Related papers: Mitigating Source and Detection Noises in Auto-cor…
Unsupervised domain adaptation (UDA) for person re-identification is challenging because of the huge gap between the source and target domain. A typical self-training method is to use pseudo-labels generated by clustering algorithms to…
Speech dereverberation is an important issue for many real-world speech processing applications. Among the techniques developed, the weighted prediction error (WPE) algorithm has been widely adopted and advanced over the last decade, which…
Conventional spoofing detection systems have heavily relied on the use of handcrafted features derived from speech data. However, a notable shift has recently emerged towards the direct utilization of raw speech waveforms, as demonstrated…
This work introduces Differential Wavelet Amplifier (DWA), a drop-in module for wavelet-based image Super-Resolution (SR). DWA invigorates an approach recently receiving less attention, namely Discrete Wavelet Transformation (DWT). DWT…
Variational Quantum Algorithms (VQAs) are a promising application for near-term quantum processors, however the quality of their results is greatly limited by noise. For this reason, various error mitigation techniques have emerged to deal…
We investigate quantum-squeezing-enhanced weak-force sensing via a nonlinear optomechanical resonator containing a movable mechanical mirror and an optical parametric amplifier (OPA). Herein, we determined that tuning the OPA parameters can…
Personalized Voice Activity Detection (PVAD) systems activate only in response to a specific target speaker. Speaker-conditioning methods are employed to inject information about the target speaker into a VAD pipeline, to achieve…
This paper develops a framework that can perform denoising, dereverberation, and source separation accurately by using a relatively small number of microphones. It has been empirically confirmed that Independent Vector Analysis (IVA) can…
Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…
The performance of spoofing countermeasure systems depends fundamentally upon the use of sufficiently representative training data. With this usually being limited, current solutions typically lack generalisation to attacks encountered in…
We use weak-value amplification to enhance the polarization-sensitive fast-light effect from induced Raman absorption in hot rubidium vapor. We experimentally demonstrate that projecting the output signal into an appropriate polarization…
Achieving higher sensitivity is an earnest purpose for precision metrology. As a response to this goal, the weak value amplification approach has been developed for measuring ultra-small physical effects, realizing sensitivity that had…
Programmatic Weak Supervision (PWS) and generative models serve as crucial tools that enable researchers to maximize the utility of existing datasets without resorting to laborious data gathering and manual annotation processes. PWS uses…
Subsurface defect detection via Ground Penetrating Radar is challenged by "weak signals" faint diffraction hyperbolas with low signal-to-clutter ratios, high wavefield similarity, and geometric degradation. Existing lightweight detectors…
Weakly-supervised segmentation (WSS) has emerged as a solution to mitigate the conflict between annotation cost and model performance by adopting sparse annotation formats (e.g., point, scribble, block, etc.). Typical approaches attempt to…
Weakly-supervised image segmentation (WSIS) is a critical task in computer vision that relies on image-level class labels. Multi-stage training procedures have been widely used in existing WSIS approaches to obtain high-quality pseudo-masks…
Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their…
Integrating audio and visual data for training multimodal foundational models remains a challenge. The Audio-Video Vector Alignment (AVVA) framework addresses this by considering AV scene alignment beyond mere temporal synchronization, and…
Post-selected weak measurement has been widely used in experiments to observe weak effects in various physical systems. However, it is still unclear how large the amplification ability of a weak measurement can be and what determines the…
We analyze the Accelerated Noisy Power Method, an algorithm for Principal Component Analysis in the setting where only inexact matrix-vector products are available, which can arise for instance in decentralized PCA. While previous works…