Đang chuẩn bị liên kết để tải về tài liệu:
báo cáo hóa học:" Research Article Automatic Query Generation and Query Relevance Measurement for Unsupervised Language Model Adaptation of Speech Recognition"

Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: Research Article Automatic Query Generation and Query Relevance Measurement for Unsupervised Language Model Adaptation of Speech Recognition | Hindawi Publishing Corporation EURASIP Journal on Audio Speech and Music Processing Volume 2009 Article ID 140575 12 pages doi 10.1155 2009 140575 Research Article Automatic Query Generation and Query Relevance Measurement for Unsupervised Language Model Adaptation of Speech Recognition Akinori Ito 1 Yasutomo Kajiura 1 Motoyuki Suzuki 2 and Shozo Makino1 1 Graduate School of Engineering Tohoku University 6-6-05 Aramaki aza Aoba Sendai 980-8579 Japan 2 Institute of Technology and Science University of Tokushima 2-1 Minamijosanjima-cho Tokushima Tokushima 770-8506 Japan Correspondence should be addressed to Akinori Ito aito@fw.ipsj.or.jp Received 3 December 2008 Revised 20 May 2009 Accepted 25 October 2009 Recommended by Horacio Franco We are developing a method of Web-based unsupervised language model adaptation for recognition of spoken documents. The proposed method chooses keywords from the preliminary recognition result and retrieves Web documents using the chosen keywords. A problem is that the selected keywords tend to contain misrecognized words. The proposed method introduces two new ideas for avoiding the effects of keywords derived from misrecognized words. The first idea is to compose multiple queries from selected keyword candidates so that the misrecognized words and correct words do not fall into one query. The second idea is that the number of Web documents downloaded for each query is determined according to the query relevance. Combining these two ideas we can alleviate bad effect of misrecognized keywords by decreasing the number of downloaded Web documents from queries that contain misrecognized keywords. Finally we examine a method of determining the number of iterative adaptations based on the recognition likelihood. Experiments have shown that the proposed stopping criterion can determine almost the optimum number of iterations. In the final experiment the word accuracy without adaptation 55.29 was improved to 60.38 which was 1.13 point better