08:31:21Z | - |
dc.date.available | 2015-07-21T08:31:21Z | - |
dc.date.issued | 2013-01-01 | en_US |
dc.identifier.issn | en_US | |
dc.identifier.uri | http://hdl.handle.net/11536/125033 | - |
dc.description.abstract | A new approach of traditional Chinese parser to improving the language modeling of Mandarin speech recognition is proposed in this paper. The parser first uses a preprocessing to correct some word segmentation inconsistencies of the text corpus. It then employs a CRF-based word segmentation method and a CRF-based POS tagger to resegment the texts so as to generate better word strings for training an n-gram language model (LM) for ASR. Experimental results on the TCC-300 corpus showed that a word error rate (WER) of 13.4% was achieved by the proposed method. It is about 45% improvement on the relative WER reduction as compared with the previous system. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | Chinese word segmentation | en_US |
dc.subject | Conditional random field | en_US |
dc.subject | Language model | en_US |
dc.subject | weighted finite state transducer | en_US |
dc.subject | automatic speech recognition | en_US |
dc.title | Traditional Chinese Parser and Language Modeling for Mandadin ASR | en_US |
dc.type | Proceedings Paper | en_US |
dc.identifier.journal | 2013 INTERNATIONAL CONFERENCE ORIENTAL COCOSDA HELD JOINTLY WITH 2013 CONFERENCE ON ASIAN SPOKEN LANGUAGE RESEARCH AND EVALUATION (O-COCOSDA/CASLRE) | en_US |
dc.contributor.department | 傳播研究所 | zh_TW |
dc.contributor.department | Institute of Communication Studies | en_US |
dc.identifier.wosnumber | WOS:000349833100046 | en_US |
dc.citation.woscount | 0 | en_US |
Appears in Collections: | Conferences Paper |