Miraç Göksu Öztürk

DNN-based Speaker-adaptive Postfiltering with Limited Adaptation Data for Statistical Speech Synthesis Systems

Deep neural networks (DNNs) have been successfully deployed for acoustic modelling in statistical parametric speech synthesis (SPSS) systems. Moreover, DNN-based postfilters (PF) have also been shown to outperform conventional postfilters that are widely used in SPSS systems for increasing the quali…