A Reliable and Efficient Detection Pipeline for Rodent Ultrasonic Vocalizations

2025-03-24

AI Summary

Existing USV (ultrasonic vocalization) detection methods predominantly rely on machine learning, suffering from poor generalizability and unstable cross-dataset performance. To address this, we propose ContourUSV—the first machine-learning-free, time-frequency contour-driven framework for robust USV detection. It comprises spectrogram denoising, contour extraction, rule-based morphological post-processing, and comprehensive evaluation using multiple metrics (precision, recall, F1-score, and specificity). Concurrently, we release a new publicly available dataset to enhance cross-domain reliability. Evaluated on two benchmark datasets against three state-of-the-art (SOTA) methods, ContourUSV achieves average improvements of 1.51× in precision, 1.80× in F1-score, and 1.49× in specificity, while accelerating inference by 117×. These results demonstrate substantial gains in both detection reliability and computational efficiency.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Analyzing ultrasonic vocalizations (USVs) is crucial for understanding rodents' affective states and social behaviors, but the manual analysis is time-consuming and prone to errors. Automated USV detection systems have been developed to address these challenges. Yet, these systems often rely on machine learning and fail to generalize effectively to new datasets. To tackle these shortcomings, we introduce ContourUSV, an efficient automated system for detecting USVs from audio recordings. Our pipeline includes spectrogram generation, cleaning, pre-processing, contour detection, post-processing, and evaluation against manual annotations. To ensure robustness and reliability, we compared ContourUSV with three state-of-the-art systems using an existing open-access USV dataset (USVSEG) and a second dataset we are releasing publicly along with this paper. On average, across the two datasets, ContourUSV outperformed the other three systems with a 1.51x improvement in precision, 1.17x in recall, 1.80x in F1 score, and 1.49x in specificity while achieving an average speedup of 117.07x.

Problem

• Automating rodent ultrasonic vocalization detection to replace manual analysis
• Improving generalization of USV detection systems across diverse datasets
• Enhancing detection precision, recall, and speed compared to existing methods

Innovation

• Automated USV detection with ContourUSV
• Pipeline includes spectrogram and contour processing
• Outperforms others in precision, recall, and speed