https://scholars.lib.ntu.edu.tw/handle/123456789/154985
標題: | A hierarchical tag-graph search scheme with layered grammar rules for spontaneous speech understanding | 作者: | Lin, Bor-shen Chen, Berlin Wang, Hsin-min LIN-SHAN LEE |
關鍵字: | Robustness; Speech understanding; Spontaneous speech; Tag-graph search | 公開日期: | 2002 | 卷: | 23 | 期: | 7 | 起(迄)頁: | 819-831 | 來源出版物: | Pattern Recognition Letters | 摘要: | It has always been difficult for language understanding systems to handle spontaneous speech with satisfactory robustness, primarily due to such problems as the fragments, disfluencies, out-of-vocabulary words, and ill-formed sentence structures. Also, the search schemes used are usually not flexible enough in accepting different input linguistic units, and great efforts are therefore required when they are used with different acoustic front ends in different tasks, specially in multi-modal and multi-lingual systems. In this paper, a new hierarchical tag-graph-based search scheme for spontaneous speech understanding is proposed. This scheme is based on a layered hierarchy of grammar rules, and therefore can integrate all the statistical and rule-based knowledge including acoustic scores, language model scores and grammar rules into the search process. More robust speech understanding is thus achievable. In addition, this scheme can accept graphs of different linguistic units such as phonemes, syllables, characters, words, spotted keywords, or phrases as the input, thus compatible to different acoustic front ends and multi-modal and multi-lingual applications can be easily developed. This search scheme has been successfully applied to a multi-domain, multi-modal dialogue system. © 2002 Elsevier Science B.V. All rights reserved. |
URI: | http://ntur.lib.ntu.edu.tw//handle/246246/142095 https://www.scopus.com/inward/record.uri?eid=2-s2.0-0036567728&doi=10.1016%2fS0167-8655%2801%2900158-1&partnerID=40&md5=20063c02355bc7f0eda6b603346cc08f |
ISSN: | 01678655 | DOI: | 10.1016/S0167-8655(01)00158-1 | SDG/關鍵字: | Audio acoustics; Graph theory; Vocabulary control; Grammer rules; Speech recognition; pattern 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。