Nós-TTS : a Web User Interface for Galician Text-to-Speech
Carmen Magariños, Alp Öktem, Antonio Moscoso Sánchez, Marta Vázquez Abuín,
Noelia García Díaz, Adina Ioana Vladu, Elisa Fernández Rei, María Baqueiro Vidal
Nós-TTS: a Web User Interface for Galician Text-to-Speech
In Proceedings of the 16th International Conference on Computational Processing of Portuguese (PROPOR 2024),
March 12-15, 2024.
Abstract
Speech synthesis, also known as text-to-speech (TTS), aims to generate human-like speech from text. The recent emergence of end-to-end deep learning TTS models has led to impressive natural-sounding results. Nevertheless, expanding these models to multiple languages and speakers poses challenges, especially for low- or limited-resource languages. In this context, we introduce Nós-TTS, a user-friendly web interface for Galician TTS developed under the Nós project. The proposed interface offers a choice among three distinct voices trained on diverse conditions regarding data quantity, training approach, and input modality. Although in an experimental stage, informal listening tests have shown a satisfactory performance of the models.