Related papers: CIS-BWE: Chaos-Informed Speech Bandwidth Extension
This chapter overviews the concept of Smart Wireless Environments (SWEs) motivated by the emerging technology of Reconfigurable Intelligent Surfaces (RISs). The operating principles and state-of-the-art hardware architectures of…
Large Language Model ensembles improve reasoning accuracy, but only up to a performance boundary beyond which additional deliberation degrades accuracy. We introduce DASE (Deliberative Adaptive Stopping Ensemble), a stopping heuristic for…
Identifying unknown differential equations from a given set of discrete time dependent data is a challenging problem. A small amount of noise can make the recovery unstable, and nonlinearity and differential equations with varying…
Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation is equally important.…
Understanding how generative models represent and transform data is a foundational problem in deep learning interpretability. While mechanistic interpretability of discriminative architectures has yielded substantial insights, relatively…
Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a…
Ultrasound Shear Wave Elastography (SWE) is a noteworthy tool for in-vivo noninvasive tissue pathology assessment. State-of-the-art techniques can generate reasonable estimates of tissue elasticity, but high-quality and noise-resiliency in…
For real-time speech enhancement (SE) including noise suppression, dereverberation and acoustic echo cancellation, the time-variance of the audio signals becomes a severe challenge. The causality and memory usage limit that only the…
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts the white noise signal into structured waveform through a…
Target speaker extraction (TSE) aims to recover the speech of a desired speaker from a mixture given a short enrollment utterance, while speech enhancement (SE) focuses on improving speech quality under noisy conditions. Most existing TSE…
Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…
Blind synchronization constitutes a major challenge in realizing highly efficient ultra wide band (UWB) systems because of the short pulse duration which requires a fast synchronization algorithm to accommodate several asynchronous users.…
Fixed representational capacity is a fundamental constraint in continual learning: practitioners must guess an appropriate model width before training, without knowing how many distinct concepts the data contains. We propose LACE…
The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…
Motor imagery (MI) based brain-computer interfaces (BCIs) hold significant potential for assistive technologies and neurorehabilitation. However, the precise and efficient decoding of MI remains challenging due to their non-stationary…
A model-based extended state observer (MB-ESO) and its variant are proposed for discrete-time linear multivariable systems, where multiple disturbances are defined as an extended state vector in the same manner as in the original…
Neural Ordinary Differential Equations (NODEs), a framework of continuous-depth neural networks, have been widely applied, showing exceptional efficacy in coping with representative datasets. Recently, an augmented framework has been…
Encoder-decoder imbalance and the reliance on large input volumes make many 3D brain tumor segmentation models both compute-heavy and brittle. We present M\textsuperscript{4}Fuse, a lightweight network that prioritizes discriminative brain…
This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimensional convolutions computed alongside the time domain,…
In this paper, we incorporate physical knowledge into learning-based high-precision target sensing using the multi-view channel state information (CSI) between multiple base stations (BSs) and user equipment (UEs). Such kind of multi-view…