[1]WANG Yu-xuan,NI Xun-bo,JIANG Feng.Discriminative training methods of HMM for sign language recognition[J].CAAI Transactions on Intelligent Systems,2007,2(1):80-84.
Copy

Discriminative training methods of HMM for sign language recognition

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 2 Number of periods: 2007 1 Page number: 80-84 Column: 学术论文—机器感知与模式识别 Public date: 2007-02-25
Title:
Discriminative training methods of HMM for sign language recognition
Author(s):
WANG Yu-xuan;  NI Xun-bo;  JIANG Feng
School of Computer Science, Harbin Institute of Technology, Harbin 150001, China
Keywords:
discriminative training; hidden Markov models;  mixture sets;  maximum mu tual information
CLC:
-
DOI:
-
Abstract:
The traditional method of training HMM (Hidden Markov Models) is based on MLE (maximum likelihood estimation). When training samples are sufficient en ough, the method can principally gain the optimal result. However, it is too dif ficult to get such large data sets practically, especially in sign language reco gnition. Discriminative training method can improve the error rate of MLE, which is caused by insufficient training data and similarities among sign language mo dels. Maximum mutual information estimation as one of discriminative training me thods has been widely applied in speech recognition. By taking competition model s into account and setting up mixture sets appropriately, MMIE method was improv ed and applied both in signerdependent and signerindependent sign language rec ognition. A great number of experiments had been taken, showing that this method greatly promoted the ability of the traditional MLE system.
References:
［1］ WANG Chunli, GAO Wen. Resampling for Chinese sign language recognition by genetic algorithm［A］.GW2005［C］.［s.l.］，2005.
［2］DENG J W, TSUI H T. A twostep approach based on PaHMM for the recognition o f ASL［A］. Proceedings of The Fifth Asian Conference on Computer Vision［C］. M elbourne, Australia, 2002.
［3］BAHLL R, BROWN P F, SOUZA P V, MERCER R L. Maximum mutual information esti ma tion of hidden Markov model parameters for speech recognition［A］. Proc . 1986 I nt. Conf. on Acoustics,Speech and Signal Processing ［C］.Tokyo,Japan1986.
?［4］NORMANDIN Y. An improved MMIE training algorithm for speaker independent［ A］. Proc. ICASSP’91［C］. Toronto,1991.
［5］SCHLUTER R,MACHEREY W,RULLER B, NEY H. Comparison of discriminat ive training criteria and optimization methods for speech recognition［J］. Spee ch Communication, 2001(34):287-310.
［6］ZHENG J，BUTZBERER J，FRANCO H. Scandinavia impro ved maximum mutual information es timation training of continuous density HMMs［J］.Andreas Stolcke Speech Technol ogy and Research Laboratory，2001,15(2):25-30.
［7］WOODLAND P C, POVEY D. Large scale discriminative training for speec h reco gnition［J］. In Proc. ITRW ASR［C］. ISCA, 2000.
［8］BAHL L R，PADMANABHAN M,NAHAMOO D,GOPALAKRISHNAN P S. An nbest candidatesbased discriminative training for speech recognition Applications［J］.IEEE Transactions on Speech and Audio Proce ssing, 1994,2(1):206-216.
［9］CHOW Y L.Maximum mutual information estimation of HMM paramet ers for continuous speech recognition using the NBest algorithm［A］. Proc. IC ASSP ’90［C］. Albuquerque，1990.
Similar References:

Memo

-

Last Update: 2009-05-05

Copyright © CAAI Transactions on Intelligent Systems