ArmanTTS single-speaker Persian dataset
This addresses the scarcity of Persian TTS resources, but it is incremental as it applies existing methods to a new language-specific dataset.
The paper tackled the lack of Persian text-to-speech datasets by introducing ArmanTTS, a single-speaker dataset, and achieved a MOS of 2.98 for synthetic speech using a Tacotron 2 and HiFi GAN model.
TTS, or text-to-speech, is a complicated process that can be accomplished through appropriate modeling using deep learning methods. In order to implement deep learning models, a suitable dataset is required. Since there is a scarce amount of work done in this field for the Persian language, this paper will introduce the single speaker dataset: ArmanTTS. We compared the characteristics of this dataset with those of various prevalent datasets to prove that ArmanTTS meets the necessary standards for teaching a Persian text-to-speech conversion model. We also combined the Tacotron 2 and HiFi GAN to design a model that can receive phonemes as input, with the output being the corresponding speech. 4.0 value of MOS was obtained from real speech, 3.87 value was obtained by the vocoder prediction and 2.98 value was reached with the synthetic speech generated by the TTS model.