MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset
This provides a valuable resource for researchers working on low-resource language TTS, specifically for Mongolian, though it is incremental as it applies existing methods to new data.
The authors tackled the lack of open-source datasets for Mongolian text-to-speech synthesis by creating MnTTS2, a multi-speaker dataset with 30 hours of recordings from three professional announcers, which they showed is sufficient for building robust TTS models.
Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays. Mongolian is the official language of the Inner Mongolia Autonomous Region and a representative low-resource language spoken by over 10 million people worldwide. However, there is a relative lack of open-source datasets for Mongolian TTS. Therefore, we make public an open-source multi-speaker Mongolian TTS dataset, named MnTTS2, for the benefit of related researchers. In this work, we prepare the transcription from various topics and invite three professional Mongolian announcers to form a three-speaker TTS dataset, in which each announcer records 10 hours of speeches in Mongolian, resulting 30 hours in total. Furthermore, we build the baseline system based on the state-of-the-art FastSpeech2 model and HiFi-GAN vocoder. The experimental results suggest that the constructed MnTTS2 dataset is sufficient to build robust multi-speaker TTS models for real-world applications. The MnTTS2 dataset, training recipe, and pretrained models are released at: \url{https://github.com/ssmlkl/MnTTS2}