Related papers: Controllable joint noise reduction and hearing los…
We present a deep neural network to reduce coherent noise in three-dimensional quantitative phase imaging. Inspired by the cycle generative adversarial network, the denoising network was trained to learn a transform between two image…
Ensuring intelligible speech communication for hearing assistive devices in low-latency scenarios presents significant challenges in terms of speech enhancement, coding and transmission. In this paper, we propose novel solutions for…
Auditory models are commonly used as feature extractors for automatic speech-recognition systems or as front-ends for robotics, machine-hearing and hearing-aid applications. Although auditory models can capture the biophysical and nonlinear…
Speech enhancement algorithms based on deep learning have greatly surpassed their traditional counterparts and are now being considered for the task of removing acoustic echo from hands-free communication systems. This is a challenging…
Deep learning technology has been widely applied to speech enhancement. While testing the effectiveness of various network structures, researchers are also exploring the improvement of the loss function used in network training. Although…
Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencies that can contribute to costly training dynamics. The…
Inspired by the recent progress in self-supervised learning for computer vision, in this paper we introduce DeLoRes, a new general-purpose audio representation learning approach. Our main objective is to make our network learn…
Deep Learning with noisy labels is a practically challenging problem in weakly supervised learning. The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the…
Implicit feedback, employed in training recommender systems, unavoidably confronts noise due to factors such as misclicks and position bias. Previous studies have attempted to identify noisy samples through their diverged data patterns,…
Recent advancements in audio-aware large language models (ALLMs) enable them to process and understand audio inputs. However, these models often hallucinate non-existent sound events, reducing their reliability in real-world applications.…
Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect…
Despite the indispensable role of X-ray computed tomography (CT) in diagnostic medicine field, the associated ionizing radiation is still a major concern considering that it may cause genetic and cancerous diseases. Decreasing the exposure…
The prevalence of noisy labels in real-world datasets poses a significant impediment to the effective deployment of deep learning models. While meta-learning strategies have emerged as a promising approach for addressing this challenge,…
An accurate objective speech intelligibility prediction algorithms is of great interest for many applications such as speech enhancement for hearing aids. Most algorithms measures the signal-to-noise ratios or correlations between the…
Objective non-stationarity measures are resource intensive and impose critical limitations for real-time processing solutions. In this paper, a novel Hard Label Criteria (HLC) algorithm is proposed to generate a global non-stationarity…
Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solutions identify noisy labels and adopt active learning to…
Attention mechanisms, such as local and non-local attention, play a fundamental role in recent deep learning based speech enhancement (SE) systems. However, natural speech contains many fast-changing and relatively brief acoustic events,…
We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…
Commercial iterative reconstruction techniques on modern CT scanners target radiation dose reduction but there are lingering concerns over their impact on image appearance and low contrast detectability. Recently, machine learning,…
Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…