The operating branch runs a spoken dialogue system on the user’s device or on a personal server. The dialogue outcomes are sent to the company delivering the desired service only.
The training branch removes personal information from voice data using privacy driven text and voice transformers. The transformed data are sent to the COMPRISE Cloud-based Platform to train the spoken dialogue system.
- COMPRISE VOICE TRANSFORMER
- Prevents biometric identification of the user by converting his/her voice to
another random person’s voice while preserving the spoken message. - Based on cutting-edge deep learning and speech processing technology.
- Validated through state-of-the-art biometric protocols.
- Can be followed by the voice builder, which further discards sensitive words and expressions.
- Prevents biometric identification of the user by converting his/her voice to
- COMPRISE TEXT TRANSFORMER
- Replaces words and expressions carrying personal information by random alternatives while preserving the sentence structure.
- Applicable to all kinds of text documents in addition to spoken dialogues
- Based on cutting-edge deep learning and natural language processing technology.
- Provides formal differential privacy guarantees.
- Focuses on PER (persons’ names), ORG (organisations), LOC (locations), DATE and TIME.
Developer survey: Since you are here and interested in our project, could you please spare a moment to share your concerns and answer 12 questions related to developing voice-enabled apps.
