Recordings of speech contain much more than the spoken content (words), but also, e.g., the speaker identity, gender, emotional state, age, regional accent… All such personal, private information can potentially be estimated from speech data and then used for nefarious or unwanted purposes. The protection of privacy as regards speech data is still very underdeveloped on account of numerous challenges. Privacy enhancing technologies are hence needed to protect speech and language technology users by preventing the use of speech recordings for purposes for which the user has not given their consent.

Consortium

Université de Lorraine – LORIA – Multispeech	Eurecom	Avignon Université – LIA

Fundings