Parametric Representation for Singing Voice Synthesis: a Comparative Evaluation

Autor: Babacan, Onur, Drugman, Thomas, Raitio, Tuomo, Erro, Daniel, Dutoit, Thierry

Various parametric representations have been proposed to model the speech signal. While the performance of such vocoders is well-known in the context of speech processing, their extrapolation to singing voice synthesis might not be straightforward. T

Externí odkaz: http://arxiv.org/abs/2006.04142

Reversible speaker de-identification using pre-trained transformation functions

Autor: Magariños, Carmen, Lopez-Otero, Paula, Docio-Fernandez, Laura, Rodriguez-Banga, Eduardo, Erro, Daniel, Garcia-Mateo, Carmen

Publikováno v: In Computer Speech & Language November 2017 46:36-52

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

IV Jornadas de Reconocimiento Biométrico de Personas

Autor: Farrús, Mireia, Erro, Daniel, Hernando, Javier

Publikováno v: Recercat. Dipósit de la Recerca de Catalunya
instname
UVaDOC. Repositorio Documental de la Universidad de Valladolid

Producción Científica
Security systems relying on voice identification can be threatened by human voice imitation or synthetic voices. As voice conversion can be seen as a sort of voice imitation, this paper analyses the performance of an auto

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::394af543745745dd7bba8306f4ad68d1

Reversible Speech De-identification Using Parametric Transformations and Watermarking.

Autor: Valdivielso, Aitor, Erro, Daniel, Hernaez, Inma

Publikováno v: Advances in Speech & Language Technologies for Iberian Languages: Third International Conference, IberSPEECH 2016, Lisbon, Portugal, November 23-25, 2016, Proceedings; 2016, p266-275, 10p