模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2011, Vol. 24 Issue (2): 249-254    DOI:
Orignal Article Current Issue| Next Issue| Archive| Adv Search |
Modified Katz Approach and Its Application in Speech Recognition Based on Lattice
ZHANG Lei, LU Dong, XIANG Xue-Zhi
College of Information and Communication Engineering, Harbin Engineering University,Harbin 150001

Download: PDF (351 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  In traditional Katz approach, the discount coefficients may be greater than 1 or can not be calculated in some serious conditions. The idea of smoothing in log domain of couple occurrence number in simple good-turing is adopted. The modified Katz approach is proposed combined with back-off model. The proposed approach is further applied in speech recognition system based on lattice. The analysis of the effects on the structure and performance of lattice with different language models is given. Experiments show that the modified Katz approach enhances the system performance compared with traditional Katz approach. The best recognition rate achieves 60.90% for the corpus from interview program.
Key wordsModified Katz      Smoothing in Log Domain      Lattice      Speech Recognition     
Received: 09 October 2009     
ZTFLH: TP181  
  TP391.4  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHANG Lei
LU Dong
XIANG Xue-Zhi
Cite this article:   
ZHANG Lei,LU Dong,XIANG Xue-Zhi. Modified Katz Approach and Its Application in Speech Recognition Based on Lattice[J]. , 2011, 24(2): 249-254.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2011/V24/I2/249
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn