L3DAS24: Computational Processing for 3D Audio Sources

Special Session at 2024 International Joint Conference on Neural Networks (IJCNN)
at IEEE WCCI 2024 - June 30 –July 5, 2024 – Yokohama, Japan

 Aim & Scope of the Special Session

The Computational Audio Processing (CAP) Task Force of the IEEE Computational Intelligence Society is glad to propose a special session on Computational Processing of 3D Audio Sources.

The special session aims at encouraging and fostering research on neural networks and computational intelligence methods for 3D audio signal processing. Applications may involve both the analysis and synthesis of spatial audio sources, giving rise to a wide variety of tasks to be addressed by neural audio architectures.

The special session is in line with a series of events under the name of the L3DAS – Learning 3D Audio Sources (www.l3das.com), organized by the team along with other international researchers. While the previous editions of L3DAS were organized as challenges, this year we propose a special session in collaboration with the Computational Audio Processing Task Forse since the number of publicly available 3D audio datasets is significantly increased in the last years.

The aim of this session is therefore to provide the most recent advances Computational Processing of 3D Audio Sources with a wide range of processing tasks and applications in real acoustic environments.

Paper submission guidelines: https://2024.ieeewcci.org/submission

 Important Dates

Paper Submission Deadline

January 15, 2024

Paper Acceptance Notification

March 15, 2024

Camera-Ready Submission

May 01, 2024


Potential topics include, but are not limited, to:

  • Differentiable 3D Audio Signal Processing
  • 3D Acoustic Impulse Response Estimation
  • 3D Speech Enhancement
  • Multimodal Spatial Audio Processing
  • Neural Audio Beamforming
  • Neural Spatial Audio Coding
  • Generative models for 3D Audio
  • Mono-to-3D Audio Translation
  • Speech Emotion Recognition in Spatial Sound Fields
  • 3D Sound Event Localization and Detection
  • Neural Spatial Audio Reproduction
  • Psychoacoustic and Perceptual Spatial Audio Evaluation
  • Neural Architectures for Extended Reality
  • Spatial Audio for Cinema and Entertainment


Michele Scarpiniti, Sapienza University of Rome, Italy
Riccardo Fosco Gramaccioni, Sapienza University of Rome, Italy
Christian Marinoni, Sapienza University of Rome, Italy
Danilo Comminiello, Sapienza University of Rome, Italy