Related papers: End-to-End Autoencoder for Drill String Acoustic C…

In this study, we propose a novel approach, namely the combined Convolutional Deep Autoencoder Echo State Network (CDAE ESN) model, for the analysis and forecasting of dynamics and low order statistics in coupled turbulent channel porous…

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer from two critical limitations: (1) inefficient token-to-expert…

With the rapid growth of the global marine economy and flourishing maritime activities, the marine Internet of Things (IoT) is gaining unprecedented momentum. However, current marine equipment is deficient in data transmission efficiency…

The problem of end-to-end learning of a communication system using an autoencoder -- consisting of an encoder, channel, and decoder modeled using neural networks -- has recently been shown to be an effective approach. A challenge faced in…

Recently, end-to-end (E2E) speech recognition has become popular, since it can integrate the acoustic, pronunciation and language models into a single neural network, which outperforms conventional models. Among E2E approaches,…

We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and…

Stacked intelligent metasurface (SIM) and dual-polarized SIM (DPSIM) enabled wave-domain signal processing have emerged as promising research directions for offloading baseband digital processing tasks and efficiently simplifying…

Autoencoders are effective deep learning models that can function as generative models and learn latent representations for downstream tasks. The use of graph autoencoders - with both encoder and decoder implemented as message passing…

With the massive developments of end-to-end (E2E) neural networks, recent years have witnessed unprecedented breakthroughs in automatic speech recognition (ASR). However, the codeswitching phenomenon remains a major obstacle that hinders…

Frequency modulation (FM) is a form of radio broadcasting which is widely used nowadays and has been for almost a century. We suggest a software-defined-radio (SDR) receiver for FM demodulation that adopts an end-to-end learning based…

Machine learning on trees has been mostly focused on trees as input to algorithms. Much less research has investigated trees as output, which has many applications, such as molecule optimization for drug discovery, or hint generation for…

End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…

Recent works in end-to-end control for autonomous driving have investigated the use of vision-based exteroceptive perception. Inspired by such results, we propose a new end-to-end memory-based neural architecture for robot steering and…

We introduce a novel method for controlling the functionality of a hands-free speech communication device which comprises a model-based acoustic echo canceller (AEC), minimum variance distortionless response (MVDR) beamformer (BF) and…

Deep learning (DL) based autoencoder is a promising architecture to implement end-to-end communication systems. One fundamental problem of such systems is how to increase the transmission rate. Two new schemes are proposed to address the…

The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network…

The Variational Autoencoder (VAE) is a powerful deep generative model that is now extensively used to represent high-dimensional complex data via a low-dimensional latent space learned in an unsupervised manner. In the original VAE model,…

Constant envelope (CE) precoding design is of great interest for massive multiuser multi-input multi-output systems because it can significantly reduce hardware cost and power consumption. However, existing CE precoding algorithms are…

Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introduce a simple training methodology to induce linearity in a…

Understanding the coordinated activity underlying brain computations requires large-scale, simultaneous recordings from distributed neuronal structures at a cellular-level resolution. One major hurdle to design high-bandwidth,…