Loading...
Search for:
overlapped-context-clusters
0.005 seconds
Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis
, Article Eurasip Journal on Audio, Speech, and Music Processing ; Vol. 2014, Issue. 1 , 2014 ; ISSN: 1687-4714 ; Sameti, H ; Bahmaninezhad, F ; King, S ; Drugman, T ; Sharif University of Technology
Abstract
Decision tree-clustered context-dependent hidden semi-Markov models (HSMMs) are typically used in statistical parametric speech synthesis to represent probability densities of acoustic features given contextual factors. This paper addresses three major limitations of this decision tree-based structure: (i) The decision tree structure lacks adequate context generalization. (ii) It is unable to express complex context dependencies. (iii) Parameters generated from this structure represent sudden transitions between adjacent states. In order to alleviate the above limitations, many former papers applied multiple decision trees with an additive assumption over those trees. Similarly, the current...