Topic: canaries

Songbirds provide a powerful model system for studying sensory-motor learning. Many analyses require time-consuming manual annotation of the units of song, often called syllables. However, songbirds produce many more songs than can be annotated by hand, creating a bottleneck that limits the questions researchers can answer. Methods exist for automated annotation[1], but, as we show, these methods exhibit limitations when applied to songs with many syllable types and variable transitions. To address these issues, we developed an artificial neural network, TweetyNet[2], that segments and labels

Many complex behaviors involve sequences of basic motor or vocal elements governed by syntactic rules, which facilitate flexible and adaptive actions. Songbirds that crystallize their repertoire of vocal syllables and syllable-to-syllable transitions allow researchers to build probabilistic models of syntax rules, providing insight into underlying neural mechanisms. However, in many complex behaviors, syntax rules change over time, such as during learning or in response to new environmental and social contexts. Here, we investigated the songs of canaries, a seasonal songbird. Canaries learn a

Manual annotation of birdsong remains a significant bottleneck in systems neuroscience, especially for species like canaries with complex vocal repertoires. Existing unsupervised dimensionality reduction approaches, such as Uniform Manifold and Projection (UMAP), can be used to analyze stereotyped songs but require extensive preprocessing. Alternatively, current deep-learning models for song annotation still require extensive training data . We present TweetyBERT, a novel self-supervised deep neural network that learns to parse complex birdsongs without annotated training data. The process res