Related papers: Unsupervised Linear and Nonlinear Channel Equaliza…
There are many problems in physics, biology, and other natural sciences in which symbolic regression can provide valuable insights and discover new laws of nature. A widespread Deep Neural Networks do not provide interpretable solutions.…
In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…
Recently, a complex variational autoencoder (VAE)-based single-channel speech enhancement system based on the DCCRN architecture has been proposed. In this system, a noise suppression VAE (NSVAE) learns to extract clean speech…
Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only…
In this paper, we address the unsupervised speech enhancement problem based on recurrent variational autoencoder (RVAE). This approach offers promising generalization performance over the supervised counterpart. Nevertheless, the involved…
Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…
We propose a method for MIMO decoding when channel state information (CSI) is unknown to both the transmitter and receiver. The proposed method requires some structure in the transmitted signal for the decoding to be effective, in…
Recently, autoencoders (AEs) have gained interest for creating parametric and invertible projections of multidimensional data. Parametric projections make it possible to embed new, unseen samples without recalculating the entire projection,…
Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent…
We consider the multichannel blind deconvolution problem where we observe the output of multiple channels that are all excited with the same unknown input. From these observations, we wish to estimate the impulse responses of each of the…
Variational Autoencoders (VAEs) provide a flexible and scalable framework for non-linear dimensionality reduction. However, in application domains such as genomics where data sets are typically tabular and high-dimensional, a black-box…
Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale structures and functionalities. This necessitates the development of the machine…
Pilot contamination (PC) is a well-known problem that affects massive multiple-input multiple-output (MIMO) systems. When frequency and pilots are reused between different cells, PC constitutes one of the main bottlenecks of the system's…
We describe our submitted system for the ZeroSpeech Challenge 2019. The current challenge theme addresses the difficulty of constructing a speech synthesizer without any text or phonetic labels and requires a system that can (1) discover…
We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input…
Inter-symbol interference (ISI) with heteroscedastic, or state-dependent, noise is a defining feature of molecular communication via diffusion (MCvD). However, such noise variance dependency across ISI states has not been systematically…
This work proposes an iterative channel estimation, detection and decoding (ICEDD) scheme for the uplink of multi-user multi-antenna systems assisted by multiple reconfigurable intelligent surfaces (RIS)}. A novel iterative code-aided…
A shift-invariant variational autoencoder (shift-VAE) is developed as an unsupervised method for the analysis of spectral data in the presence of shifts along the parameter axis, disentangling the physically-relevant shifts from other…
An effective approach to non-parallel voice conversion (VC) is to utilize deep neural networks (DNNs), specifically variational auto encoders (VAEs), to model the latent structure of speech in an unsupervised manner. A previous study has…
A discrete-time intersymbol interference channel with additive Gaussian noise is considered, where only the receiver has knowledge of the channel impulse response. An approach for combining decision-feedback equalization with channel coding…