Tempo comes with tools for automatically detecting features in audio files. Currently there are tools for detecting fly song and mouse vocalization. To run one of the tools choose Edit -> Detect Features or click the equivalent icon on the toolbar.
This detector looks for differences between existing sets of features. It will show which features would need to be added and which would need to be removed to make the sets identical. Thresholds for how different features can be in time and frequency can be set.
This detector can find sine and pulse song in audio recordings of Drosophila. It is based on the FlySongSegmenter software published in:
Arthur et al.: Multi-channel acoustic recording and automated analysis of Drosophila courtship songs. BMC Biology 2013 11:11
and available at <http://github.com/FlyCourtship/FlySongSegmenter>.
This detector can find vocalizations in audio recordings of mice. It is based on the Ax software published in:
???
and available at ???.
This detector can find repeated sequences of features in other sets of features. Each “train” that is found has a minimum number of repeats and a maximum time between each feature within the train. For example, it can find a minimum of ten fly song pulses in a row, no more than 0.1 seconds apart. Typically it is used to detect trains of pulses from fly song but can be used in other contexts.