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

Traditional transformer-based semantic segmentation relies on quantized embeddings. However, our analysis reveals that autoencoder accuracy on segmentation mask using quantized embeddings (e.g. VQ-VAE) is 8% lower than continuous-valued…

Despite recent advancements in packet loss concealment (PLC) using deep learning techniques, packet loss remains a significant challenge in real-time speech communication. Redundancy has been used in the past to recover the missing…

Multiple-input multiple-output (MIMO) or multi-antenna communication is a key technique to achieve high spectral efficiency in wireless systems. For the point-to-point MIMO channel, it is a well-known result that the channel singular value…

The research in Deep Learning applications in sound and music computing have gathered an interest in the recent years; however, there is still a missing link between these new technologies and on how they can be incorporated into real-world…

End-to-end design of communication systems using deep autoencoders (AEs) is gaining attention due to its flexibility and excellent performance. Besides single-user transmission, AE-based design is recently explored in multi-user setup,…

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…

In a multiple-input multiple-output frequency-division duplexing (MIMO-FDD) system, the user equipment (UE) sends the downlink channel state information (CSI) to the base station to report link status. Due to the complexity of MIMO systems,…

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers,…

Deep generative models (DGMs) have achieved remarkable advances. Semi-supervised variational auto-encoders (SVAE) as a classical DGM offer a principled framework to effectively generalize from small labelled data to large unlabelled ones,…

Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data remains a significant challenge in the field. Self-supervised…

Neural networks have been applied to the physical layer of wireless communication systems to solve complex problems. In millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, hybrid precoding has been considered as…

Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or…

We introduce a novel physical layer scheme for single user Multiple-Input Multiple-Output (MIMO) communications based on unsupervised deep learning using an autoencoder. This method extends prior work on the joint optimization of physical…

Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised…

Most of the data-driven approaches applied to bearing fault diagnosis up to date are established in the supervised learning paradigm, which usually requires a large set of labeled data collected a priori. In practical applications, however,…

Denoising autoencoders (DAEs) are powerful deep learning models used for feature extraction, data generation and network pre-training. DAEs consist of an encoder and decoder which may be trained simultaneously to minimise a loss (function)…

Human perception is inherently multimodal. We integrate, for instance, visual, proprioceptive and tactile information into one experience. Hence, multimodal learning is of importance for building robotic systems that aim at robustly…

Massive multiple-input multiple-output (MIMO) has the potential to substantially improve the spectral efficiency, robustness and coverage of mobile networks. However, such potential is limited by hardware cost and power consumption…

Classical methods for model order selection often fail in scenarios with low SNR or few snapshots. Deep learning-based methods are promising alternatives for such challenging situations as they compensate lack of information in the…

We develop an end-to-end deep learning framework for downlink beamforming in large-scale sparse MIMO channels. The core is a deep EDN architecture with three modules: (i) an encoder NN, deployed at each user end, that compresses estimated…