Generating coherent and efficient melodic continuations with deterministic discrete diffusion.
Saved in:
| Title: | Generating coherent and efficient melodic continuations with deterministic discrete diffusion. |
|---|---|
| Authors: | Gao, Zhiqiang1 (AUTHOR) kiplingktlnnic@gmx.com, Gao, Yening2 (AUTHOR) |
| Source: | Automatika: Journal for Control, Measurement, Electronics, Computing & Communications. Dec2025, Vol. 66 Issue 4, p15-31. 17p. |
| Subjects: | Diffusion control, Musical composition, Themes in music |
| Abstract: | Melody continuation aims to automatically generate coherent melodic sequences conditioned on an initial musical motif, presenting significant challenges due to the intricate balance required between structural consistency, rhythmic coherence, and computational efficiency. This paper introduces Deterministic Discrete Diffusion for Melody Continuation (D3MC), a novel framework leveraging discrete diffusion processes with a deterministic mask-based sampling strategy. Unlike conventional autoregressive models suffering from slow sequential inference, or traditional diffusion models susceptible to rhythmic inconsistency, D3MC integrates a progressive timestep sampling schedule and a predominantly mask-driven noise injection strategy. This combination systematically preserves rhythmic and harmonic structures while enabling parallel prediction of melodic events. Evaluations conducted on the Lakh MIDI and MAESTRO datasets demonstrate superior performance of D3MC compared to leading baselines. Specifically, our model achieves a Pitch Contour Dynamic Time Warping (DTW) score of 13.1 (outperforming standard diffusion methods by approximately 10.9%), a Rhythm KL divergence of 0.44, and a Harmony compatibility score of 0.79, all achieved with an inference speed of merely 0.8 seconds per sequence–representing up to an 8.9-fold efficiency gain over autoregressive counterparts. [ABSTRACT FROM AUTHOR] |
| Copyright of Automatika: Journal for Control, Measurement, Electronics, Computing & Communications is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Melody continuation aims to automatically generate coherent melodic sequences conditioned on an initial musical motif, presenting significant challenges due to the intricate balance required between structural consistency, rhythmic coherence, and computational efficiency. This paper introduces Deterministic Discrete Diffusion for Melody Continuation (D3MC), a novel framework leveraging discrete diffusion processes with a deterministic mask-based sampling strategy. Unlike conventional autoregressive models suffering from slow sequential inference, or traditional diffusion models susceptible to rhythmic inconsistency, D3MC integrates a progressive timestep sampling schedule and a predominantly mask-driven noise injection strategy. This combination systematically preserves rhythmic and harmonic structures while enabling parallel prediction of melodic events. Evaluations conducted on the Lakh MIDI and MAESTRO datasets demonstrate superior performance of D3MC compared to leading baselines. Specifically, our model achieves a Pitch Contour Dynamic Time Warping (DTW) score of 13.1 (outperforming standard diffusion methods by approximately 10.9%), a Rhythm KL divergence of 0.44, and a Harmony compatibility score of 0.79, all achieved with an inference speed of merely 0.8 seconds per sequence–representing up to an 8.9-fold efficiency gain over autoregressive counterparts. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 00051144 |
| DOI: | 10.1080/00051144.2025.2591993 |
