Call Classification

In addition to manually classifying calls, DeepSqueak includes two automated methods.

Unsupervised clustering applies featured-based machine learning with k-means to cluster calls, by minimizing the variance between a call's features and the nearest prototype cluster.

Supervised classification uses a convolution neural network to classify calls based on the spectrogram.

We've found that creating clustering with unsupervised methods, and using the cleanest clusters to train a supervised classification network, resulted in fast and accurate clustering.

Clusters may be viewed and renamed with "Tools > Call Classification > View Clusters"

To view a visual embedding of the call features (see supplemental figure 6), create a t-sne plot with "Tools > Call Classification > Create t-sne". This will plot each call in a two-dimensional field, places similar calls near each other. The similarity is calculated from the reduced dimension contours used for clustering. Set the size of the image in pixels. The size of the calls in pixels is constant, so larger image sizes will produce smaller calls.