Published January 28, 2021
| Version 1
Presentation
Open
Use voice conversion for pseudonymisation?
Creators
- 1. Netherlands Cancer Institute, Amsterdam & ACLC, University of Amsterdam
Contributors
Project members:
- 1. École Polytechnique Fédérale de Lausanne: Lausanne, VD, CH
- 2. Idiap Research Institute: Martigny, CH
Description
Sharing speech data is needed for progress in speech science&technology. Privacy is a concern, especially for pathological speech. The question is discussed whether pseudonymization is possible such that the identity of the speaker is obscured but linguistic & para-linguistic features of the speech are retained. Possible applications are demonstrations for live audience, speech corpora for study, generating fully Open Data, and protection during speech processing in the cloud.
Notes
The ZIP file contains the presentation PDF, LaTeX Beamer code, figures, and Audio files. Opening the presentation PDF in Acrobat Reader, Skim, or Evince will allow to play the audio during the presentation. Other PDF readers were not tested.
Files
DELAD_012021.zip
Files
(14.3 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:bf04ba5c2949d04e27dc9a90ab326c02
|
9.9 MB | Preview Download |
|
md5:013913c886f7bc6385cd4116cf9f7210
|
4.4 MB | Preview Download |
Additional details
Related works
- References
- Software: 10.5281/zenodo.4454183 (DOI)
- Software: 10.5281/zenodo.3773951 (DOI)
- Dataset: 10.5281/zenodo.3773936 (DOI)