Abstract
Vocalizations are widely used for communication between animals. Mice use a large repertoire of ultrasonic vocalizations (USVs) in different social contexts. During social interaction recognizing the partner's sex is important, however, previous research remained inconclusive whether individual USVs contain this information. Using deep neural networks (DNNs) to classify the sex of the emitting mouse from the spectrogram we obtain unprecedented performance (77%, vs. SVM: 56%, Regression: 51%). Performance was even higher (85%) if the DNN could also use each mouse's individual properties during training, which may, however, be of limited practical value. Splitting estimation into two DNNs and using 24 extracted features per USV, spectrogram-to-features and features-to-sex (60%) failed to reach single-step performance. Extending the features by each USVs spectral line, frequency and time marginal in a semi-convolutional DNN resulted in a performance mid-way (64%). Analyzing the network structure suggests an increase in sparsity of activation and correlation with sex, specifically in the fully-connected layers. A detailed analysis of the USV structure, reveals a subset of male vocalizations characterized by a few acoustic features, while the majority of sex differences appear to rely on a complex combination of many features. The same network architecture was also able to achieve above-chance classification for cortexless mice, which were considered indistinguishable before. In summary, spectrotemporal differences between male and female USVs allow at least their partial classification, which enables sexual recognition between mice and automated attribution of USVs during analysis of social interactions.
Highlights
Sexual identification on the basis of sensory cues provides important information for successful reproduction
We find that the distinction of mouse (C57Bl/6) male/female ultrasonic vocalizations (USVs) can be successfully performed using advanced classification using deep learning [23]: A custom-developed Deep Neural Network (DNN) reaches an average accuracy of 77%, substantially exceeding the performance of linear or nonlinear classifiers, which could be further improved to 85%, if properties of individual mice are available and can be included in the classifier
Separate DNNs were trained for predicting features from spectrograms as well as sex from features, on the basis of human-classified features
Summary
Sexual identification on the basis of sensory cues provides important information for successful reproduction. When listening to a conversation, humans can typically make an educated guess about the sexes of the participants. Limited research on this topic has suggested a range of acoustic predictors, mostly the fundamental frequency and formant measures [1]. Mice vocalize frequently during social interactions [2,3,4,5,6]. The complexity of the vocalizations produced during social interactions can be substantial [7,8,9]. Experiments replaying male mouse courtship songs to adult females suggest that at least females are able to guess the sex of other mice based on the properties of individual vocalizations [10,11]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
