Danilo Comminiello

Pubblicazioni

Titolo Pubblicato in Anno
Quaternion widely linear forecasting of air quality Progresses in Artificial Intelligence and Neural Systems 2021
Deep recurrent neural networks for audio classification in construction sites European signal processing conference 2021
A wide multimodal dense U-net for fast magnetic resonance imaging European signal processing conference 2021
Flexible generative adversarial networks with non-parametric activation functions Smart Innovation, Systems and Technologies 2021
A quaternion-valued variational autoencoder ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2021
L3DAS21 challenge: machine learning for 3D audio signal processing IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021
An information-theoretic perspective on proper quaternion variational autoencoders ENTROPY 2021
Music genre classification using stacked auto-encoders Smart Innovation, Systems and Technologies 2020
Differentiable branching in deep networks for fast inference ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2020
Compressing deep-quaternion neural networks with targeted regularisation CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY 2020
Quaternion neural networks for 3D sound source localization in reverberant environments IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020
Steady-state performance of an adaptive combined MISO filter using the multichannel affine projection algorithm ALGORITHMS 2019
Separation of drum and bass from monaural tracks Smart Innovation, Systems and Technologies 2019
On 4-dimensional hypercomplex algebras in adaptive signal processing Smart Innovation, Systems and Technologies 2019
Learning activation functions from data using cubic spline interpolation Smart Innovation, Systems and Technologies 2019
A low-complexity linear-in-the-parameters nonlinear filter for distorted speech signals Smart Innovation, Systems and Technologies 2019
Frequency-domain adaptive filtering: from real to hypercomplex signal processing 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019) 2019
Convex combination of spline adaptive filters Proceedings of the 27th European Signal Processing Conference (EUSIPCO2019) 2019
Widely linear kernels for complex-valued Kernel activation functions Proceedings 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019
Quaternion convolutional neural networks for detection and localization of 3D sound events Proceedings 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019

ERC

  • PE6_6
  • PE6_7
  • PE6_8
  • PE6_11
  • PE7_7

KET

  • Big data & computing
  • Life-science technologies & biotechnologies
  • Sustainable technologies & development

Interessi di ricerca

His research interests concern circuits and algorithms for machine learning and deep learning, with particular focus on audio processing and biomedical imaging.

Keywords

deep learning
machine learning
audio processing
3D audio
biomedical analysis
biomedical imaging
adaptive algorithms
nonlinear system identification
echo cancellation
generative adversarial models (GANs)
quaternion neural networks
Quaternion-Valued Adaptive Filtering
Regularization techniques
Speech recognition

Progetti di Ricerca

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma