Individual-level monitoring is essential in many behavioural and bioacoustics studies, but collecting these data is costly in human effort. Many studies of bird vocalisations in particular also involve manipulating the animals or human presence during observations, which can bias vocal production. Autonomous recording units can be used to collect large amounts of data without human supervision, largely removing these sources of bias. Moreover, the recent progress of deep learning greatly facilitated analysing these large amounts of data, for instance to extract vocalisations, classify the species, or classify the vocalisation types in recordings. Acoustic individual identification, however, has so far largely remained limited to a single vocalisation type for a given species, preventing the use of these techniques for automated data collection. We developed a deep convolutional neural network to detect vocalisations as well as identify individuals regardless of the vocalisation produced. We tested it in a group of rooks, a Eurasian social corvid with a diverse vocal repertoire, and found the system to work reliably for these tasks. Our system can readily assist data collection and individual monitoring of groups of animals in both outdoor and indoor settings, even across long periods of time, and regardless of a species' vocal complexity.