We are glad to announce that the following paper, authored by our MT Group at FBK, has been accepted at the INTERSPEECH 2024 conference:
As part of this work, we have already open sourced the dataset and the code for baseline End-to-end (E2E) SLU models
- Speech-MASSIVE dataset [FBK-MT resource, HuggingFace]
- End-to-end (E2E) SLU model baseline code using Speech-MASSIVE [FBK-MT github]
If you want to know more about our work, don’t hesitate to look for us at Interspeech 2024.
On Monday, September 2nd, from 4:00 to 4:20 pm:
- “Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond“, Beomseok Lee, Ioan Calapodescu, Marco Gaido, Matteo Negri, Laurent Besacier
- Location: Iasso Room
Our work has been nominated for the ISCA Best Student Paper Award 2024. (PaperID-957)
