Related papers: MEG-to-MEG Transfer Learning and Cross-Task Speech…

Decoding speech from stereo-electroencephalography (sEEG) signals has emerged as a promising direction for brain-computer interfaces (BCIs). Its clinical applicability, however, is limited by the inherent non-stationarity of neural signals,…

The paradigm of representation learning through transfer learning has the potential to greatly enhance clinical natural language processing. In this work, we propose a multi-task pre-training and fine-tuning approach for learning…

Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naive formulations often degrade performance and in particular, identifying the tasks that would benefit from…

This doctoral thesis improves the transfer learning for sequence labeling tasks by adapting pre-trained neural language models. The proposed improvements in transfer learning involve introducing a multi-task model that incorporates an…

This paper studies task-oriented, otherwise known as goal-oriented, communications, in a setting where a transmitter communicates with multiple receivers, each with its own task to complete on a dataset, e.g., images, available at the…

Transformers are groundbreaking architectures that have changed a flow of deep learning, and many high-performance models are developing based on transformer architectures. Transformers implemented only with attention with encoder-decoder…

In this study, we introduce an innovative EEG signal reconstruction sub-module designed to enhance the performance of deep learning models on EEG eye-tracking tasks. This sub-module can integrate with all Encoder-Classifier-based deep…

Task transfer, transferring knowledge contained in related tasks, holds the promise of reducing the quantity of labeled data required to fine-tune language models. Dialogue understanding encompasses many diverse tasks, yet task transfer has…

Accurate decoding of surface electromyography (sEMG) is pivotal for muscle-to-machine-interfaces (MMI) and their application for e.g. rehabilitation therapy. sEMG signals have high inter-subject variability, due to various factors,…

While speech emotion recognition (SER) research has made significant progress, achieving generalization across various corpora continues to pose a problem. We propose a novel domain adaptation technique that embodies a multitask framework…

Objective: EEG-based methods can predict speech intelligibility, but their accuracy and robustness lag behind behavioral tests, which typically show test-retest differences under 1 dB. We introduce the multi-decoder method to predict speech…

Understanding how the brain responds to sensory inputs is challenging: brain recordings are partial, noisy, and high dimensional; they vary across sessions and subjects and they capture highly nonlinear dynamics. These challenges have led…

Understanding the neural mechanisms underlying speech production is essential for both advancing cognitive neuroscience theory and developing practical communication technologies. In this study, we investigated magnetoencephalography…

We present a large autoregressive model for source-space MEG that scales next-token prediction to long context across datasets and scanners: handling a corpus of over 500 hours and thousands of sessions across the three largest MEG…

End-to-end training of deep learning-based models allows for implicit learning of intermediate representations based on the final task loss. However, the end-to-end approach ignores the useful domain knowledge encoded in explicit…

Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked…

Video-to-speech synthesis is the task of reconstructing the speech signal from a silent video of a speaker. Most established approaches to date involve a two-step process, whereby an intermediate representation from the video, such as a…

Reading comprehension is a challenging task in natural language processing and requires a set of skills to be solved. While current approaches focus on solving the task as a whole, in this paper, we propose to use a neural network `skill'…

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…