May 26, 2020 · We showed that the E2E systems accomplished the best quality, but required the power of GPU to achieve real-time performance. We also showed ...

May 28, 2020 · We showed that the E2E systems accomplished the best quality, but required the power of GPU to achieve real-time performance. We also showed ...

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 ...

Deep learning has been a hot research topic in various machine learning related areas including general object recognition and automatic speech recognition.

A comparison of Vietnamese Statistical Parametric Speech Synthesis Systems. P. Kinh, V. Phung, A. Dinh, and Q. Nguyen. KSE, page 1-6. IEEE, (2020 ). 1. 1 ...

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 ...

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 ...

This article describes an approach in Vietnamese speech synthesis, using statistical parameters speech synthesis system based on hidden Markov models (HMMs) ...

A comparison of Vietnamese Statistical Parametric Speech Synthesis Systems. HK Phan, VL Phung, AT Dinh, QB Nguyen. 2020 12th International Conference on ...

Data Processing for Optimizing Naturalness of Vietnamese Text-to-speech System · A comparison of Vietnamese Statistical Parametric Speech Synthesis Systems.