Generating identities with mixture models for speaker anonymization
Speaker anonymization methods are a growing research area, due to the common use of voice interfaces coupled with growing privacy requirements. However, existing systems suffer from several issues, in particular a reduction in the entropy space of the newly created voices. This is problematic as it...
Main Authors: | Turner, H, Lovisotto, G, Martinovic, I |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Elsevier
2021
|
Similar Items
-
Attacking speaker recognition systems with phoneme morphing
by: Turner, H, et al.
Published: (2019) -
Seeing red: PPG biometrics using smartphone cameras
by: Lovisotto, G, et al.
Published: (2020) -
Zero-Shot Unseen Speaker Anonymization via Voice Conversion
by: Hyung-Pil Chang, et al.
Published: (2022-01-01) -
Anonymity and non-identity cases
by: Francis, T
Published: (2021) -
Speaker Anonymization using End-to-End Zero-Shot Voice Conversion
by: Kang, Wonjune
Published: (2022)