论文标题
使用集合时间预测错误的无监督符号音乐细分
Unsupervised Symbolic Music Segmentation using Ensemble Temporal Prediction Errors
论文作者
论文摘要
符号音乐分割是将符号旋律分为较小有意义的群体（例如旋律短语）的过程。我们提出了一种无监督的方法，用于分割符号音乐。提出的模型基于时间预测误差模型的集合。在训练过程中，每个模型都预测了下一个令牌，以识别音乐短语变化。在测试时，我们执行峰值检测算法以选择候选段。最后，我们汇总了参与集合的每个模型以预测最终分割的预测。结果表明，在考虑F得分和R值时，该方法在无监督的设置下达到了Essen Folksong数据集的最新性能。我们还提供一项消融研究，以更好地评估每个模型组件对最终结果的贡献。正如预期的那样，所提出的方法不如监督环境，这在未来的研究中留出了改善的空间，考虑到缩小无监督和监督方法之间的差距。
Symbolic music segmentation is the process of dividing symbolic melodies into smaller meaningful groups, such as melodic phrases. We proposed an unsupervised method for segmenting symbolic music. The proposed model is based on an ensemble of temporal prediction error models. During training, each model predicts the next token to identify musical phrase changes. While at test time, we perform a peak detection algorithm to select segment candidates. Finally, we aggregate the predictions of each of the models participating in the ensemble to predict the final segmentation. Results suggest the proposed method reaches state-of-the-art performance on the Essen Folksong dataset under the unsupervised setting when considering F-Score and R-value. We additionally provide an ablation study to better assess the contribution of each of the model components to the final results. As expected, the proposed method is inferior to the supervised setting, which leaves room for improvement in future research considering closing the gap between unsupervised and supervised methods.
