Requirements and Motivations of Low-Resource Speech Synthesis for Language Revitalization

Abstract

This paper describes the motivation and development of speech synthesis systems for the purposes of language revitalization. By building speech synthesis systems for three Indigenous languages spoken in Canada, Kanien'kéha, Gitksan & SENCOTEN, we re-evaluate the question of how much data is required to build low-resource speech synthesis systems featuring state-of-the-art neural models. For example, preliminary results with English data show that a FastSpeech2 model trained with 1 hour of training data can produce speech with comparable naturalness to a Tacotron2 model trained with 10 hours of data. Finally, we motivate future research in evaluation and classroom integration in the field of speech synthesis for language revitalization.