Related papers: Target-centered Subject Transfer Framework for EEG…
In the Machine Learning (ML) literature, a well-known problem is the Dataset Shift problem where, differently from the ML standard hypothesis, the data in the training and test sets can follow different probability distributions, leading ML…
The scarcity of speaker-annotated far-field speech presents a significant challenge in developing high-performance far-field speaker verification (SV) systems. While data augmentation using large-scale near-field speech has been a common…
Achieving robust generalization across individuals remains a major challenge in electroencephalogram based imagined speech decoding due to substantial variability in neural activity patterns. This study examined how training dynamics and…
Advances in neuroscience and artificial intelligence have enabled preliminary decoding of brain activity. However, despite the progress, the interpretability of neural representations remains limited. A significant challenge arises from the…
Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper…
Data augmentation is an effective way to improve the performance of many neural text generation models. However, current data augmentation methods need to define or choose proper data mapping functions that map the original samples into the…
Recently, end-to-end (E2E) automatic speech recognition (ASR) models have made great strides and exhibit excellent performance in general speech recognition. However, there remain several challenging scenarios that E2E models are not…
Current state-of-the-art neural dialogue models learn from human conversations following the data-driven paradigm. As such, a reliable training corpus is the crux of building a robust and well-behaved dialogue model. However, due to the…
Conventional unsupervised domain adaptation (UDA) methods need to access both labeled source samples and unlabeled target samples simultaneously to train the model. While in some scenarios, the source samples are not available for the…
Unlike conventional data such as natural images, audio and speech, raw multi-channel Electroencephalogram (EEG) data are difficult to interpret. Modern deep neural networks have shown promising results in EEG studies, however finding robust…
Unsupervised Domain adaptation methods solve the adaptation problem for an unlabeled target set, assuming that the source dataset is available with all labels. However, the availability of actual source samples is not always possible in…
Electroencephalography (EEG) denoising methods typically depend on manual intervention or clean reference signals. This work introduces a task-oriented learning framework for automatic EEG denoising that uses only task labels without clean…
Electroencephalography (EEG) stands as a crucial tool in neuroscientific research and clinical diagnostics, providing valuable insights into the electrical activities of the brain. Traditional EEG signal processing techniques, predominantly…
The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learning and data augmentation to alleviate this issue. We study…
Humans can effortlessly modify various prosodic attributes, such as the placement of stress and the intensity of sentiment, to convey a specific emotion while maintaining consistent linguistic content. Motivated by this capability, we…
Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data. While recently developed end-to-end methods largely simplify the modeling pipelines, they still suffer from the data…
Electroencephalogram (EEG)-based seizure subtype classification enhances clinical diagnosis efficiency. Source-free semi-supervised domain adaptation (SF-SSDA), which transfers a pre-trained model to a new dataset with no source data and…
Target confusion, defined as occasional switching to non-target speakers, poses a key challenge for end-to-end speaker extraction (E2E-SE) systems. We argue that this problem is largely caused by the lack of generalizability and…
The challenge of creating domain-centric embeddings arises from the abundance of unstructured data and the scarcity of domain-specific structured data. Conventional embedding techniques often rely on either modality, limiting their…
For deep learning applications, the massive data development (e.g., collecting, labeling), which is an essential process in building practical applications, still incurs seriously high costs. In this work, we propose an effective data…