Machine Learning for Signal Processing

Supported by the SPS Challenge Program.

Accurate analysis of liver vasculature in three dimensions (3D) is essential for a variety of medical procedures including computer-aided diagnosis, treatment planning, or pre-operative planning of hepatic diseases.

Supported by the SPS Challenge Program.

This challenge addresses the global problem of hearing loss, which will affect 1 in 10 people by 2050. Hearing loss can create many issues with music: quieter passages being inaudible; poor and anomalous pitch perception; and difficulties identifying and picking out instruments and lyrics.

Supported by the SPS Challenge Program

The George B. Moody PhysioNet Challenges are annual competitions that invite participants to develop automated approaches for addressing important physiological and clinical problems. The 2024 Challenge invites teams to develop algorithms for digitizing and classifying electrocardiograms (ECGs) captured from images or paper printouts. 

PLC is an important part of audio telecommunications technology and codec development, and methods for performing PLC using machine learning approaches are now becoming viable for practical use.

This challenge will require developing an engine for signal separation  of radio-frequency (RF) waveforms. At inference time, a superposition of a signal of interest (SOI) and an interfering signal will be fed to the engine, which should recover the SOI by performing a sophisticated interference cancellation. 

Associated SPS Event: IEEE ICASSP 2022 Grand Challenge

The L3DAS22 Challenge aims at encouraging and fostering research on machine learning for 3D audio signal processing. 3D audio is gaining increasing interest in the machine learning community in recent years. The range of applications is incredibly wide, extending from virtual and real conferencing to autonomous driving, surveillance and many more.

3D audio is gaining increasing interest in the machine learning community in recent years. The field of application is incredibly wide and ranges from virtual and real conferencing to game development, music production, autonomous driving, surveillance and many more. In this context, Ambisonics prevails among other 3D audio formats for its simplicity, effectiveness and flexibility.

A new Challenge on self-awareness in heterogeneous multi-robot systems has been organized within the first International Conference on Autonomous Systems (ICAS 2021). The research field of this competition is the unsupervised anomaly detection through self-aware autonomous systems, which is an active topic involving IEEE Signal Processing Society, also through the Autonomous Systems Initiative, and Intelligent Transportation Systems Society.

The Clarity Project will be organising a series of machine learning challenges for advancing hearing-aid signal processing and speech-in-noise perception modelling.