[NFBCS] SAND Challenge @IEEE ICASSP 2026

[Nadia Brancati]

Dear Colleague,
I deeply apologize if you received multiple copies of this call.

We cordially invite you to participate in the SAND “Speech Analysis for
Neurodegenerative Diseases” Challenge, which will be held during the IEEE
ICASSP 2026 international conference.
We encourage you to tackle one or both critical tasks:
- Classifying patients;
- Predicting disease progression over time.

Go to *www.sand.icar.cnr.it <http://www.sand.icar.cnr.it>* and register
your team for the challenge through the *Sign Up* section.
Once logged in, you can access the *Dashboard* from the menu, where the
dataset will be available for download.

The five teams with the highest scores will be invited to present their
work at IEEE ICASSP 2026, which will take place in Barcelona, Spain, from
May 4 to 8, 2026.
The contributions will be published in the official conference proceedings,
indexed in the most important academic databases, such as IEEE Xplore
Digital Library, Scopus, and Web of Science.

If you need any information or have any questions, please do not hesitate
to contact us.
Best Regards

=======================================================
SAND - Speech Analysis for Neurodegenerative Diseases challenge
@IEEE International Conference on Acoustics, Speech, and Signal Processing

4-8 May 2026, Barcelona, Spain
https://www.sand.icar.cnr.it/
=======================================================


MISSION:
-----------------------------------------------------------------------------------------------

This challenge deals with Amyotrophic Lateral Sclerosis (ALS). Starting
from a data set of vocal signals gathered by the organizers from both ill
and healthy subjects, the challenge proposes two different tasks: (i)
classify the subjects, and (ii) predict how the disease worsens over time.


INTRODUCTION:
-----------------------------------------------------------------------------------------------
SAND stems from the need to analyze noninvasive, objective, and scalable
biomarkers for early diagnosis and longitudinal monitoring. This is because
diseases such as ALS, present complex diagnostic challenges due to
heterogeneous symptom profiles and overlapping clinical features. Current
diagnostic tools are largely based on subjective clinical scales and often
fail to detect early changes, resulting in delayed intervention and
suboptimal care for patients. This underscores the urgent need to use
noninvasive biomarkers.

With this challenge, we would like to redefine neurodegenerative disease
assessment by positioning speech as a central, AI-powered biomarker for
diagnosis and monitoring.
Speech captures the interaction between motor and cognitive systems and is
often subtly impaired in the prodromal phases of neurodegeneration. Unlike
traditional biomarkers (e.g., neuroimaging, CSF analysis), voice data can
be collected easily, repeatedly, and inexpensively, offering a
transformative opportunity for global, equitable healthcare solutions.

GOALS:
-----------------------------------------------------------------------------------------------
We have designed two tasks to address the major challenges faced in the
monitoring of neurodegenerative diseases.

We warmly welcome researchers from academia and industry to participate and
jointly explore reliable solutions
for these challenging scenarios. Participants can contribute to one or both
tasks proposed here:
• TASK 1: multi-class classification at time 0 (first assessment);
• TASK 2: multi-class prediction (latest assessment).

Detailed information and all guidelines are available on the challenge's
official website, www.sand.icar.cnr.it

The five highest-ranked teams will be invited to showcase their work at the
IEEE ICASSP 2026 Conference.

Accepted contributions will be published in the official ICASSP proceedings
(IEEE-indexed).
The challenge-dedicated session will highlight presentations from the
top-performing participants and conclude
with a panel discussion.

Don’t miss this engaging event!


IMPORTANT DATES:
-----------------------------------------------------------------------------------------------
• September 01, 2025: Challenge Registration opens and Release of the
datasets (training)
• October 01, 2025: Release of the datasets (testing) - first day for
submitting results and code
• November 20, 2025: Challenge submission closes – last day for
registration, submitting results, and code
• December 02, 2025: Results announcement
• December 07, 2025: 2-page Papers Due (by invitation only)
• January 11, 2026: 2-page Paper Acceptance Notification
• January 18, 2026: Camera-ready 2-page Papers Due


-- 
Nadia Brancati
Researcher @ AI-ISA Lab
<https://www.icar.cnr.it/en/gruppi-di-ricerca/artificial-intelligence-in-image-and-signal-analysis/>
Institute for High Performance Computing and Networking - National Research
Council of Italy (CNR - ICAR)
Via P. Castellino, 111 - 80131 Napoli
Tel. 081.6139228
nadia.brancati at icar.cnr.it
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://nfbnet.org/pipermail/nfbcs_nfbnet.org/attachments/20250917/d16c6de7/attachment.htm>