A comparison of Vietnamese Statistical Parametric Speech Synthesis Systems

TL;DR

This paper compares four Vietnamese statistical parametric speech synthesis systems, evaluating their speech quality and efficiency, revealing that end-to-end systems offer the best quality but require GPU, while HMM is most efficient.

Contribution

It provides a comprehensive comparison of Vietnamese SPSS techniques, highlighting the trade-offs between speech quality and computational efficiency.

Findings

E2E systems achieved the highest speech quality.

HMM systems were the most computationally efficient.

GAN did not outperform DNN in quality.

Abstract

In recent years, statistical parametric speech synthesis (SPSS) systems have been widely utilized in many interactive speech-based systems (e.g.~Amazon's Alexa, Bose's headphones). To select a suitable SPSS system, both speech quality and performance efficiency (e.g.~decoding time) must be taken into account. In the paper, we compared four popular Vietnamese SPSS techniques using: 1) hidden Markov models (HMM), 2) deep neural networks (DNN), 3) generative adversarial networks (GAN), and 4) end-to-end (E2E) architectures, which consists of Tacontron~2 and WaveGlow vocoder in terms of speech quality and performance efficiency. We showed that the E2E systems accomplished the best quality, but required the power of GPU to achieve real-time performance. We also showed that the HMM-based system had inferior speech quality, but it was the most efficient system. Surprisingly, the E2E systems were more efficient than the DNN and GAN in inference on GPU. Surprisingly, the GAN-based system did not outperform the DNN in term of quality.