Neurona-sareetan onarritutako sintesi-ahots pertsonalizatuen hobekuntzen garapena eta ebaluazioa

Authors

  • Iñigo Hierro Muga University of the Basque Country (UPV/EHU)
  • Ibon Saratxaga Couceiro University of the Basque Country (UPV/EHU)
  • Inma Hernáez Rioja University of the Basque Country (UPV/EHU)
  • Ander Arriandiaga Laresgoiti University of the Basque Country (UPV/EHU)
  • Victor Garcia Romillo University of the Basque Country (UPV/EHU)

DOI:

https://doi.org/10.26876/ikergazte.vi.03.29

Keywords:

Speech synthesis, Text-to-Speech, neural networks, personalization of synthesis voices

Abstract

With the growth of Artificial Intelligence neural network based speech synthesis models that improve the results of previous have been created. The personalization of speech synthesis is a solution to the high number of resources needed to train speech synthesis that offers a new approach to getting synthetic voices. In this paper, we present the evaluation and improvements of the personalization of a state of the art Text-to-Speech (TTS) model.

License

Copyright (c) 2025 IkerGazte. Nazioarteko ikerketa euskaraz

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Downloads

Published

2025-05-30

How to Cite

Hierro Muga, I., Saratxaga Couceiro, I., Hernáez Rioja, I., Arriandiaga Laresgoiti, A., & Garcia Romillo, V. (2025). Neurona-sareetan onarritutako sintesi-ahots pertsonalizatuen hobekuntzen garapena eta ebaluazioa. IkerGazte. Nazioarteko Ikerketa Euskaraz, 3, 235–242. https://doi.org/10.26876/ikergazte.vi.03.29

Conference Proceedings Volume

Vol. 3 (2025): VI. Ikergazte. Nazioarteko ikerketa euskaraz. Kongresuko artikulu bilduma. Ingeniaritza eta Arkitektura

Section

Artikuluak

Categories