论文标题
通过神经分发学习对音乐的发作概率进行建模
Modeling Musical Onset Probabilities via Neural Distribution Learning
论文作者
论文摘要
音乐发作检测可以通过将音乐定义为一系列发作事件来表达为事件时间（TTE）或时间 - 事件（TSE）预测任务。在这里，我们提出了一种新颖的方法，通过引入顺序密度预测模型来模拟Onset的概率。提出的模型使用卷积神经网络（CNN）作为密度预测指标估算MEL光谱图的TTE和TSE分布。我们在Bock数据集显示与以前的深度学习模型相当的结果上评估了我们的模型。
Musical onset detection can be formulated as a time-to-event (TTE) or time-since-event (TSE) prediction task by defining music as a sequence of onset events. Here we propose a novel method to model the probability of onsets by introducing a sequential density prediction model. The proposed model estimates TTE & TSE distributions from mel-spectrograms using convolutional neural networks (CNNs) as a density predictor. We evaluate our model on the Bock dataset show-ing comparable results to previous deep-learning models.
