Paper accepted at EMNLP 2024 – main track

Our paper in collaboration with the Machine Transaltion group: “Towards an Open-Source Speech Foundation Model for EU: 950,000 Hours of Open-Source Compliant Speech Data for EU Languages” will be presented in the main track of the forthcoming EMNLP conference in Miami.
The paper has been authroed by Marco Gaido, Sara Papi, Luisa Bentivogli, Alessio Brutti, Mauro Cettolo, Roberto Gretter, Marco Matassoni, Mohamed Nabih, Matteo Negri.