Related papers: SVD-Embedded Deep Autoencoder for MIMO Communicati…

Masked Autoencoder (MAE) pre-training of vision transformers (ViTs) yields strong performance in low-label data regimes but comes with substantial computational costs, making it impractical in time- and resource-constrained industrial…

Deep speaker embedding has achieved state-of-the-art performance in speaker recognition. A potential problem of these embedded vectors (called `x-vectors') are not Gaussian, causing performance degradation with the famous PLDA back-end…

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image…

Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to…

In this paper, we propose a sequential and incremental precoder design for downlink joint transmission (JT) network MIMO systems with imperfect backhaul links. The objective of our design is to minimize the maximum of the sub-stream mean…

We study the multi-user massive multiple-input-single-output (MISO) and focus on the downlink systems where the base station (BS) employs hybrid analog-digital precoding with low-cost 1-bit digital-to-analog converters (DACs). In this…

We present a preliminary study on an end-to-end variational autoencoder (VAE) for sound morphing. Two VAE variants are compared: VAE with dilation layers (DC-VAE) and VAE only with regular convolutional layers (CC-VAE). We combine the…

The near-field effect of short-range multiple-input multiple-output (MIMO) systems imposes many challenges on direction-of-arrival (DoA) estimation. Most conventional scenarios assume that the far-field planar wavefronts hold. In this…

The Automatic Dependent Surveillance Broadcast protocol is one of the latest compulsory advances in air surveillance. While it supports the tracking of the ever-growing number of aircraft in the air, it also introduces cybersecurity issues…

We consider the use of deep neural network (DNN) to develop a decision-directed (DD)-channel estimation (CE) algorithm for multiple-input multiple-output (MIMO)-space-time block coded systems in highly dynamic vehicular environments. We…

In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very…

Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data. This work focuses on a feature enhancement for noise…

Accurate precoding in massive multiple-input multiple-output (MIMO) frequency-division duplexing (FDD) systems relies on efficient channel state information (CSI) acquisition. End-to-end learning frameworks improve performance by jointly…

We present a Split Vector Quantized Variational Autoencoder (SVQ-VAE) architecture using a split vector quantizer for NTTS, as an enhancement to the well-known Variational Autoencoder (VAE) and Vector Quantized Variational Autoencoder…

Data encoding is a common and central operation in most data analysis tasks. The performance of other models downstream in the computational process highly depends on the quality of data encoding. One of the most powerful ways to encode…

Enabling high-definition (HD)-map-assisted cooperative driving among autonomous vehicles (AVs) to improve the navigation safety faces technical challenges due to increased communication traffic volume for data dissemination and increased…

Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient…

Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding.…

Recent work has shown that Variational Autoencoders (VAEs) can be used to upper-bound the information rate-distortion (R-D) function of images, i.e., the fundamental limit of lossy image compression. In this paper, we report an improved…

Stack autoencoder (SAE), as a representative deep network, has unique and excellent performance in feature learning, and has received extensive attention from researchers. However, existing deep SAEs focus on original samples without…