50 citations · 91 across the 12 of their papers we have counts for
12 papers
Towards Robust Waveform-Based Acoustic Models
Dino Oglic, Zoran Cvetkovic, Peter Sollich +2
We study the problem of learning robust acoustic models in adverse environments, characterized by a significant mismatch between training and test conditions. This problem is of pa…
When saliency goes off on a tangent: Interpreting Deep Neural Networks with nonlinear saliency maps
Jan Rosenzweig, Zoran Cvetkovic, Ivana Rosenzweig
A fundamental bottleneck in utilising complex machine learning systems for critical applications has been not knowing why they do and what they do, thus preventing the development…
Goldilocks Neural Networks
Jan Rosenzweig, Zoran Cvetkovic, Ivana Rosenzweig
We introduce the new "Goldilocks" class of activation functions, which non-linearly deform the input signal only locally when the input signal is in the appropriate range. The smal…
ITENE: Intrinsic Transfer Entropy Neural Estimator
Jingjing Zhang, Osvaldo Simeone, Zoran Cvetkovic +2
Quantifying the directionality of information flow is instrumental in understanding, and possibly controlling, the operation of many complex systems, such as transportation, social…
Localization Uncertainty in Time-Amplitude Stereophonic Reproduction
Enzo De Sena, Zoran Cvetkovic, Huseyin Hacihabiboglu +2
This article studies the effects of inter-channel time and level differences in stereophonic reproduction on perceived localization uncertainty, which is defined as how difficult i…
Dictionary Learning with BLOTLESS Update
Qi Yu, Wei Dai, Zoran Cvetkovic +1
Algorithms for learning a dictionary to sparsely represent a given dataset typically alternate between sparse coding and dictionary update stages. Methods for dictionary update aim…
Learning Waveform-Based Acoustic Models using Deep Variational Convolutional Neural Networks
Dino Oglic, Zoran Cvetkovic, Peter Sollich
We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech re…
Efficient Synthesis of Room Acoustics via Scattering Delay Networks
Enzo De Sena, Huseyin Hacihabiboglu, Zoran Cvetkovic +1
An acoustic reverberator consisting of a network of delay lines connected via scattering junctions is proposed. All parameters of the reverberator are derived from physical propert…
A Subband-Based SVM Front-End for Robust ASR
Jibran Yousafzai, Zoran Cvetkovic, Peter Sollich +1
This work proposes a novel support vector machine (SVM) based robust automatic speech recognition (ASR) front-end that operates on an ensemble of the subband components of high-dim…
Speech Recognition Front End Without Information Loss
Matthew Ager, Zoran Cvetkovic, Peter Sollich
Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness o…
Classification of Human Ventricular Arrhythmia in High Dimensional Representation Spaces
Yaqub Alwan, Zoran Cvetkovic, Michael Curtis
We studied classification of human ECGs labelled as normal sinus rhythm, ventricular fibrillation and ventricular tachycardia by means of support vector machines in different repre…
Weyl-Heisenberg Spaces for Robust Orthogonal Frequency Division Multiplexing
Zoran Cvetkovic, Vincent Sinn
Design of Weyl-Heisenberg sets of waveforms for robust orthogonal frequency division multiplex- ing (OFDM) has been the subject of a considerable volume of work. In this paper, a c…