arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.07968cs.SDcs.LGeess.AS
收藏

音乐声源分离的损失函数与评价指标

On loss functions and evaluation metrics for music source separation

Universitat Pompeu Fabra(庞培法布拉大学);Dolby Laboratories(杜比实验室)

Enric Gusó, Jordi Pons, Santiago Pascual, Joan Serrà

摘要:

我们调查损失函数提供更好的分离,通过基准测试的音乐声源分离的广泛的一套。为此,我们首先调查了我们确定的最具代表性的音频声源分离损失,然后在受控的实验设置中对其进行一致的基准测试。我们还探索使用这样的损失作为评估指标,通过交叉相关的主观测试的结果。根据观察,标准的信号失真比度量可能会误导在某些情况下,我们研究替代评估指标的基础上考虑的损失。

英文摘要:

We investigate which loss functions provide better separations via benchmarking an extensive set of those for music source separation. To that end, we first survey the most representative audio source separation losses we identified, to later consistently benchmark them in a controlled experimental setup. We also explore using such losses as evaluation metrics, via cross-correlating them with the results of a subjective test. Based on the observation that the standard signal-to-distortion ratio metric can be misleading in some scenarios, we study alternative evaluation metrics based on the considered losses.

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。

↑