Data Processing for Optimizing Naturalness of Vietnamese Text-to-speech System

End-to-end text-to-speech (TTS) systems has proved its great success in the presence of a large amount of high-quality training data recorded in an anechoic room with high-quality microphones. Another approach is to use available source of found data like radio broadcast news. We aim to optimize the naturalness of TTS system on the found data using a novel data processing method. The data processing method includes 1) utterance selection and 2) prosodic punctuation insertion to prepare training data which can optimize the naturalness of TTS systems. We showed that using the processing data method, an end-to-end TTS achieved a mean opinion score (MOS) of 4.1 compared to 4.3 of natural speech. We showed that the punctuation insertion contributed the most to the result. To facilitate the research and development of TTS systems, we distributed the processed data, which is known as Zalo-TTS database at https://forms.gle/6Hk5YkqgDxAaC2BU6; It consists of 18-hours of speech at a sampling rate of 44.1 kHz of one speaker with Hanoi dialect.