https://scholars.lib.ntu.edu.tw/handle/123456789/121835
標題: | Improved pronunciation modelling by inverse word frequency and pronunciation entropy | 作者: | Tsai, Ming-yi Chou, Fu-chiang LIN-SHAN LEE |
公開日期: | 十二月-2001 | 起(迄)頁: | 53-56 | 來源出版物: | 2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings | 會議論文: | IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 | 摘要: | We propose a new approach to rank the potential pronunciations for each word by their pronunciation frequency and inverse word frequency (pf-iwf) weights. The pronunciation set obtained in this way can then be pruned with different criteria. This approach not only considers the frequencies of occurrence of the pronunciations, but tries to minimize the extra confusion which may be introduced by pronunciation variations, such that the best overall performance can be achieved. A new entropy-based approach for pruning the pronunciation variations is also proposed. Experimental results showed that the proposed approach can not only improve the recognition performance, but make the performance more stable and less sensitive to various parameters, factors and options including the different pruning criteria. All the experiments were performed with the LDC Mandarin Call Home corpus, although the approaches and principles are definitely not limited to Mandarin Chinese. © 2001 IEEE. |
URI: | http://ntur.lib.ntu.edu.tw//handle/246246/2007041910043003 https://www.scopus.com/inward/record.uri?eid=2-s2.0-84962892877&doi=10.1109%2fASRU.2001.1034587&partnerID=40&md5=d75f97e574965c3087f9d878c5ba9af7 |
ISSN: | N/A | 其他識別: | N/A | DOI: | 10.1109/ASRU.2001.1034587 | SDG/關鍵字: | Data mining; Entropy; Linguistics; Entropy based approach; Mandarin Chinese; New approaches; Pronunciation modelling; Pronunciation variation; Word frequencies; Speech recognition |
顯示於: | 電信工程學研究所 |
檔案 | 描述 | 大小 | 格式 | |
---|---|---|---|---|
01034587.pdf | 369.38 kB | Adobe PDF | 檢視/開啟 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。