We introduce Self-Monitored Inference-Time INtervention (SMITIN), an approach for controlling an autoregressive generative music transformer using classifier probes. These simple logistic regression probes are trained on the output of each attention head in the transformer using a small dataset of audio examples both exhibiting and missing a specific musical trait (e.g., the presence/absence of drums, or real/synthetic music). We then steer the attention heads in the probe direction, ensuring the generative model output captures the desired musical trait. Additionally, we monitor the probe output to avoid adding an excessive amount of intervention into the autoregressive generation, which could lead to temporally incoherent music. We validate our results objectively and subjectively for both audio continuation and text-to-music applications, demonstrating the ability to add controls to large generative models for which retraining or even fine-tuning is impractical for most musicians. Audio samples of the proposed intervention approach are available on our demo page http://tinyurl.com/smitin .

翻译：我们提出自我监测推理时干预（Self-Monitored Inference-Time INtervention, SMITIN），一种通过分类器探针对自回归生成式音乐Transformer进行控制的方法。这些简化的逻辑回归探针利用包含特定音乐特征（例如鼓声存在/缺失、真实/合成音乐）及不含该特征的小型音频样本集，在Transformer每个注意力头的输出上进行训练。随后我们沿探针方向引导注意力头，确保生成模型输出具备目标音乐特征。同时，我们通过监测探针输出来避免在自回归生成过程中施加过度干预，以免产生时序不连贯的音乐。针对音频延续及文本生成音乐两种应用场景，我们进行了客观与主观验证，结果表明该方法能够为大型生成模型添加控制能力，而最广大音乐从业者通常难以对这些模型进行重训练甚至微调。所提干预方法的音频样本可在演示页面http://tinyurl.com/smitin 获取。