Meetween: My Personal AI Mediator for Virtual Meetings

Meetween is a project funded by the European Commission with the mission to build the AI-based technology solutions needed to power the next generation of video conferencing platforms to support smooth, engaging and barrier-free collaboration across languages, geographies and time zones.

Banner image
feature image

Ambition and Objectives

Meetween’s core objectives centre on creation and dissemination of open-source AI-based models and datasets aimed at enhancing human-human and human-machine interaction.

  • SpeechLMM: a multilingual AI model focussed on speech that supports text, audio and video both as inputs and outputs
  • Mumospee: the multimodal and multilingual dataset used for the training of SpeechLMM, with coverage of all official EU languages.
  • 20+ Specialised Downstream Models through adaptation of SpeechLMM targeting common use cases like speech translation or transcription.
  • SPEECHM: a suite of AI metrics that can be used to measure and track the performance of the task-specific models.