Sorry, you need to enable JavaScript to visit this website.

ICASSP is the world's largest and most comprehensive technical conference on signal processing and its applications. It provides a fantastic networking opportunity for like-minded professionals from around the world. ICASSP 2016 conference will feature world-class presentations by internationally renowned speakers and cutting-edge session topics.

A joint maximum likelihood (ML) modulation classification (MC) of the co-scheduled user and data detection receiver is developed


We propose two computationally efficient subspace detection algorithms, based on a preprocessing stage that consists of special layer ordering, followed by permutation-robust QR decomposition (QRD) and elementary matrix operations.


This paper studies distributionally robust chance-constrained minimum variance beamforming. In contrast to deterministic modeling of the steering vector, our approach models the uncertainty statistically via distributions. We select the weights that minimize the combined output power subject to the distributionally robust chance constraint that for all distributions in the uncertainty set, the gain should exceed unity with high probability.


This paper investigates the optimal design of precoders or decoders
under a channel inversion criterion for multi-user (MU) MIMO filterbank
multicarrier (FBMC) modulations. The base station (BS)
is assumed to use a single tap precoding/decoding matrix at each
subcarrier in the downlink/uplink, resulting in a low complexity of
implementation. The expression of the asymptotic mean squared error
(MSE) for this precoding/decoding design in the case of strong
channel selectivity is recalled and simplified. Optimizing the MSE


This presentation introduces a Deep Learning model that performs classification of the Audio Scene in the subway environment. The final goal is to detect Screams and Shouts for surveillance purposes. The model is a combination of Deep Belief Network and Deep Neural Network, (generatively pre-trained within the DBN framework and fine-tuned discriminatively within the DNN framework), and is trained on a novel database of pseudo-real signals collected in the Paris metro.