Towards Quantitative Measures of Evaluating Song Segmentation
Towards Quantitative Measures of Evaluating Song Segmentation
复制标题
寻求评估歌曲分割的定量方法
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
Hanna M. Lukashevich
中科院分区：
文献类型：
--
作者：
Hanna M. Lukashevich
自动音乐结构分析或歌曲分割在音乐信息检索领域有着直接的应用。这些应用程序是积极的音乐导航，自动生成音频摘要，自动音乐分析等歌曲分割任务的重要方面之一是它的评价。通常，这意味着将自动估计的分割与由人类专家注释的地面实况进行比较。分割算法的自动评估提供了反映估计的分割与注释的地面实况匹配程度的定量度量。本文提出了一种基于信息论条件熵的评价方法。所提出的方法的主要优点在于应用规范化，这使得自动评估结果的比较，获得不同数量的状态的歌曲。讨论并比较了目前常用的歌曲切分评价分数。我们提供了几个例子，说明不同的评估措施的行为，并权衡所提出的度量对其他人的好处。
Automatic music structure analysis or song segmentation has immediate applications in the field of music information retrieval. Among these applications is active music navigation, automatic generation of audio summaries, automatic music analysis, etc. One of the important aspects of a song segmentation task is its evaluation. Commonly, that implies comparing the automatically estimated segmentation with a ground-truth, annotated by human experts. The automatic evaluation of segmentation algorithms provides the quantitative measure that reflects how well the estimated segmentation matches the annotated ground-truth. In this paper we present a novel evaluation measure based on informationtheoretic conditional entropy. The principal advantage of the proposed approach lies in the applied normalization, which enables the comparison of the automatic evaluation results, obtained for songs with a different amount of states. We discuss and compare the evaluation scores commonly used for evaluating song segmentation at present. We provide several examples illustrating the behavior of different evaluation measures and weigh the benefits of the presented metric against the others.