论文标题
越南统计参数语音合成系统的比较
A comparison of Vietnamese Statistical Parametric Speech Synthesis Systems
论文作者
论文摘要
近年来，统计参数语音合成（SPSS）系统已在许多基于交互式语音的系统（例如〜Amazon的Alexa，Bose的耳机）中广泛使用。要选择合适的SPSS系统，必须考虑语音质量和性能效率（例如〜解码时间）。 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.我们表明，E2E系统达到了最佳质量，但需要GPU实现实时性能的力量。我们还表明，基于HMM的系统的语音质量较低，但这是最有效的系统。令人惊讶的是，在推断GPU时，E2E系统比DNN和GAN更有效。令人惊讶的是，基于GAN的系统在质量方面并没有胜过DNN。
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.
