Related papers: ALIGN: Adversarial Learning for Generalizable Spee…

Learning domain-invariant representation is a dominant approach for domain generalization (DG), where we need to build a classifier that is robust toward domain shifts. However, previous domain-invariance-based methods overlooked the…

Deep learning methods for person identification based on electroencephalographic (EEG) brain activity encounters the problem of exploiting the temporally correlated structures or recording session specific variability within EEG.…

The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in…

We propose FAR-SIGN (Fully Asynchronous Robust optimization via SIGNed directional projections) for adversary-resilient learning in parameter-server--worker systems. FAR-SIGN achieves robustness through sign-based updates along carefully…

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…

A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. The most common non-invasive BCI modality, electroencephalogram (EEG), is sensitive to noise/artifact and suffers…

Automatic music transcription is considered to be one of the hardest problems in music information retrieval, yet recent deep learning approaches have achieved substantial improvements on transcription performance. These approaches commonly…

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

We introduce here the idea of Meta-Learning for training EEG BCI decoders. Meta-Learning is a way of training machine learning systems so they learn to learn. We apply here meta-learning to a simple Deep Learning BCI architecture and…

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…

Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Conditional generative adversarial networks (cGANs) show promise in…

Brain computer interface (BCI) research, as well as increasing portions of the field of neuroscience, have found success deploying large-scale artificial intelligence (AI) pre-training methods in conjunction with vast public repositories of…

When it comes to the classification of brain signals in real-life applications, the training and the prediction data are often described by different distributions. Furthermore, diverse data sets, e.g., recorded from various subjects or…

Conventional augmentative and alternative communication (AAC) systems and language-learning platforms often fail to adapt in real time to the user's cognitive and linguistic needs, especially in neurological conditions such as post-stroke…

Semantic encoders and decoders for digital semantic communication (SC) often struggle to adapt to variations in unpredictable channel environments and diverse system designs. To address these challenges, this paper proposes a novel…

A brain-computer interface (BCI) enables direct communication between the brain and an external device. Electroencephalogram (EEG) is a common input signal for BCIs, due to its convenience and low cost. Most research on EEG-based BCIs…

We present ALIGN-FL, a novel approach to distributed learning that addresses the challenge of learning from highly disjoint data distributions through selective sharing of generative components. Instead of exchanging full model parameters,…

A brain-computer interface (BCI) system usually needs a long calibration session for each new subject/task to adjust its parameters, which impedes its transition from the laboratory to real-world applications. Domain adaptation, which…

Brain-Computer Interface (BCI) bridges the human's neural world and the outer physical world by decoding individuals' brain signals into commands recognizable by computer devices. Deep learning has lifted the performance of brain-computer…