arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2201.00052cs.SDcs.LGeess.AS
收藏

使用数据增强评估深度音乐生成方法

Evaluating Deep Music Generation Methods Using Data Augmentation

Imperial College London(帝国理工学院);University of Augsburg(奥格斯堡大学)

Toby Godwin, Georgios Rizos, Alice Baird, Najla D. Al Futaisi, Vincent Brisse, Bjoern W. Schuller

摘要:

尽管在深度算法音乐生成方面取得了进展,但对所生成样本的评估通常依赖于主观且成本高昂的人工评估。我们专注于设计一个同质的,客观的框架来评估算法生成的音乐样本。任何评估生成音乐的工程测量通常试图定义样本的音乐性,但不捕获音乐的质量,如主题或情绪。我们不寻求评估生成的音乐的音乐价值,而是探索生成的样本是否包含有关情感或情绪/主题的有意义的信息。我们实现这一点,通过测量的音乐情绪/主题分类器的预测性能的变化后,增加其训练数据与生成的样本。我们分析了由三种模型生成的音乐样本-- SampleRNN、Juventure和DDSP --并在所有方法中采用了一个同质框架,以便进行客观比较。这是第一次尝试用有条件生成的音乐来增强音乐流派分类数据集。我们研究了使用深度音乐生成的分类性能改进,以及生成器通过使用数据集的附加情感注释来制作情感音乐的能力。最后,我们使用一个在真实数据上训练的分类器来评估类条件生成样本的标签有效性。

英文摘要:

Despite advances in deep algorithmic music generation, evaluation of generated samples often relies on human evaluation, which is subjective and costly. We focus on designing a homogeneous, objective framework for evaluating samples of algorithmically generated music. Any engineered measures to evaluate generated music typically attempt to define the samples' musicality, but do not capture qualities of music such as theme or mood. We do not seek to assess the musical merit of generated music, but instead explore whether generated samples contain meaningful information pertaining to emotion or mood/theme. We achieve this by measuring the change in predictive performance of a music mood/theme classifier after augmenting its training data with generated samples. We analyse music samples generated by three models -- SampleRNN, Jukebox, and DDSP -- and employ a homogeneous framework across all methods to allow for objective comparison. This is the first attempt at augmenting a music genre classification dataset with conditionally generated music. We investigate the classification performance improvement using deep music generation and the ability of the generators to make emotional music by using an additional, emotion annotation of the dataset. Finally, we use a classifier trained on real data to evaluate the label validity of class-conditionally generated samples.

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。

↑