A shared-task benchmark shows a simple CNN on audible-range spectrograms distinguishes autism-model mice from wild-type mice with UAR around 0.60 at segment level and 0.625 at subject level.
We described the extensive challenge dataset and reported a set of competitive baseline results that serve as bench- marks for participants’ approaches
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MADUV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge
A shared-task benchmark shows a simple CNN on audible-range spectrograms distinguishes autism-model mice from wild-type mice with UAR around 0.60 at segment level and 0.625 at subject level.