Saved in:
Bibliographic Details
Main Authors: Yang, Zijiang, Song, Meishu, Jing, Xin, Zhang, Haojie, Qian, Kun, Hu, Bin, Tamada, Kota, Takumi, Toru, Schuller, Björn W., Yamamoto, Yoshiharu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.04292
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912404790575104
author Yang, Zijiang
Song, Meishu
Jing, Xin
Zhang, Haojie
Qian, Kun
Hu, Bin
Tamada, Kota
Takumi, Toru
Schuller, Björn W.
Yamamoto, Yoshiharu
author_facet Yang, Zijiang
Song, Meishu
Jing, Xin
Zhang, Haojie
Qian, Kun
Hu, Bin
Tamada, Kota
Takumi, Toru
Schuller, Björn W.
Yamamoto, Yoshiharu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_04292
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MADUV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge
Yang, Zijiang
Song, Meishu
Jing, Xin
Zhang, Haojie
Qian, Kun
Hu, Bin
Tamada, Kota
Takumi, Toru
Schuller, Björn W.
Yamamoto, Yoshiharu
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
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.
title MADUV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2501.04292