Ponències/Comunicacions de congressos
Recent Submissions
-
Adaptive and iterative QoT estimator retraining for launch power optimization
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessWe dynamically optimize the transponders launch powers with iterative closed control loops. We close the loop after an adaptable number of algorithm’s intermediate calculations, to monitor and retrain the QoT estimator ... -
Machine learning assisted EDFA gain ripple modelling for accurate QoT estimation
(The Institution of Engineering and Technology, 2019)
Conference report
Open AccessWavelength dependent EDFA gain ripple has an impact on connection's OSNR performance. We propose a machine learning regression model to estimate the end to end gain ripple penalty and to increase QoT estimation accuracy. -
Data plane elements for optical performance monitoring agnostic to the modulation format for disaggregated optical networks
(2020)
Conference report
Open AccessIn this paper, data plane alternatives for optical performance monitoring are presented as enablers to address the key challenges in disaggregated optical networks. In fact, a key element of the disaggregated networks is ... -
Energy-efficient analog beamforming with short packets in millimeter-wave MIMO systems
(Institute of Electrical and Electronics Engineers (IEEE), 2020)
Conference report
Open AccessThe energy-aware design of fully analog precoders and combiners is investigated in this paper. To that aim, we consider a millimeter-wave short-packet communication scenario where power consumption and hardware complexity ... -
Dataset reduction for neural network based digital predistorters under strong nonlinearities
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessThe artificial neural networks (ANN) are gaining momentum in the digital predistorters (DPD) thanks to their inherently good approximation capabilities. Under strong or complex power amplifier nonlinearities, the size of ... -
Rate allocation in massive multiple access combining successive decoding with error control
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessThe Gaussian multiple access channel under asymptotically many code-division-multiple-access users and successive interference cancellation (SIC) is investigated in this work. Users transmit n-symbol packets and select ... -
Double multi-head attention for speaker verification
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessMost state-of-the-art Deep Learning systems for text-independent speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a ... -
Fourier analysis of submillimeter-wave scattering from the human cornea
(Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessWave scattering from a human cornea illuminated with a submillimeter-wave Gaussian beam is explored with Fourier analysis. This new approach enabled us to investigate the cornea as a coated sphere rather than a homogenized ... -
Multilingual machine translation: Closing the gap between shared and language-specific encoder-decoders
(Association for Computational Linguistics, 2021)
Conference lecture
Open AccessState-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on ... -
Estimation of information in parallel Gaussian channels via model order selection
(Institute of Electrical and Electronics Engineers (IEEE), 2020)
Conference lecture
Open AccessWe study the problem of estimating the overall mutual information in M independent parallel discrete-time memory-less Gaussian channels from N independent data sample pairs per channel (inputs and outputs). We focus on the ... -
The TALP-UPC system for the WMT similar language task: statistical vs neural machine translation
(Association for Computational Linguistics, 2019)
Conference lecture
Open AccessAlthough the problem of similar language translation has been an area of research interest for many years, yet it is still far from being solved. In this paper, we study the performance of two popular approaches: statistical ... -
Machine-learning based traffic forecasting for resource management in C-RAN
(Institute of Electrical and Electronics Engineers (IEEE), 2020)
Conference report
Restricted access - publisher's policyThe assumption of a fixed computational capacityat the Baseband Unit (BBU) pools in a Cloud Radio Access Network (C-RAN) deployment results in underutilized resourcesor unsatisfied users depending on ...
RSS 1.0