Abstract | ||
---|---|---|
In this paper, we extend the Hierarchical Mixtures of Experts (HME) to temporal processing and explore it for a substantial problem, that of text-dependent speaker id entification. For a specific multiway classification, we propose a generalized Bernoulli density instead of the multinomial logit density to avoid the instability during training. Time-delay technique is appl ied for spatio-temporal processing in the HME and a combining scheme is presented for combining multiple time-delay HMEs in order to complete multi-scale analysis for the temporal data. Using the time-d elay HME along with the EM algorithm as well as the combination of multiple time-delay HMEs, the speaker identification system has a good performance and yields significantly fast training. We have als o addressed some issues about the time-delay techniques in the HME. |
Year | Venue | Keywords |
---|---|---|
1996 | Int. J. Neural Syst. | temporal data,multinomial logit,em algorithm |
Field | DocType | Volume |
Speaker identification,Pattern recognition,Expectation–maximization algorithm,Computer science,Multinomial logistic regression,Speech recognition,Temporal database,Mixture of experts,Artificial intelligence,Machine learning,Bernoulli's principle | Journal | 7 |
Issue | Citations | PageRank |
1 | 11 | 1.59 |
References | Authors | |
16 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ke Chen | 1 | 750 | 60.37 |
Dahong Xie | 2 | 42 | 5.34 |
Huisheng Chi | 3 | 211 | 22.81 |