Knowledge Integration for Improving Performance in LVCSR
檔案
本條目沒有附加檔案。
日期
2013-01-01
類型
系所
期刊名稱
14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5
卷期與頁次
頁 1785–1789
ISSN
2308-457X
語言
英文
摘要
This paper presents a knowledge integration framework to improve performance in large vocabulary continuous speech recognition. Two types of knowledge sources, manner attribute and prosodic structure, are incorporated. For manner of articulation, six attribute detectors trained with an American English corpus (WSJO) are utilized to rescore hypothesized phones in word lattices obtained by a baseline ASR system. For the prosodic structure, models trained with an unsupervised joint prosody labeling and modeling (PLM) technique using WSJO are used in lattice rescoring. Experimental results on the American English WSJ word recognition task of the Nov92 test set show that the proposed approach significantly outperforms the baseline system that does not use articulatory and prosodic information. The results also demonstrate the effectiveness and usefulness of the PLM technique in constructing prosodic models for American English ASR.
所屬典藏
會議論文引用此條目
Chiang, C.-Y., Siniscalchi, S. M., Chen, S.-H., & Lee, C.-H. (2013). Knowledge Integration for Improving Performance in LVCSR. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 1785–1789. https://ir.lib.nycu.edu.tw/handle/11536/146414
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/146414