Rooter

COMPRISE has just published an article titled “Anonymisation and Re-Identification Risk for Voice Data” in Volume 7 (2021), Issue 2 of the European Data Protection Law Review (EDPL). Check it out! compriseh2020.eu/published-e…

Companies in the field of speech and language technologies will significantly benefit from COMPRISE Weakly Supervised NLU! Its main value lies in the possibility it offers to reduce the need for manual data labelling or postediting youtube.com/watch?v=J0l5vx3q…

Companies in the field of speech and language technologies will greatly benefit from COMPRISE Weakly Supervised Speech-to-Text. Its main value is to reduce the need for manual transcription! youtube.com/watch?v=JpVWDNYA…

Check our new blog post:"Protecting User Privacy with Voice Conversion"! #voicefirst #privacy compriseh2020.eu/protecting-…

Fortunately to all SMEs out there, Weakly Supervised Learning has emerged as a cost-effective alternative to human labelling. Check our inforgraphic to learn more about it! #voicefirst #machinelearning compriseh2020.eu/reducing-th…

To better understand the difficulties of developers who are integrating voice-enabled features in their apps, we would like to ask you to spare a few minutes to answer a small survey. Find the survey at the following link! #voicefirst #voiceapps compriseh2020.eu/developer-s…

COMPRISE Speech-to-Text-Translation combines “Speech-to-Text” and “Machine Translation” in a smart way, to allow a user to speak his or her own language when interacting with a dialogue system that is internally designed for a different language. #voice compriseh2020.eu/discover-th…

Deliverable D5.1.b: "Updated data Protection and GDPR Requirements" is available now! The document analyses new published guidelines and works on the processing of personal data by voice technologies and provides recommendations on GDPR compliance. compriseh2020.eu/files/2021/…

Check our new blog post: "Ethics in voice technologies!" #ethics #voiceassistant compriseh2020.eu/ethics-in-v…

The COMPRISE Cloud Platform provides a highly scalable, open-source, cloud-based solution for the management of multilingual speech and text data and models. Check it out! youtube.com/watch?v=VhCZ4BIU…

The Accent Gap: What it is, and how to tackle it. Check our new infographic at the following link! #voicefirst #accentgap compriseh2020.eu/the-accent-…

The COMPRISE Cloud Platform provides a highly scalable, open-source, cloud-based solution for the management of multilingual speech and text data and models. Check it out! #voicefirst #multilingual #privacy compriseh2020.eu/the-compris…

Our deliverable "Cost-effective multilingual voice interaction " is now available online. This deliverable documents the advances on the COMPRISE weakly supervised learning library. Check it out! compriseh2020.eu/files/2021/…

Our deliverable "Final transformation library and privacy guarantees " is now available online. This deliverable closes the work on speech and text anonymisation in Comprise. Check it out! #privacy #anonymisation compriseh2020.eu/files/2021/…

The COMPRISE Cloud Platform has been released! Thanks to the COMPRISE Cloud Platform, developers can manage multilingual speech and text data and models to create multilingual, voice-enabled applications in a faster, cost-effective, privacy-driven way. compriseh2020.eu/comprise-cl…

"Multilingual personalised voice interaction" is now available! This deliverable is devoted to the presentation, evaluation and analysis of model personalisation strategies for Speech-to-Text, Spoken Language Understanding and Dialogue Management. compriseh2020.eu/files/2021/…

Check our new blog post: "Are voice-based technologies still important in 2021?"! compriseh2020.eu/are-voice-b…