Structure

Description of work

T1.1 – Administrative and financial management (M1-M24)

The administrative management concerns the communication with the funding agency, arrangements with the Host Institution and Collaborating Organizations, as well as interactions between members in the team. The financial management entails the establishment of a plan ensuring that the expected income, expenditure and disbursements are clear and verifiable. It also includes reviewing the financial status and creating the yearly budgets.

T1.2 – Technical management and quality assurance (M1-M24)

Εnsures that all WPs stay on course and react to unexpected events. Throughout the project there will be a cycle consisting of authorizing work to be done, gathering progress information, watching for changes, reviewing the situation, reporting and taking any necessary corrective action. T1.2 covers these activities, together with contingency planning.

T1.3 – Ethical, legal and privacy requirements and guidelines for implementation (M1-M24)

This task will supervise all data-related activities for the whole duration of the project to ensure that the project activities are in-line with the EU regulations in terms of ethical, legal and privacy practices and will abide to the neurorights proposed by the NeuroRights Foundation. Finally, this task will be responsible for getting ethical approvals for all data collection processes (from the designated ethical committee).

Description of Work

T2.1 – Investigating existing practices (M1-M5)

The purpose of this task is threefold as it aims to the investigation of the most suitable methods for imagined speech decoding, the understanding of the underlying neural mechanisms of imagined speech and the identification of publicly available EEG-based datasets for imagined speech decoding, that are considered as crucial aspects towards the development of informed decoding algorithms. Extra attention will be paid to Deep Learning approaches given the nature of the task, but also considering that such approaches will be more efficient, robust and easy to adapt to the needs of the incremental vocabulary generation (see T2.3).

T2.2 – Neuro-informed imagined speech decoding algorithms (M6-M21)

This task aims at the design of neuro-informed algorithms for imagined speech decoding. The developed algorithms will leverage both the knowledge gained as part of T2.1 and the team’s expertise in the decoding process of similar mental tasks (e.g. motor imagery, mental arithmetic). The neuro-informed algorithms will be firstly evaluated on existing datasets (identified by T2.1) and then adapted for the in-house dataset generated as part of T3.2.

T2.3 – Incremental Learning for Vocabulary Expansion (M8-M21)

T2.3 aims at enriching existing vocabularies with extra prompts. Within this context, incremental learning approaches will be employed to investigate the potential of multiclass scalability of the algorithmic frameworks developed in T2.2, with the main target being the robust extensibility of the imagined speech vocabulary.

T2.4 – Interconnection between languages (M15-M21)

This task will explore the semantics of the imagined speech, aiming to identify commonalities and differences between words of identical meaning in different languages (i.e., Greek and English). This may shed light to the existing neuroscientific hypotheses with respect to the imagined speech paradigm or even give rise to new ones. Finally, we must note here that this task is highly dependent on tasks T3.1 and T3.2 as to the best of our knowledge publicly available datasets that contain bilingual mental imagery speech data do not exist.

T2.5 – Imagined Speech decoding Toolbox (M15-M24)

This task will gather the different methods, modules and pre-trained models developed and employed as part of WP2 (i.e. T2.2 –T2.4) in an open-source, properly documented and ready-to-use toolbox, accessed via a publicly available repository.

Description of Work

T3.1 – Data Collection Protocol (M6-M14)

Aims to formulate the data collection protocol. The protocol will be defined based on both the knowledge gained as part of T2.1 and literature review, including among others the provided cue/stimulus, the type and number of the imagined words/phonemes and the words that will be explored as part of the activities of T2.4. Additionally, the protocol must be formulated in such a way that it will facilitate the investigation towards an incremental vocabulary as well as cross-session testing. Finally, synchronization mechanisms, like LSL, will be explored, aiming to record the available data streams (i.e., cue/stimulus, EEG, timestamps) in a synchronous fashion.

T3.2 – Data Recording (M10-M21)

This task materializes the data collection protocol(s) developed in T3.1 and includes the recording of the EEG data for at least 30 participants. Following the standard practice of EEG research in social science and humanities involving working with human participants, the written informed consent will be obtained for all participants, and their personal data will be privately stored. Finally, the whole process will be oriented towards neuroprotection (i.e. the explicit protection of neurorights) based on the practices identified by T1.3.

T3.3 – Evaluation Plan (M15-M24)

This task is dedicated to the evaluation of the BINGO’s developed algorithms, with respect to the imagined speech decoding, incremental vocabulary learning and interconnection between languages. In this direction, an early prototype will be developed in order to support the online system evaluation. The evaluation will be based upon both existing measurements (e.g. classification accuracy, ITR, etc.) and on metrics identified as part of this task, appropriately tailored to imagined speech decoding, that will allow us to establish a benchmarking framework. Finally, a comparison with existing SoTA imagined speech decoding algorithms will also be performed.

Description of Work

T4.1 – Project Communication (M1-M24)

Aims to establish the project’s communication channels, including the project’s website and social media accounts. Outreach content will be organized, reviewed and communicated to the public periodically, on a 3-month basis. To further communicate the project’s activities to the public, demonstration activities, both within the project’s lifecycle and the post-project era, like the participation in the Researcher’s Night organized by the EU, will also be planned.

T4.2 – Dissemination – Publications in Scientific Venues (M1-M24)

Aims to establish an efficient dissemination plan. More specifically, the end of the project’s first year, that coincides with the completion of the first round of T2.2’s activities, will mark the initiation of the preparation phase for publication submissions to high-impact international conference(s), like CHI, EUSIPCO and SIGMAP. From M18, extended versions will be prepared with the scope of submission to high-impact scientific journals (e.g. Journal of Neural Engineering, Human-Computer Interaction, IEEE Trans. on Biomedical Engineering).

T4.3 – Uptake of BINGO’s results (M12-M24)

Aims to ensure the uptake of BINGO’s results by the scientific community by launching a competition oriented in BINGO’s benchmarking framework and imagined speech dataset. The metrics identified in T3.3 will be used to organize a competition in online popular scientific communities, like Kaggle, in neuroscientific events, like BCI competitions, or in impactful scientific venues (e.g., Graz BCI Conference, IEEE EMBC, NeuIPS, ACM CHI).