Amadeus: Autoregressive Model With Bidirectional Attribute Modelling For Symbolic Music

Abstract

Existing state-of-the-art symbolic music generation models predominantly adopt autoregressive or hierarchical autoregressive architectures, modelling symbolic music as a sequence of attribute tokens with unidirectional temporal dependencies, under the assumption of a fixed, strict dependency structure among these attributes. However, we observe that using different attributes as the initial token in these models leads to comparable performance. This suggests that the attributes of a musical note are, in essence, a concurrent and unordered set, rather than a temporally dependent sequence. Based on this insight, we introduce Amadeus, a novel symbolic music generation framework. Amadeus adopts a two-level architecture: an autoregressive model for note sequences and a bidirectional discrete diffusion model for attributes. To enhance performance, we propose Music Latent Space Discriminability Enhancement Strategy(MLSDES), incorporating contrastive learning constraints that amplify discrimin

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysu2025amadeus

Related papers

• Conditional Diffusion As Latent Constraints For Controllable Symbolic Music Generation (2025)0.00
• Learning Style-aware Symbolic Music Representations By Adversarial Autoencoders (2020)2.26
• Fusing Memory And Attention: A Study On LSTM, Transformer And Hybrid Architectures For Symbolic Music Generation (2026)0.00
• Midi-sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN Networks For Symbolic Single-track Music Generation (2019)0.00
• On The Joint Minimization Of Regularization Loss Functions In Deep Variational Bayesian Methods For Attribute-controlled Symbolic Music Generation (2025)0.00
• The Effect Of Explicit Structure Encoding Of Deep Neural Networks For Symbolic Music Generation (2018)11.49
• Rethinking Recurrent Latent Variable Model For Music Composition (2018)7.50
• A Predictive Model For Music Based On Learned Interval Representations (2018)0.00