相关论文: Towards Homogeneous Lexical Tone Decoding from Het…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

Brain-related research topics in artificial intelligence have recently gained popularity, particularly due to the expansion of what multimodal architectures can do from computer vision to natural language processing. Our main goal in this…

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Decoding text stimuli from cognitive signals (e.g. fMRI) enhances our understanding of the human language system, paving the way for building versatile Brain-Computer Interface. However, existing studies largely focus on decoding individual…

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…

Decoding continuous language from neural signals remains a significant challenge in the intersection of neuroscience and artificial intelligence. We introduce Neuro2Semantic, a novel framework that reconstructs the semantic content of…

This study proposes a Transformer-based longitudinal modeling method to address challenges in clinical risk classification with heterogeneous Electronic Health Record (EHR) data, including irregular temporal patterns, large modality…

This paper introduces an end-to-end neural speech restoration model, HD-DEMUCS, demonstrating efficacy across multiple distortion environments. Unlike conventional approaches that employ cascading frameworks to remove undesirable noise…

Universal audio codecs learn entangled representations across audio types, whereas some specific codecs offer decoupled representations but are limited to speech. Real-world audio, however, often contains mixed speech and background sounds,…

This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. Our approach identifies both spurious and invariant latent features…

This thesis delves into the world of non-invasive electrophysiological brain signals like electroencephalography (EEG) and magnetoencephalography (MEG), focusing on modelling and decoding such data. The research aims to investigate what…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

Deep learning-based hearing loss compensation (HLC) seeks to enhance speech intelligibility and quality for hearing impaired listeners using neural networks. One major challenge of HLC is the lack of a ground-truth target. Recent works have…

Brain decoding aims to reconstruct visual perception of human subject from fMRI signals, which is crucial for understanding brain's perception mechanisms. Existing methods are confined to the single-subject paradigm due to substantial brain…

Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, following a semantic-modeling and acoustic-synthesis paradigm.…

Decoding linguistic information from non-invasive brain signals using EEG has gained increasing research attention due to its vast applicational potential. Recently, a number of works have adopted a generative-based framework to decode…

The popularity and diffusion of wearable devices provides new opportunities for sensor-based human activity recognition that leverages deep learning-based algorithms. Although impressive advances have been made, two major challenges remain.…

Recent work on intracranial brain-machine interfaces has demonstrated that spoken speech can be decoded with high accuracy, essentially by treating the problem as an instance of supervised learning and training deep neural networks to map…

Limited amount of labelled training data are a common problem in medical imaging. This makes it difficult to train a well-generalised model and therefore often leads to failure in unknown domains. Hippocampus segmentation from magnetic…

We introduce and compare several strategies for learning discriminative features from electroencephalography (EEG) recordings using deep learning techniques. EEG data are generally only available in small quantities, they are…