Date: Thursday 19/01/2023, 3:30 pm (GMT+2/Warsaw time)
Join online: zoom link
Join live: s. 3099, Wydział Geologii UW, ul. Żwirki i Wigury 93
Abstract
The main goal of this talk is to present the activities developed in the laboratory related to esophageal voices and silent interfaces. We will first describe a previously developed database of esophageal voices for Spanish as well as the main results obtained in voice conversion experiments. Then we will describe the project ReSSInt: the corpus, present state of the recordings, problems we have encountered while acquiring the data etc. We will also show our preliminary results in phone classification experiments.
To better follow the talk, you can read these publications:
- Inma Hernaez, Jose Andrés González-López, Eva Navas, Jose Luis Pérez Córdoba, Ibon Saratxaga, Gonzalo Olivares, Jon Sánchez de la Fuente, Alberto Galdón, Víctor García Romillo, Míriam González-Atienza, Tanja Schultz, Phil Green, Michael Wand, Ricard Marxer and Lorenz Diener. (2021). Voice Restoration with Silent Speech Interfaces (ReSSInt). Proc. IberSPEECH 2021, 130-134, doi: 10.21437/IberSPEECH.2021-28. [PDF]
- Eder Del Blanco, Inge Salomons, Eva Navas, Inma Hernáez. (2022). Phone classification using electromyographic signals. Proc. IberSPEECH 2022, 31-35, doi: 10.21437/IberSPEECH.2022-7. [PDF]
- Luis Serrano García, Sneha Raman, Inma Hernáez Rioja, Eva Navas Cordón, Jon Sanchez, Ibon Saratxaga (2021). A Spanish multispeaker database of esophageal speech. Computer Speech & Language, 66, March 2021. [PDF]
This talk is a part of the Traincrease Lecture Series (D4.2).
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 952324.
