Time-Shifted Token Scheduling for Symbolic Music Generation
This addresses the problem of balancing computational efficiency and musical coherence for researchers and practitioners in symbolic music generation, representing an incremental improvement.
The paper tackles the trade-off between efficiency and quality in symbolic music generation by adapting a delay-based scheduling mechanism to expand compound-like tokens across decoding steps, improving all metrics over standard compound tokenizations and narrowing the gap to fine-grained tokenizations on symbolic orchestral MIDI datasets.
Symbolic music generation faces a fundamental trade-off between efficiency and quality. Fine-grained tokenizations achieve strong coherence but incur long sequences and high complexity, while compact tokenizations improve efficiency at the expense of intra-token dependencies. To address this, we adapt a delay-based scheduling mechanism (DP) that expands compound-like tokens across decoding steps, enabling autoregressive modeling of intra-token dependencies while preserving efficiency. Notably, DP is a lightweight strategy that introduces no additional parameters and can be seamlessly integrated into existing representations. Experiments on symbolic orchestral MIDI datasets show that our method improves all metrics over standard compound tokenizations and narrows the gap to fine-grained tokenizations.