Recurrent Neural Network Postfilters for Statistical Parametric Speech Synthesis
This work addresses speech synthesis quality for applications like text-to-speech systems, but it is incremental as it builds on existing postfiltering methods.
The paper tackled the problem of improving speech synthesis by using Recurrent Neural Networks as postfilters, finding that this approach allowed for easy integration of new features and joint training with existing models.
In the last two years, there have been numerous papers that have looked into using Deep Neural Networks to replace the acoustic model in traditional statistical parametric speech synthesis. However, far less attention has been paid to approaches like DNN-based postfiltering where DNNs work in conjunction with traditional acoustic models. In this paper, we investigate the use of Recurrent Neural Networks as a potential postfilter for synthesis. We explore the possibility of replacing existing postfilters, as well as highlight the ease with which arbitrary new features can be added as input to the postfilter. We also tried a novel approach of jointly training the Classification And Regression Tree and the postfilter, rather than the traditional approach of training them independently.