Millisecond-scale detection of mouse ultrasonic vocalizations enables closed-loop experiments
- 1Institute for Experimental Epileptology and Cognition Research, University of Bonn Medical Faculty
Abstract
Mouse ultrasonic vocalizations (USVs) provide a rapidly evolving readout of social interaction but are typically analysed only after acquisition. Here we introduce DeepFisFis, a waveform-based neural network that detects USVs while they are being produced. DeepFisFis classifies consecutive 5 ms audio segments directly from the waveform with high accuracy, processing each segment in approximately 2.5 ms and therefore faster than the incoming audio stream. This enables ongoing vocalizations to guide experimental interventions in real time. In a deployed closed-loop system, detections triggered an external stimulus, demonstrating online control of ongoing vocal behaviour. DeepFisFis also enables event-triggered data acquisition: gating storage around detected calls preserved more than 99% of vocalization time while retaining only approximately 22% of the continuous recording. DeepFisFis thus transforms USVs from a retrospective behavioural readout into a real-time experimental signal for selective acquisition and closed-loop causal interrogation of vocal communication and its underlying neural circuits.
Related
- Heightened Fear Memory Retention During Infancy, but Not Number of Separation‐Induced Ultrasonic Vocalizations, Predicts a Fearful Phenotype in a Diverse Cohort of Rats
- Ultrasonic local anesthetic uncaging enables noninvasive, targeted, and transient knock-out of brain function
- Ultrasonic Detection of Venous Gas Emboli and Tissue Gas in Rodents: Toward Imaging Biomarkers for Decompression Stress
- SPECHTacle: An Efficient Detection and Visualization of Cell Specific Regulation in Single Cell-Based Experiments Using a Novel Combinatorial Computational Tool
- Fluorescence-based sorting of extracellular vesicles enables detection and omics
BibTeX
@misc{mohammadi2026millisecondscale,
title = {{Millisecond-scale detection of mouse ultrasonic vocalizations enables closed-loop experiments}},
author = {A. Mohammadi and J. Tillmann and M. K. Schwarz},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.754020},
url = {https://www.biorxiv.org/content/10.64898/2026.09.24.754020v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Millisecond-scale detection of mouse ultrasonic vocalizations enables closed-loop experiments
AU - A. Mohammadi
AU - J. Tillmann
AU - M. K. Schwarz
PY - 2026
DA - 2026/09/24
PB - bioRxiv
DO - 10.64898/2026.09.24.754020
UR - https://www.biorxiv.org/content/10.64898/2026.09.24.754020v1
AB - Mouse ultrasonic vocalizations (USVs) provide a rapidly evolving readout of social interaction but are typically analysed only after acquisition. Here we introduce DeepFisFis, a waveform-based neural network that detects USVs while they are being produced. DeepFisFis classifies consecutive 5 ms audio segments directly from the waveform with high accuracy, processing each segment in approximately 2.5 ms and therefore faster than the incoming audio stream. This enables ongoing vocalizations to guide experimental interventions in real time. In a deployed closed-loop system, detections triggered an external stimulus, demonstrating online control of ongoing vocal behaviour. DeepFisFis also enables event-triggered data acquisition: gating storage around detected calls preserved more than 99% of vocalization time while retaining only approximately 22% of the continuous recording. DeepFisFis thus transforms USVs from a retrospective behavioural readout into a real-time experimental signal for selective acquisition and closed-loop causal interrogation of vocal communication and its underlying neural circuits.
ER -