In this paper, we investigate a combination of several feed-forward deep neural networks (DNNs) for a high-quality statistical parametric speech synthesis system. Recently, DNNs have significantly improved the performance of essential components in the statistical parametric speech synthesis, e.g. spectral feature extraction, acoustic modeling and spectral post-filter. In this paper our proposed technique combines these feed-forward DNNs so that the DNNs can perform all standard steps of the statistical speech synthesis from end to end, including the feature extraction from STRAIGHT spectral amplitudes, acoustic modeling, smooth trajectory generation and spectral post-filter. The proposed DNN-based speech synthesis system is then compared to the state-of-the-art speech synthesis systems, i.e. conventional HMM-based, DNN-based and unit selection ones.
Bibliographic reference. Takaki, Shinji / Kim, SangJin / Yamagishi, Junichi / Kim, JongJin (2015): "Multiple feed-forward deep neural networks for statistical parametric speech synthesis", In INTERSPEECH-2015, 2242-2246.