no code implementations • 18 Feb 2015 • Sankar Mukherjee, Shyamal Kumar Das Mandal
In this paper, Deep Belief Network (DBN), a class of DNN family has been employed and applied to model the F0 contour of synthesized speech which was generated by HMM-based speech synthesis system.
no code implementations • 16 Jun 2014 • Sankar Mukherjee, Shyamal Kumar Das Mandal
In this synthesis method, trajectories of speech parameters are generated from the trained Hidden Markov Models.