Abstract | ||
---|---|---|
In this paper, we propose two methods of obtaining a parallel-branch subunit model for improved recognition performance. In one method, the model is obtained by adding a new subunit branch based on misrecognized data in training to the previous parallel branches for that submit. In the other method, it is obtained by splitting off each subunit branch based on mixture components in continuous hidden Markov model. We propose to use a good initialization point obtained by error corrective estimation rather than by random or probabilistic statistics in the parallel-branch model when the number of mixtures and parallel branches increases |
Year | DOI | Venue |
---|---|---|
1996 | 10.1109/89.506932 | IEEE Transactions on Speech and Audio Processing |
Keywords | Field | DocType |
error correction,hidden Markov models,maximum likelihood estimation,speech recognition,continuous HMM,continuous hidden Markov model,error corrective estimation,misrecognized data,mixture components,parallel-branch subunit model,speech recognition performance,training | Pattern recognition,Markov model,Computer science,Maximum likelihood,Speech recognition,Error detection and correction,Artificial intelligence,Initialization,Probabilistic logic,Hidden Markov model | Journal |
Volume | Issue | ISSN |
4 | 4 | 1063-6676 |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Park, Y.K. | 1 | 0 | 0.34 |
C. K. Un | 2 | 249 | 70.41 |