Speech Synthesis Based on Hidden Markov Models

Citations Over TimeTop 1% of 2013 papers

Abstract

This paper gives a general overview of hidden Markov model (HMM)-based speech synthesis, which has recently been demonstrated to be very effective in synthesizing speech. The main advantage of this approach is its flexibility in changing speaker identities, emotions, and speaking styles. This paper also discusses the relation between the HMM-based approach and the more conventional unit-selection approach that has dominated over the last decades. Finally, advanced techniques for future developments are described.

Related Papers

• → Hidden semi-Markov model based speech synthesis(2004)132 cited
• → Reducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion(2017)6 cited
• → Hidden Markov Model(2015)3 cited
• → Explicit duration modelling in HMM-based speech synthesis using continuous hidden Markov Model(2012)4 cited
• → Hidden Markov Model ( HMM , Hidden Semi‐Markov Models, Profile Hidden Markov Models, Training of Hidden Markov Models, Dynamic Programming, Pair Hidden Markov Models)(2004)2 cited