Pseudonymize Speech

A Praat script to pseudonymize speech. That is, Pseudonymize Speech tries to make it difficult to recognize a speaker while still retaining relevant (para-)linguistic features and intelligibility. There is a trade-off between the level of pseudonymization and the (para-)linguistic features retained.

Manual

How to use the script.

Example listening experiment

Audio from: ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Xin Wang et al. https://doi.org/10.48550/arXiv.1911.01601

Pseudonymize Speech on Github

Articles

• Adjustable Deterministic Pseudonymization of Speech Listening Experiment, Report of listening experiments at Zenodo
• Adjustable Deterministic Pseudonymisation of Speech: Idiap-NKI’s submission to VoicePrivacy 2020 Challenge at Voice Privacy Challenge website