Voice production models provide valuable information about the human voice generation. However, providing them with expressiveness remains a challenge. This work proposes a …
M Arnela, O Guasch - IEEE/ACM Transactions on Audio …, 2024 - ieeexplore.ieee.org
Nowadays it is possible to acquire three-dimensional (3D) geometries of the vocal tract by means of Magnetic Resonance Imaging (MRI) and introduce them into a 3D acoustic model …
The source-filter model is one of the main techniques applied to speech analysis and synthesis. Recent advances in voice production by means of three-dimensional (3D) source …
Porozumění vzniku a modelaci hlasového projevu člověku je nezbytným předpokladem pro nalezení odpovědí na otázky pokládané klinickou praxí. S ohledem na potřeby hlasových …
The GENIOVOX project:“Computational synthesis of expressive voice”, with ref. TEC2016- 81107-P and funded by the Ministerio de Economía, Industria y Competitividad (Plan …
This document presents the research project TIN2017-88858-C2-1-R of the Spanish Government for the incorporation of a module for automatic prediction of oral productions …
M Arnela - Computational Analysis and Simulation of the Human … - drops.dagstuhl.de
This talk introduces a methodology for tuning formants in 3D vocal tract geometries obtained via MRI to produce specific voice or singing effects. The process involves converting 3D MRI …