A multilingual training strategy for low resource Text to Speech
This addresses the scalability issue of TTS for low-resource languages, offering a practical solution for communities with limited data, though it is incremental as it builds on existing transfer learning techniques.
The paper tackled the problem of building Text-to-Speech (TTS) models for low-resource languages by investigating the use of social media data for dataset construction and cross-lingual transfer learning, finding that multilingual pre-training improves intelligibility and naturalness compared to monolingual approaches.
Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly scalable to all existing languages, especially that seldom attention is given to low resource languages. With techniques such as knowledge transfer, the burden of creating datasets can be alleviated. In this paper, we therefore investigate two aspects; firstly, whether data from social media can be used for a small TTS dataset construction, and secondly whether cross lingual transfer learning (TL) for a low resource language can work with this type of data. In this aspect, we specifically assess to what extent multilingual modeling can be leveraged as an alternative to training on monolingual corporas. To do so, we explore how data from foreign languages may be selected and pooled to train a TTS model for a target low resource language. Our findings show that multilingual pre-training is better than monolingual pre-training at increasing the intelligibility and naturalness of the generated speech.