ISCA Archive Blizzard 2021
ISCA Archive Blizzard 2021

VRAIN-UPV MLLP’s system for the Blizzard Challenge 2021

Alejandro Pérez-González-de-Martos, Albert Sanchis, Alfons Juan

This paper presents the VRAIN-UPV MLLP’s speech synthesis system for the SH1 task of the Blizzard Challenge 2021. The SH1 task consisted in building a Spanish text-to-speech system trained on (but not limited to) the corpus released by the Blizzard Challenge 2021 organization. It included 5 hours of studio-quality recordings from a native Spanish female speaker. In our case, this dataset was solely used to build a two-stage neural text-to-speech pipeline composed of a non-autoregressive acoustic model with explicit duration modeling and a HiFi-GAN neural vocoder. Our team is identified as J in the evaluation results. Our system obtained very good results in the subjective evaluation tests. Only one system among other 11 participants achieved better naturalness than ours. Concretely, it achieved a naturalness MOS of 3.61 compared to 4.21 for real samples.

doi: 10.21437/Blizzard.2021-5

Cite as: Pérez-González-de-Martos, A., Sanchis, A., Juan, A. (2021) VRAIN-UPV MLLP’s system for the Blizzard Challenge 2021. Proc. The Blizzard Challenge 2021, 31-35, doi: 10.21437/Blizzard.2021-5

  author={Alejandro Pérez-González-de-Martos and Albert Sanchis and Alfons Juan},
  title={{VRAIN-UPV MLLP’s system for the Blizzard Challenge 2021}},
  booktitle={Proc. The Blizzard Challenge 2021},