Abstract We utilize Lempel-Ziv universal compression for music note generation. We control the algorithm's tendency to over-copy or under-copy training data by manipulating the average sequence length saved in the dictionary.
Explore similar work May 18, 2026 · Julian D. Parker, Zach Evans, CJ Carr +4 Masked Autoencoders Neural Audio Codecs
Jun 11, 2026 · Dezhi Yu, Kyuil Lee, Yongkang Huang Generative Models Autoregressive Model
Jul 13, 2026 · Congren Dai, Danni Zhao, Enyang Liu +7 Music Generation Data Generation
May 18, 2026 · cs.SD J/K move · Enter open · S save
Julian D. Parker, Zach Evans, CJ Carr, Zachary Zukowski +3
Stability AI
Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio-codec autoencoder. In this work we introduce SAME (Semantically-Aligned Music autoEncoder), an autoencoder for stereo music and general audio that reaches a 4096
× \times × temporal compression ratio while maintaining reconstruction quality and downstream generative performance. We achieve this by combining a tranformer-based backbone with set of semantic regularisation approaches, phase-aware reconstruction losses and improved discriminator designs. The architecture delivers substantial computational cost benefits, through both its high compression ratio and its reliance on well-optimised transformer primitives. Two variants (a large SAME-L and a CPU-deployable SAME-S) are released in open-weights form.