DEEP NEURAL NETWORKS EMPLOYING MULTI-TASK LEARNING AND STACKED BOTTLENECK FEATURES FOR SPEECH SYNTHESIS Zhizheng Wu Cassia Valentini-Botinhao Oliver Watts Simon King Centre for Speech Technology Research, University of Edinburgh, United Kingdom ABSTRACT Deep neural networks (DNNs) use a cascade of hidden representa- tions to enable the learning of complex mappings from input to out- put features. They are able to learn the complex mapping from text- based linguistic features to speech acoustic features, and so perform text-to-speech synthesis. Recent results suggest that DNNs can pro- duce more natural synthetic speech than conventional HMM-based statistical parametric systems. In this paper, we show that the hidden representation used within a DNN can be improved through the use of Multi-Task Learning, and that stacking multiple frames of hid- den layer activations (stacked bottleneck features) also leads to im- provements. Experimental results confirmed the effectivene
