Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song Generation

Excerpt

arXiv:2609.39552v1 Announce Type: cross Abstract: Text-to-song generation models can be prompted to imitate specific artists or regurgitate entire songs from their training data. Although these phenomena have been documented behaviorally on small datasets, little is known about the internal representations that may give rise to them. Prior interpretability work on generative audio has focused on locating semantic concepts such as genre or time signature within model activations. In this work, we