Fig. 3From: Text-to-speech system for low-resource language using cross-lingual transfer learning and data augmentationTraining flow diagrams for our single-speaker TTS models. Transfer learning from the source languages to the target language is used, where a are models using only different amounts of the English dataset, b is a model using only the Japanese dataset, and c is a model using the entire datasets of both high-resource languagesBack to article page