A Waveform Representation Framework for High-quality Statistical Parametric Speech Synthesis
Abstract
State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Magnitude spectrum has been a dominant feature over the years. Although perceptual studies have shown that phase spectrum is essential to the quality of synthesized speech, it is often ignored by using a minimum phase filter during synthesis and the speech quality suffers. To bypass this bottleneck in vocoded speech, this paper proposes a phase-embedded waveform representation framework and establishes a magnitude-phase joint modeling platform for high-quality SPSS. Our experiments on waveform reconstruction show that the performance is better than that of the widely-used STRAIGHT. Furthermore, the proposed modeling and synthesis platform outperforms a leading-edge, vocoded, deep bidirectional long short-term memory recurrent neural network (DBLSTM-RNN)-based baseline system in various objective evaluation metrics conducted.
Cite
@article{arxiv.1510.01443,
title = {A Waveform Representation Framework for High-quality Statistical Parametric Speech Synthesis},
author = {Bo Fan and Siu Wa Lee and Xiaohai Tian and Lei Xie and Minghui Dong},
journal= {arXiv preprint arXiv:1510.01443},
year = {2015}
}
Comments
accepted and will appear in APSIPA2015; keywords: speech synthesis, LSTM-RNN, vocoder, phase, waveform, modeling