MADUV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge

TL;DR

The MADUV challenge introduces a novel task of detecting autism in mice through ultrasound vocalizations, demonstrating the feasibility of automated classification using spectrogram features and machine learning.

Contribution

This work presents the first INTERSPEECH challenge focused on ASD detection in mice via vocalizations, providing a baseline system and encouraging interdisciplinary research.

Findings

Audible-range features achieved best performance (UAR 0.600 segment-level, 0.625 subject-level)

Automated ASD detection in mice via vocalizations is feasible

The challenge fosters collaboration between speech technology and biomedical research

Abstract

The Mice Autism Detection via Ultrasound Vocalization (MADUV) Challenge introduces the first INTERSPEECH challenge focused on detecting autism spectrum disorder (ASD) in mice through their vocalizations. Participants are tasked with developing models to automatically classify mice as either wild-type or ASD models based on recordings with a high sampling rate. Our baseline system employs a simple CNN-based classification using three different spectrogram features. Results demonstrate the feasibility of automated ASD detection, with the considered audible-range features achieving the best performance (UAR of 0.600 for segment-level and 0.625 for subject-level classification). This challenge bridges speech technology and biomedical research, offering opportunities to advance our understanding of ASD models through machine learning approaches. The findings suggest promising directions for vocalization analysis and highlight the potential value of audible and ultrasound vocalizations in ASD detection.