
Brain Imagined-Speech Communication
BINGO revolves around this intuitive paradigm that decodes human speech imagery from EEG signals aiming to explore and develop novel decoding frameworks that take advantage of the neural processes that underpin the imagined speech.
What is BINGO
BINGO is a project that aims to develop a Brain-Computer Interface (BCI) system that can decode imagined speech (speech that is thought but not spoken). To do this, the project will use cutting-edge machine learning techniques and a carefully designed experimental protocol. The project will also investigate the potential of imagined speech as an intuitive paradigm and will explore the possibility of expanding the vocabulary of imagined speech that can be decoded. In addition, the project will release a publicly available benchmarking framework to facilitate the comparison and validation of computational methods for imagined speech decoding.

To achieve our goals, BINGO sets its ground on three pillars
Neuro-informed approach: Algorithms tailored to the neural phenomena of imagined speech.
Robust decoding algorithms: Our approach will emphasize interpretability both
from the perspectives of conventional neuroscience and deep learning.
Imagined-speech BCI: Offering multiclass scalability, which can lead to high(er) degrees of freedom in a BCI system.
Latest News
Latest brain-to-text decoding results from Brain team at Meta-AI
Deep learning has enabled the decoding of language from intracranial brain recordings, but achieving this…
BINGO applies for a Sponsored Kaggle Competition!
We are pleased to share that we have submitted an application to host the BINGO…
Scientists aim to unveil the geometry of thought using LLMs
Language provides the most revealing window into the ways humans structure conceptual knowledge within cognitive…
