Cross-validation EM training for robust parameter estimation
T Shinozaki, M Ostendorf - 2007 IEEE International Conference …, 2007 - ieeexplore.ieee.org
A new maximum likelihood training algorithm is proposed that compensates for weaknesses
of the EM algorithm by using cross-validation likelihood in the expectation step to avoid
overtraining. By using a set of sufficient statistics associated with a partitioning of the training
data, as in parallel EM, the algorithm has the same order of computational requirements as
the original EM algorithm. Analyses using a GMM with artificial data show the proposed
algorithm is more robust for overtraining than the conventional EM algorithm. Large …
of the EM algorithm by using cross-validation likelihood in the expectation step to avoid
overtraining. By using a set of sufficient statistics associated with a partitioning of the training
data, as in parallel EM, the algorithm has the same order of computational requirements as
the original EM algorithm. Analyses using a GMM with artificial data show the proposed
algorithm is more robust for overtraining than the conventional EM algorithm. Large …
Cross-Validation EM Training for Robust Parameter Estimation
M Ostendorf, T Shinozaki - … Conference on Acoustics, Speech and Signal …, 2007 - cir.nii.ac.jp
A new maximum likelihood training algorithm is proposed that compensates for weaknesses
of the EM algorithm by using cross-validation likelihood in the expectation step to avoid
overtraining. By using a set of sufficient statistics associated with a partitioning of the training
data, as in parallel EM, the algorithm has the same order of computational requirements as
the original EM algorithm. Analyses using a GMM with artificial data show the proposed
algorithm is more robust for overtraining than the conventional EM algorithm. Large …
of the EM algorithm by using cross-validation likelihood in the expectation step to avoid
overtraining. By using a set of sufficient statistics associated with a partitioning of the training
data, as in parallel EM, the algorithm has the same order of computational requirements as
the original EM algorithm. Analyses using a GMM with artificial data show the proposed
algorithm is more robust for overtraining than the conventional EM algorithm. Large …
Showing the best results for this search. See all results