Automatic Segmentation of Ultrasonic Vocalizations in Rodents
Ultrasonic vocalizations studies in rodents have increasingly drawn researchers attention as it have been considered a powerful tool to understand the animals behavior and their interactions in different social and environmental contexts.
This paper presents an entropy-based algorithm for accurate and robust segmentation of mouse ultrasonic calls. Instead of using the conventional energy-based features, the spectral entropy is developed to identify the audio segments accurately. The new approach for mice calls detection has been able to detect up to 97% of the vocalizations.
KeywordsRodents ultrasonic vocalizations Signal processing Signal segmentation Spectral Entropy
This work was supported by FCT fellowship SFRH/BPD/112863/2015 to L.I.P and FLAD Life Sciences 2016, BIGDATIMAGE (CENTRO-01-0145-FEDER, 000016) to M.C.B.
- 4.Harma, A.: Automatic identification of bird species based on sinusoidal modeling of syllables. In: 2003 IEEE International Conference on Acoustics Speech, Signal Processing 2003, Proceedings, (ICASSP 2003), vol. 5, p. V–545–8. IEEE (2004)Google Scholar
- 6.Ivanenko, A., Watkins, P., van Gerven, M.A.J., Hammerschmidt, K., Englitz, B.: Classification of mouse ultrasonic vocalizations using deep learning. bioRxiv, p. 358143, January 2018Google Scholar
- 7.MathWorks: Spectral entropy (2019)Google Scholar
- 8.Portfors, C.V.: Types and functions of ultrasonic vocalizations in laboratory rats and mice. J. Am. Assoc. Lab. Anim. Sci. 46(1), 28–34 (2007)Google Scholar
- 12.Vinet, L., Zhedanov, A.: Rodent Bioacoustics. Springer Handbook of Auditory Research, vol. 67. Springer International Publishing, Cham (2018)Google Scholar