旋律序列的概率模型比较
Comparing Probabilistic Models for Melodic Sequences
摘要：
对音乐的真实世界复杂性进行建模是机器学习的一个挑战。我们解决的任务，从同一音乐流派的旋律序列建模。我们进行了比较分析的两个概率模型;狄利克雷变长马尔可夫模型（狄利克雷-VMM）和时间卷积限制玻尔兹曼机（TC-RBM）。我们表明，TC-RBM学习描述性的音乐功能，如基本的和弦和典型的旋律过渡和动态。我们评估未来的预测模型，并将其性能与VMM进行比较，VMM是旋律生成的最新技术。我们发现，这两种模型的性能显着优于VMM，与狄利克雷-VMM略优于TC-RBM。最后，我们评估了模型的短顺序统计量，使用测试序列和模型样本之间的库尔贝克-莱布勒散度，并表明我们提出的方法与音乐流派的统计量的匹配明显优于VMM。
英文摘要：
Modelling the real world complexity of music is a challenge for machine learning. We address the task of modeling melodic sequences from the same music genre. We perform a comparative analysis of two probabilistic models; a Dirichlet Variable Length Markov Model (Dirichlet-VMM) and a Time Convolutional Restricted Boltzmann Machine (TC-RBM). We show that the TC-RBM learns descriptive music features, such as underlying chords and typical melody transitions and dynamics. We assess the models for future prediction and compare their performance to a VMM, which is the current state of the art in melody generation. We show that both models perform significantly better than the VMM, with the Dirichlet-VMM marginally outperforming the TC-RBM. Finally, we evaluate the short order statistics of the models, using the Kullback-Leibler divergence between test sequences and model samples, and show that our proposed methods match the statistics of the music genre significantly better than the VMM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
