A Waveform Representation Framework for High-quality Statistical Parametric Speech Synthesis

TL;DR

This paper introduces a waveform representation framework that incorporates phase information into statistical parametric speech synthesis, significantly improving speech quality over traditional vocoder-based methods.

Contribution

It proposes a novel phase-embedded waveform representation and joint modeling platform that enhances speech synthesis quality beyond existing vocoded and neural network approaches.

Findings

Outperforms STRAIGHT in waveform reconstruction quality.

Surpasses DBLSTM-RNN baseline in multiple objective metrics.

Demonstrates the importance of phase information in high-quality 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.