Mon-S&T-1-5 CATOTRON–A Neural Text-to-Speech System in Catalan

Abstract: We present Catotron, a neural network-based open-source speech synthesis system in Catalan. Catotron consists of a sequence-to-sequence model trained with two small opensource datasets based on semi-spontaneous and read speech. We demonstrate how a neural TTS can be built for languages with limited resources using found-data optimization and crosslingual transfer learning. We make the datasets, initial models and source code publicly available for both commercial and research purposes.