SPS Webinars

Sound field estimation using a microphone array is a fundamental problem in acoustic signal processing, which has a wide variety of applications, such as visualization/auralization of an acoustic field, spatial audio reproduction using a loudspeaker array or headphones, and active noise cancellation in a spatial region.

As a popular signal modeling technique, sparse representation (SR) has achieved great success in image fusion during the last decade. However, due to the patch-based manner adopted in standard SR models, most existing SR-based image fusion methods suffer from two drawbacks, namely, limited ability in detail preservation and high sensitivity to mis-registration, while these two issues are of great concern in image fusion. 

Many problems encountered in sensing and imaging can be formulated as estimating a low-rank object from incomplete, and possibly corrupted, linear measurements; prominent examples include matrix completion and tensor completion. 

The 2022 International Conference on Acoustics, Speech, & Signal Processing (ICASSP) invites proposals for its Signal Processing Grand Challenges (SPGC) program. ICASSP is the IEEE Signal Processing Society’s flagship conference targeting signal processing and its applications.

Adaptive (i.e., data-driven) methods have become very popular these last decades. Among the existing techniques, the empirical mode decomposition has proven to be very efficient in extracting accurate time-frequency information from non-stationary signals.

This webinar will demonstrate how deep learning can solve difficult communication problems that prior approaches often fail with two case studies. The first half will discuss a novel iterative BP-CNN architecture for channel decoding under correlated noise. This architecture concatenates a trained convolutional neural network (CNN) with a standard belief-propagation (BP) decoder. 

We study the dual problem of image super-resolution (SR), which we term image compact-resolution (CR). Opposite to image SR that hallucinates a visually plausible high-resolution image given a low-resolution input, image CR provides a low-resolution version of a high-resolution image, such that the low-resolution version is both visually pleasing and as informative as possible compared to the high-resolution image. 

Facial expressions are configurations of different muscle movements in the face. The local characters of muscle movements play an important role in distinguishing facial expressions by machines. In this webinar, the presenter will explore the local characters local characters of muscle movements by introducing the attention mechanism into two frameworks.

This webinar will discuss the MMSE channel estimator for a simple SIMO system model, without knowledge of the required channel statistics. Although the derived MMSE estimator is computationally intractable in the general form, its structure can be used to motivate a neural network architecture with lower complexity.

Graphs are generic models of signal structure that can help to learn in several practical problems. To learn from graph data, we need scalable architectures that can be trained on moderate dataset sizes and that can be implemented in a distributed manner. Drawing from graph signal processing, the webinar will define graph convolutions and use them to introduce graph neural networks (GNNs).