Utilizing synthetic training data for the supervised classification of rat ultrasonic vocalizations
This addresses the workload in analyzing rodent vocalizations for behavioral research, though it is incremental as it builds on existing CNNs with data augmentation.
The study tackled the time-consuming manual classification of rat ultrasonic vocalizations by comparing two convolutional neural networks (CNNs) against human performance, finding that VocalMat outperformed DeepSqueak and that adding synthetic training data improved accuracy to near-human levels.
Murine rodents generate ultrasonic vocalizations (USVs) with frequencies that extend to around 120kHz. These calls are important in social behaviour, and so their analysis can provide insights into the function of vocal communication, and its dysfunction. The manual identification of USVs, and subsequent classification into different subcategories is time consuming. Although machine learning approaches for identification and classification can lead to enormous efficiency gains, the time and effort required to generate training data can be high, and the accuracy of current approaches can be problematic. Here we compare the detection and classification performance of a trained human against two convolutional neural networks (CNNs), DeepSqueak and VocalMat, on audio containing rat USVs. Furthermore, we test the effect of inserting synthetic USVs into the training data of the VocalMat CNN as a means of reducing the workload associated with generating a training set. Our results indicate that VocalMat outperformed the DeepSqueak CNN on measures of call identification, and classification. Additionally, we found that the augmentation of training data with synthetic images resulted in a further improvement in accuracy, such that it was sufficiently close to human performance to allow for the use of this software in laboratory conditions.