The first FOSD-tacotron-2-based text-to-speech application for Vietnamese

Abstract

Recently, with the development and deployment of voicebots which help to minimize personnels at call centers, text-to-speech (TTS) systems supporting English and Chinese have attracted attentions of researchers and corporates worldwide. However, there is very limited published works in TTS developed for Vietnamese. Thus, this paper presents in detail the first Tacotron-2-based TTS application development for Vietnamese that utilizes the publicly available FPT open speech dataset (FOSD) containing approximately 30 hours of labeled audio files together with their transcripts. The dataset was made available by FPT Corporation with an open access license. A new cleaner was developed for supporting Vietnamese language rather than English which was provided by default in Mozilla TTS source code. After 225,000 training steps, the generated speeches have mean opinion score (MOS) well above the average value of 2.50 and center around 3.00 for both clearness and naturalness in a crowd-source survey.

Text-to-speech on health monitoring bracelet for the visually impaired

“…The purpose of this technology is to make computers able to communicate and interact with everyday spoken language. The use of TTS today has been widely practiced by researchers, such as to recognize Vietnamese directly [3] or through a voice Bot [4], recognizing Japanese and English [1], the use of this TTS can also be used to conduct interviews [5], used in agriculture [6], and also helpful for people with aphasia [7]. In the configuration process, the words are split into syllables using Indonesian language rules with the aim that the resulting sound can be heard in the Indonesian language.…”