https://scholars.lib.ntu.edu.tw/handle/123456789/498659
標題: | Improved language model adaptation using existing and derived external resources | 作者: | Chang, P.-C. LIN-SHAN LEE |
公開日期: | 2003 | 起(迄)頁: | 531-536 | 來源出版物: | 2003 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003 | 會議論文: | IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2003 | 摘要: | Adaptation of language models to obtain better parameters for the topics addressed by the spoken documents to be recognized has been a key issue for speech recognition. In this paper, we propose to collect existing as well as derived external resources for improved language model adaptation. The derived external resources are those retrieved based on the baseline transcriptions for the input spoken documents from the Internet using some search engine. The design of queries for such purposes are also analyzed in this paper, in which the special structure of Chinese language is considered. The obtained existing and derived external resources are then used in the model adaptation under a Clustering-Classification framework. Very encouraging results were obtained in the preliminary experiments with two test sets: broadcast news and interview recording. © 2003 IEEE. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/498659 https://www.scopus.com/inward/record.uri?eid=2-s2.0-33846229912&doi=10.1109%2fASRU.2003.1318496&partnerID=40&md5=23e3900e25a6209d53340c22a14786ef |
DOI: | 10.1109/ASRU.2003.1318496 | SDG/關鍵字: | Computational linguistics; Search engines; Broadcast news; Chinese language; Clustering classifications; External resources; Language model adaptation; Model Adaptation; Special structure; Spoken document; Speech recognition |
顯示於: | 電機工程學系 |
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。