Abstract | ||
---|---|---|
Based on the analysis and comparisons of complexity between stochastic segment model (SSM) and hidden Markov model (HMM) in this paper, we presented a fast and robust SSM, which yields a 94.75% speaker-independent performance on Mandarin digit string recognition. This result is better than HMM based system at the same level of computational complexity and just only a little slower than HNM in the running time. We also studied a region based discriminative method, which achieves 18.0% error rate reduction for substitution error and 95.08% accuracy for Mandarin digit string recognition. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/IJCNN.2008.4633987 | 2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8 |
Keywords | Field | DocType |
stochastic processes,hidden markov model,error rate,computational complexity,natural languages,artificial neural networks,robustness,speaker recognition,neural networks,hidden markov models | Computer science,Robustness (computer science),Speaker recognition,Artificial intelligence,Artificial neural network,Discriminative model,Pattern recognition,Word error rate,Stochastic process,Speech recognition,Hidden Markov model,Machine learning,Computational complexity theory | Conference |
ISSN | Citations | PageRank |
2161-4393 | 0 | 0.34 |
References | Authors | |
4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenju Liu | 1 | 214 | 39.32 |
Yun Tang | 2 | 7 | 2.73 |
Shouye Peng | 3 | 5 | 1.52 |