1st generation of SpeechLMM models, capable of ingesting video, audio and text and generate text as output. From the Meetween consortium (meetween.eu)
AI & ML interests
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.
Recent Activity
View all activity
Research papers published within the MEETWEEN project
-
Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?
Paper • 2402.12025 • Published • 2 -
StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection
Paper • 2406.06097 • Published • 2 -
SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
Paper • 2406.14177 • Published • 1 -
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
Paper • 2410.01036 • Published • 16
1st generation of SpeechLMM models, capable of ingesting video, audio and text and generate text as output. From the Meetween consortium (meetween.eu)
Research papers published within the MEETWEEN project
-
Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?
Paper • 2402.12025 • Published • 2 -
StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection
Paper • 2406.06097 • Published • 2 -
SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
Paper • 2406.14177 • Published • 1 -
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
Paper • 2410.01036 • Published • 16