Related papers: Dynamic nsNet2: Efficient Deep Noise Suppression w…

Current self-supervised denoising techniques achieve impressive results, yet their real-world application is frequently constrained by substantial computational and memory demands, necessitating a compromise between inference speed and…

We propose a new method to probe the learning mechanism of Deep Neural Networks (DNN) by perturbing the system using Noise Injection Nodes (NINs). These nodes inject uncorrelated noise via additional optimizable weights to existing…

The recent advances in Deep Neural Networks (DNNs) stem from their exceptional performance across various domains. However, their inherent large size hinders deploying these networks on resource-constrained devices like edge, mobile, and…

Semantic segmentation and change detection are two fundamental challenges in remote sensing, requiring models to capture either spatial semantics or temporal differences from satellite imagery. Existing deep learning models often struggle…

We introduce a new method for speeding up the inference of deep neural networks. It is somewhat inspired by the reduced-order modeling techniques for dynamical systems.The cornerstone of the proposed method is the maximum volume algorithm.…

Mobile and edge computing devices for always-on classification tasks require energy-efficient neural network architectures. In this paper we present several changes to neural architecture searches (NAS) that improve the chance of success in…

Deep neural networks (DNNs) have achieved remarkable success across diverse domains, but their performance can be severely degraded by noisy or corrupted training data. Conventional noise mitigation methods often rely on explicit…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Deep learning methods have brought substantial advancements in speech separation (SS). Nevertheless, it remains challenging to deploy deep-learning-based models on edge devices. Thus, identifying an effective way to compress these large…

We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these…

With the prosperity of mobile devices, the distributed learning approach enabling model training with decentralized data has attracted wide research. However, the lack of training capability for edge devices significantly limits the energy…

In real acoustic environment, speech enhancement is an arduous task to improve the quality and intelligibility of speech interfered by background noise and reverberation. Over the past years, deep learning has shown great potential on…

Deep neural network (DNN) inference is increasingly being executed on mobile and embedded platforms due to several key advantages in latency, privacy and always-on availability. However, due to limited computing resources, efficient DNN…

When dealing with deep neural network (DNN) applications on edge devices, continuously updating the model is important. Although updating a model with real incoming data is ideal, using all of them is not always feasible due to limits, such…

Neoteric works have shown that modern deep learning models can exhibit a sparse double descent phenomenon. Indeed, as the sparsity of the model increases, the test performance first worsens since the model is overfitting the training data;…

Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring…

Deep feedforward and recurrent networks have achieved impressive results in many perception and language processing applications. This success is partially attributed to architectural innovations such as convolutional and long short-term…

Recent advances in deep learning motivate the use of deep neutral networks in sensing applications, but their excessive resource needs on constrained embedded devices remain an important impediment. A recently explored solution space lies…

In this paper, we propose a framework to enhance the robustness of the neural models by mitigating the effects of process-induced and aging-related variations of analog computing components on the accuracy of the analog neural networks. We…

In recent years, deep neural networks (DNNs) were studied as an alternative to traditional acoustic echo cancellation (AEC) algorithms. The proposed models achieved remarkable performance for the separate tasks of AEC and residual echo…