Related papers: Short-wave admittance correction for a time-domain…
Large language models are increasingly adopted as semantic backbones for neural text-to-speech systems. However, frozen LLM representations are insufficient for modeling speaker specific acoustic and perceptual characteristics. Our…
Deep reinforcement learning (RL) is a powerful approach to complex decision making. However, one issue that limits its practical application is its brittleness, sometimes failing to train in the presence of small changes in the environment.…
The multipath radio channel is considered to have a non-bandlimited channel impulse response. Therefore, it is challenging to achieve high resolution time-delay (TD) estimation of multipath components (MPCs) from bandlimited observations of…
Current transfer learning methods for high-dimensional linear regression assume feature alignment across domains, restricting their applicability to semantically matched features. In many real-world scenarios, however, distinct features in…
Accurate knowledge of transmission line (TL) impedance parameters helps to improve accuracy in relay settings and power flow modeling. To improve TL parameter estimates, various algorithms have been proposed in the past to identify TL…
Medical image segmentation traditionally relies on fully supervised 3D architectures that demand a large amount of dense, voxel-level annotations from clinical experts which is a prohibitively expensive process. Vision Language Models…
Deep learning has achieved substantial improvement on single-channel speech enhancement tasks. However, the performance of multi-layer perceptions (MLPs)-based methods is limited by the ability to capture the long-term effective history…
In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…
Broad emission lines of active galactic nuclei stem from a spatially extended region (broad-line region, BLR) that is composed of discrete clouds and photoionized by the central ionizing continuum. The temporal behaviors of these emission…
Large Audio Language Models (LALMs) demonstrate impressive general audio understanding, but once deployed, they are static and fail to improve with new real-world audio data. As traditional supervised fine-tuning is costly, we introduce a…
We propose Deep Longitudinal Targeted Minimum Loss-based Estimation (Deep LTMLE), a novel approach to estimate the counterfactual mean of outcome under dynamic treatment policies in longitudinal problem settings. Our approach utilizes a…
We consider the estimation of the average treatment effect in the treated as a function of baseline covariates, where there is a valid (conditional) instrument. We describe two doubly robust (DR) estimators: a locally efficient g-estimator,…
Transfer learning (TL) has been widely used in motor imagery (MI) based brain-computer interfaces (BCIs) to reduce the calibration effort for a new subject, and demonstrated promising performance. While a closed-loop MI-based BCI system,…
In this paper, phase correction and amplitude compensation are introduced to a previously developed mixed domain method (MDM), which is only accurate for modeling wave propagation in weakly heterogeneous media. Multiple reflections are also…
Due to their high resolution, dynamic medical 2D+t and 3D+t volumes from computed tomography (CT) and magnetic resonance tomography (MR) reach a size which makes them very unhandy for teleradiologic applications. A lossless scalable…
We present experimental evidence of a thermally-driven amplitude-frequency nonlinearity in a thin-film quartz phononic crystal resonator at millikelvin temperatures. The nonlinear response arises from the coupling of the mechanical mode to…
The Hubble Tension is a well-known issue in modern cosmology that refers to the apparent disagreement in inferences of the Hubble constant $H_0$ as found through low-redshift observations and those derived from the $\Lambda$CDM model…
Transfer learning is a promising method for AOI applications since it can significantly shorten sample collection time and improve efficiency in today's smart manufacturing. However, related research enhanced the network models by applying…
We show that a minimally extended varying-speed-of-light (meVSL) cosmology can alleviate the Hubble tension through a single parameter, b. This parameter both shortens the sound horizon at the drag epoch and modifies cosmological time…
The rapid growth in mobile broadband usage and increasing subscribers have made it crucial to ensure reliable network performance. As mobile networks grow more complex, especially during peak hours, manual collection of Key Performance…