Loading...
Search for:
gaussian-conditional-random-field
0.006 seconds
Speech synthesis based on gaussian conditional random fields
, Article Communications in Computer and Information Science ; Vol. 427, issue , 2014 , p. 183-193 ; Bahmaninezhad, F ; Sameti, H ; Sharif University of Technology
Abstract
Hidden Markov Model (HMM)-based synthesis (HTS) has recently been confirmed to be the most effective method in generating natural speech. However, it lacks adequate context generalization when the training data is limited. As a solution, current study provides a new context-dependent speech modeling framework based on the Gaussian Conditional Random Field (GCRF) theory. By applying this model, an innovative speech synthesis system has been developed which can be viewed as an extension of Context-Dependent Hidden Semi Markov Model (CD-HSMM). A novel Viterbi decoder along with a stochastic gradient ascent algorithm was applied to train model parameters. Also, a fast and efficient parameter...
Improving Speech Signal Models for Statistical Parametric Speech Synthesis
, Ph.D. Dissertation Sharif University of Technology ; Sameti, Hossein (Supervisor)
Abstract
Statistical parametric speech synthesis (SPSS) has dominated speech synthesis research area over the last decade, due to its remarkable advantages such as high intelligibility and flexibility. Decision tree-clustered context-dependent hidden semi-Markov models are typically used in SPSS to represent probability densities of acoustic features given contextual factors. This research addresses four major limitations of this decision tree-based structure: (a) The decision tree structure lacks adequate context generalization; (b) It is unable to express complex context dependencies; (c) Parameters generated from this structure represent sudden transitions between adjacent states; (e) This...