Related papers: DeepSpectrumLite: A Power-Efficient Transfer Learn…

Optical transmission spectroscopy is one method to understand brain tissue structural properties from brain tissue biopsy samples, yet manual interpretation is resource intensive and prone to inter observer variability. Deep convolutional…

Spectral Embedding (SE) has often been used to map data points from non-linear manifolds to linear subspaces for the purpose of classification and clustering. Despite significant advantages, the subspace structure of data in the original…

Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…

Medical imaging plays a vital role in modern diagnostics; however, interpreting high-resolution radiological data remains time-consuming and susceptible to variability among clinicians. Traditional image processing techniques often lack the…

Deploying sophisticated deep learning models on embedded devices with the purpose of solving real-world problems is a struggle using today's technology. Privacy and data limitations, network connection issues, and the need for fast model…

Speech, Music and Noise classification/segmentation is an important preprocessing step for audio processing/indexing. To this end, we propose a novel 1D Convolutional Neural Network (CNN) - SwishNet. It is a fast and lightweight…

We present a novel model designed for resource-efficient multichannel speech enhancement in the time domain, with a focus on low latency, lightweight, and low computational requirements. The proposed model incorporates explicit spatial and…

Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context,…

While deep neural networks have shown impressive results in automatic speaker recognition and related tasks, it is dissatisfactory how little is understood about what exactly is responsible for these results. Part of the success has been…

Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time reasoning to multi-model collaboration. We study language model networks, where pre-trained language…

Transfer learning (TL) is an increasingly popular approach to training deep learning (DL) models that leverages the knowledge gained by training a foundation model on diverse, large-scale datasets for use on downstream tasks where less…

Adaptive network coding schemes provide a promising approach to bridging the gap between high data rates and low delay in real-time streaming applications. However, their effectiveness often relies on accurate channel prediction, which is…

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. The development of high-performing neural network sound recognition systems has raised the possibility of…

Classical speech coding uses low-complexity postfilters with zero lookahead to enhance the quality of coded speech, but their effectiveness is limited by their simplicity. Deep Neural Networks (DNNs) can be much more effective, but require…

Recently, neural machine translation has achieved remarkable progress by introducing well-designed deep neural networks into its encoder-decoder framework. From the optimization perspective, residual connections are adopted to improve…

Although mission-critical applications require the use of deep neural networks (DNNs), their continuous execution at mobile devices results in a significant increase in energy consumption. While edge offloading can decrease energy…

Recent studies have shown the latency and energy consumption of deep neural networks can be significantly improved by splitting the network between the mobile device and cloud. This paper introduces a new deep learning architecture, called…

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…