Compensation for the homogeneous assumption of classical HMM by probability penalty
-
Graphical Abstract
-
Abstract
The theoretical weakness of classical Hidden Markov Model (HMM), i.e. its homogeneous assumption and two inhomogeneous HMMs are studied in this paper. Control experbent for speeCh recognition shows that the penalty approach is robust and more effective in compensating this unreasonable assumption.
-
-