Don’t hide in the frames: Note- and pattern-based evaluation of automated melody extraction algorithms

Don’t hide in the frames: Note- and pattern-based evaluation of automated melody extraction algorithms
复制标题

不要隐藏在框架中:基于音符和模式的自动旋律提取算法评估

DOI:
10.1145/3358664.3358672
复制
发表时间:
2019
期刊:
Proceedings of the 6th International Conference on Digital Libraries for Musicology
影响因子:
--
通讯作者:
G. Peeters
G. Peeters
中科院分区:
--
文献类型:
--
作者:
K. Frieler;D. Başaran;F. Höger;H.-C. Crayencour;G. Peeters

文献摘要

参考文献

被引文献

相似文献

在本文中,我们将讨论如何评估和提高性能的自动主旋律提取系统从模式挖掘的角度,重点是爵士乐即兴。传统上,主旋律提取系统估计的旋律上的帧级,但对于现实世界的音乐学应用的音符级表示是必要的。对于估计的音符音轨的评估,当前逐帧度量不完全合适,并且至多提供第一近似。此外,挖掘旋律模式(n-gram)构成了另一个挑战,因为音符错误随着模式长度的增加而几何传播。另一方面,对于某些衍生指标,如表演者之间的模式共性,提取错误可能不那么重要,如果至少可以复制定性排名。最后,当在旋律数据库中搜索相似模式时,结果集中不相关模式的数量随着相似性阈值的降低而增加。出于可用性的原因,了解使用不完美的自动旋律提取的行为将是有趣的。我们提出了三种新的评估策略,估计注意到轨道的基础上三个应用场景:模式挖掘,模式共性,模糊模式搜索。我们提出的指标,一个一般的国家的最先进的旋律估计方法(旋律)和两个变种的算法,优化提取爵士乐独奏旋律。魏玛爵士乐数据库的一个子集,91独奏用于评价。结果表明,优化后的算法明显优于参考算法,后者会迅速退化并最终分解为更长的n-grams。逐帧度量确实提供了对逐音符度量的估计,但仅用于足够好的提取,而更长的n元语法的F1分数根本不能从逐帧F1分数预测。表演者之间的模式共性的排名可以用优化算法再现,但不能用参考算法再现。最后,模式相似性搜索的结果集的大小对于自动注释提取和对于较大的相似性阈值减小,但是对于较小的阈值差异变平。
In this paper, we address how to evaluate and improve the performance of automatic dominant melody extraction systems from a pattern mining perspective with a focus on jazz improvisations. Traditionally, dominant melody extraction systems estimate the melody on the frame-level, but for real-world musicological applications note-level representations are needed. For the evaluation of estimated note tracks, the current frame-wise metrics are not fully suitable and provide at most a first approximation. Furthermore, mining melodic patterns (n-grams) poses another challenge because note-wise errors propagate geometrically with increasing length of the pattern. On the other hand, for certain derived metrics such as pattern commonalities between performers, extraction errors might be less critical if at least qualitative rankings can be reproduced. Finally, while searching for similar patterns in a melody database the number of irrelevant patterns in the result set increases with lower similarity thresholds. For reasons of usability, it would be interesting to know the behavior using imperfect automated melody extractions. We propose three novel evaluation strategies for estimated note-tracks based on three application scenarios: Pattern mining, pattern commonalities, and fuzzy pattern search. We apply the proposed metrics to one general state-of-the-art melody estimation method (Melodia) and to two variants of an algorithm that was optimized for the extraction of jazz solos melodies. A subset of the Weimar Jazz Database with 91 solos was used for evaluation. Results show that the optimized algorithm clearly outperforms the reference algorithm, which quickly degrades and eventually breaks down for longer n-grams. Frame-wise metrics provide indeed an estimate for note-wise metrics, but only for sufficiently good extractions, whereas F1 scores for longer n-grams cannot be predicted from frame-wise F1 scores at all. The ranking of pattern commonalities between performers can be reproduced with the optimized algorithms but not with the reference algorithm. Finally, the size of result sets of pattern similarity searches decreases for automated note extraction and for larger similarity thresholds but the difference levels out for smaller thresholds.
DOI: 10.1177/1029864912448329
发表时间: 2012
期刊: Musicae Scientiae
影响因子: 2.4
作者:
A. Volk;Peter van Kranenburg
通讯作者: Peter van Kranenburg
查理·帕克:即兴创作技巧
DOI: --
发表时间: 1974
期刊:
影响因子: --
作者:
Thomas Owens
通讯作者: Thomas Owens
查理·帕克
DOI: --
发表时间: 2020
期刊: B Jenkins
影响因子: --
作者:
Carl Woideck
通讯作者: Carl Woideck
用于探索爵士乐独奏旋律模式的两个 Web 应用程序
DOI: --
发表时间: 2018
期刊: --
影响因子: --
作者:
K. Frieler
通讯作者: K. Frieler
DOI: --
发表时间: 2014
期刊: --
影响因子: --
作者:
Colin Raffel;Brian McFee;Eric J. Humphrey;J. Salamon;Oriol Nieto;Dawen Liang;D. Ellis
通讯作者: Colin Raffel;Brian McFee;Eric J. Humphrey;J. Salamon;Oriol Nieto;Dawen Liang;D. Ellis