Enhancing the analysis of murine neonatal ultrasonic vocalizations

• Verfasst von: Herdt, Rudolf [VerfasserIn]
• Verfasst von: Kinzel, Louisa [VerfasserIn]
• Verfasst von: Maaß, Johann Georg [VerfasserIn]
• Verfasst von: Walther, Marvin [VerfasserIn]
• Verfasst von: Fröhlich, Henning [VerfasserIn]
• Verfasst von: Schubert, Tim Felix [VerfasserIn]
• Verfasst von: Maass, Peter [VerfasserIn]
• Verfasst von: Schaaf, Christian P. [VerfasserIn]
• Titel: Enhancing the analysis of murine neonatal ultrasonic vocalizations
• Titelzusatz: development, evaluation, and application of different mathematical models
• Verf.angabe: Rudolf Herdt, Louisa Kinzel, Johann Georg Maaß, Marvin Walther, Henning Fröhlich, Tim Schubert, Peter Maass and Christian Patrick Schaaf
• E-Jahr: 2024
• Jahr: October 14 2024
• Umfang: 19 S.
• Illustrationen: Illustrationen
• Fussnoten: Gesehen am 24.03.2025
• Titel Quelle: Enthalten in: Acoustical Society of AmericaThe journal of the Acoustical Society of America
• Ort Quelle: Melville, NY : AIP Publ., 1929
• Jahr Quelle: 2024
• Band/Heft Quelle: 156(2024), 4 vom: Okt., Seite 2448-2466
• ISSN Quelle: 1520-8524
• DOI: doi:10.1121/10.0030473
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 192038443X

Abstract

Rodents employ a broad spectrum of ultrasonic vocalizations (USVs) for social communication. As these vocalizations offer valuable insights into affective states, social interactions, and developmental stages of animals, various deep learning approaches have aimed at automating both the quantitative (detection) and qualitative (classification) analysis of USVs. So far, no notable efforts have been made to determine the most suitable architecture. We present the first systematic evaluation of different types of neural networks for USV classification. We assessed various feedforward networks, including a custom-built, fully-connected network, a custom-built convolutional neural network, several residual neural networks, an EfficientNet, and a Vision Transformer. Our analysis concluded that convolutional networks with residual connections specifically adapted to USV data, are the most suitable architecture for analyzing USVs. Paired with a refined, entropy-based detection algorithm (achieving recall of 94.9 % and precision of 99.3 %), the best architecture (achieving 86.79 % accuracy) was integrated into a fully automated pipeline capable of analyzing extensive USV datasets with high reliability. In ongoing projects, our pipeline has proven to be a valuable tool in studying neonatal USVs. By comparing these distinct deep learning architectures side by side, we have established a solid foundation for future research.