We introduce Cadenza, a new multi-stage generative framework for predicting expressive variations of symbolic musical ideas as well as unconditional generations. To accomplish this we propose a novel MIDI encoding method, PerTok (Performance Tokenizer) that captures minute expressive details whilst reducing sequence length up to 59% and vocabulary size up to 95% for polyphonic, monophonic and rhythmic tasks. The proposed framework comprises of two sequential stages: 1) Composer and 2) Performer. The Composer model is a transformer-based Variational Autoencoder (VAE), with Rotary Positional Embeddings (RoPE)ROPE and an autoregressive decoder modified to more effectively integrate the latent codes of the input musical idea. The Performer model is a bidirectional transformer encoder that is separately trained to predict velocities and microtimings on MIDI sequences. Objective and human evaluations demonstrate Cadenza's versatile capability in 1) matching other unconditional state-of-the-art symbolic models in musical quality whilst sounding more expressive, and 2) composing new, expressive ideas that are both stylistically related to the input whilst providing novel ideas to the user. Our framework is designed, researched and implemented with the objective of ethically providing inspiration for musicians.

翻译：我们提出了Cadenza，一种新的多阶段生成框架，用于预测符号音乐创意的表达性变奏以及无条件生成。为实现这一目标，我们提出了一种新颖的MIDI编码方法——PerTok（性能分词器），它能够捕捉细微的表达细节，同时将复调、单音和节奏任务的序列长度减少高达59%，词汇量减少高达95%。所提出的框架包含两个顺序阶段：1）作曲器 和 2）演奏器。作曲器模型是一个基于Transformer的变分自编码器（VAE），采用旋转位置嵌入（RoPE），并修改了自回归解码器以更有效地整合输入音乐创意的潜在编码。演奏器模型是一个双向Transformer编码器，经过单独训练以预测MIDI序列的力度和微时序。客观评估和人工评估均表明，Cadenza在以下两方面展现出卓越能力：1）在音乐质量上匹配其他最先进的无条件符号模型，同时听起来更具表现力；2）创作新颖的表达性创意，这些创意既在风格上与输入相关，又为用户提供了新的想法。我们的框架在设计、研究和实施时，均以合乎伦理的方式为音乐家提供灵感为目标。