1. Deep recurrent neural networks in speech synthesis using a continuous vocoder;Al-Radhi,2017
2. Time-domain envelope modulating the noise component of excitation in a continuous residual-based vocoder for statistical parametric speech synthesis;Al-Radhi,2017
3. Deep voice: Real-time neural text-to-speech;Arik,2017
4. High fidelity speech synthesis with adversarial networks;Binkowski,2020
5. A deep generative architecture for postfiltering in statistical parametric speech synthesis;Chen;IEEE Trans. Audio Speech Lang. Process.,2015