CATOTRON – A Neural text-to-speech system in catalan

Külebi, Baybars; Öktem, Alp; Peiró Lilja, Àlex; Pascual, Santiago; Farrús, Mireia

CATOTRON – A Neural text-to-speech system in catalan

Citation

Külebi B, Öktem A, Peiró-Lilja A, Pascual S, Farrús M. CATOTRON – A Neural text-to-speech system in catalan. In: Proceedings of Interspeech 2020; 2020 Oct 25-29; Shanghai, China. [Baixas]: ISCA; 2020. p. 490-1.

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.