Abstract | ||
---|---|---|
This paper presents a comparative study of two discriminative methods, i.e., Rival Penalized Competitive Learning (RPCL) and Minimum Classification Error (MCE), for the tasks of Large Vocabulary Continuous Speech Recognition (LVCSR). MCE aims at minimizing a smoothed sentence error on training data, while RPCL focuses on avoiding misclassification through enforcing the learning of correct class and de-learning its best rival class. For a fair comparison, both the two discriminative mechanisms are implemented at the levels of phones and/or hidden Markov states using the same training corpus. The results show that both the MCE and RPCL based methods perform better than the Maximum Likelihood Estimation (MLE) based method. Comparing with the MCE based method, the RPCL based methods have better discriminative and generalizing abilities on both two levels. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1016/j.neucom.2013.05.060 | Neurocomputing |
Keywords | Field | DocType |
training data,comparative study,training corpus,discriminative mechanism,discriminative method,large vocabulary continuous speech,best rival class,maximum likelihood estimation,correct class,better discriminative,discriminative training method,minimum classification error | Competitive learning,Computer science,Maximum likelihood,Artificial intelligence,Discriminative model,Training set,Pattern recognition,Generalization,Speech recognition,Hidden Markov model,Vocabulary,Sentence,Machine learning | Journal |
Volume | ISSN | Citations |
134, | 0925-2312 | 0 |
PageRank | References | Authors |
0.34 | 9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zaihu Pang | 1 | 11 | 1.96 |
Shikui Tu | 2 | 39 | 14.25 |
Xihong Wu | 3 | 279 | 53.02 |
Lei Xu | 4 | 3590 | 387.32 |