Pekar Darko Jovan

Publications in Math-Net.Ru

1. Style-code method for multi-style parametric text-to-speech synthesis
   
   Tr. SPIIRAN, 60 (2018),  216–240
2. Learning prosodic stress from data in neural network based text-to-speech synthesis
   
   Tr. SPIIRAN, 59 (2018),  192–215
3. Improvements in Serbian speech recognition using sequence-trained deep neural networks
   
   Tr. SPIIRAN, 58 (2018),  53–76