This paper presents a new approach for controlling emotion in symbolic music generation with Monte Carlo Tree Search. We use Monte Carlo Tree Search as a decoding mechanism to steer the probability distribution learned by a language model towards a given emotion. At every step of the decoding process, we use Predictor Upper Confidence for Trees (PUCT) to search for sequences that maximize the average values of emotion and quality as given by an emotion classifier and a discriminator, respectively. We use a language model as PUCT's policy and a combination of the emotion classifier and the discriminator as its value function. To decode the next token in a piece of music, we sample from the distribution of node visits created during the search. We evaluate the quality of the generated samples with respect to human-composed pieces using a set of objective metrics computed directly from the generated samples. We also perform a user study to evaluate how human subjects perceive the generated samples' quality and emotion. We compare PUCT against Stochastic Bi-Objective Beam Search (SBBS) and Conditional Sampling (CS). Results suggest that PUCT outperforms SBBS and CS in almost all metrics of music quality and emotion.
翻译:本文展示了一种用蒙特卡洛树搜索来控制象征性音乐生成中情感的新方法。 我们使用蒙特卡洛树搜索作为一种解码机制来引导语言模型所学的概率分布到特定情感。 在解码过程的每一步, 我们使用“ 树的预言者最高信任度” 来寻找能够使情感和质量平均值最大化的序列, 正如情感分类器和歧视器分别给出的那样。 我们用一种语言模型来作为 PUCT 的政策, 以及情感分类器与歧视器的组合作为它的值函数。 为了解码下一个符号, 我们从搜索过程中创建的节点访问的分布中取样。 我们使用直接从生成样本中计算出来的一套客观指标来评估所生成的人类拼图的质量。 我们还进行一项用户研究, 评估人类主体如何看待所生成样品的质量和情感。 我们比较了PUCT与Stocistic Biutive Beam搜索(SBBBSBS) 和 Conditional Samling (CS) 。 结果表明, PUCTTSBS 和MIS 几乎超越了SBBS和MIBS 和Ms 。