用预测控制方法生成有逻辑连贯性的音乐
Predictive Controlled Music
- 将音乐生成建模为预测控制问题，动态优化音符序列
- 采用前馈神经网络评估乐谱质量，作为优化目标
- 通过循环神经网络建模音符间关系，实现反馈式生成
本文提出一种新的算法作曲方法——预测控制音乐（Predictive Controlled Music, PCM），将模型预测控制（MPC）与音乐生成结合。PCM利用动态模型预测并优化音乐生成过程，将音符计算视为一个优化问题，通过最大化性能指标来生成音乐。采用基于前馈神经网络的评估函数对生成的乐谱进行评分，作为优化目标。同时，使用循环神经网络捕捉音符间的依赖关系，并将其作为约束条件嵌入到PCM优化中。与传统MPC类似，PCM以滚动时域方式计算音符，实现反馈控制下的预测生成。通过数值实例验证了该方法的有效性。
原文摘要 · Abstract (English)
This paper presents a new approach to algorithmic composition, called predictive controlled music (PCM), which combines model predictive control (MPC) with music generation. PCM uses dynamic models to predict and optimize the music generation process, where musical notes are computed in a manner similar to an MPC problem by optimizing a performance measure. A feedforward neural network-based assessment function is used to evaluate the generated musical score, which serves as the objective function of the PCM optimization problem. Furthermore, a recurrent neural network model is employed to capture the relationships among the variables in the musical notes, and this model is then used to define the constraints in the PCM. Similar to MPC, the proposed PCM computes musical notes in a receding-horizon manner, leading to feedback controlled prediction. Numerical examples are presented to illustrate the PCM generation method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。