Videos

What is Comprise?



Check out the first video of COMPRISE! It introduces the project, the problems addressed,and the partners involved.

Problems


Lack of privacy Non inclusiveness Cost – effectiveness

Solutions


 

COMPRISE SDK COMPRISE Voice Transformer COMPRISE Text transformer
COMPRISE Cloud Platform COMPRISE Weakly Supervised NLU COMPRISE Weakly Supervised STT
Interviews and media:

COMPRISE @France 3 TV Channel COMPRISE @Rue89 Strasbourg Marc Tommasi (Inria) explains how COMPRISE ensures privacy
Research results:

Brij Mohan Lal Srivastav (Inria): “Evaluating voice conversion based privacy protection against informed attackers” (ICASSP 2020 paper) David Adelani (University of Saarland): “Privacy guarantees for de-identifying text transformations” (Interspeech) Natalia Tomashenko: “Introducing the Voice Privacy Initiative” (Interspeech)
Imran Sheik (Inria): “On Semi Supervised LF MMI Training of Acoustic Models with Limited Data” (Interspeech) Mohamed Maouche (Inria): “A Comparative Study of Speech Anonymization Metrics” (Interspeech) Brij Mohan Lal Srivastava (Inria): “Design choices for x-vectors based speaker anonymization” (Interspeech)
Tugtekin Turan (from Inria): “Achieving multi-accent ASR via unsupervised acoustic model adaptation” (Interspeech) Mossad Helali (Saarland University): Assessing Unintended Memorization in Neural Discriminative Sequence Models” (Conference on TSD 2020) Aleena Thomas (Saarland University): “Investigating the impact of pre-trained word embeddings on memorization in neural networks” (Conference on TSD)

Comments are closed.