arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.03689cs.SDcs.AIeess.AS
收藏

MAJL:一种用于音乐源分离与音高估计的模型无关联合学习框架

MAJL: A Model-Agnostic Joint Learning Framework for Music Source Separation and Pitch Estimation

School of Information(信息学院);Renmin University of China(中国人民大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);School of Computer Science and Technology(计算机科学与技术学院);Huazhong University of Science and Technology(华中科技大学)

Haojie Wei, Jun Yuan, Rui Zhang, Quanyu Dai, Yueguo Chen

AI总结:

提出模型无关联合学习框架MAJL,通过两阶段训练与DWHS动态加权缓解标注数据不足及联合优化难题,在音乐源分离和音高估计上均显著超越现有方法。

摘要:

音乐源分离和音高估计是音乐信息检索中的两项重要任务。通常,音高估计的输入来自音乐源分离的输出。因此,现有方法尝试同时执行这两项任务,以利用二者之间互利的关系。然而,这些方法仍面临两个限制两项任务性能提升的关键挑战:标注数据不足和联合学习优化问题。为应对这些挑战,我们提出了一种适用于两项任务的模型无关联合学习(Model-Agnostic Joint Learning,MAJL)框架。MAJL是一个通用框架,可为每项任务使用不同模型。它包含两阶段训练方法和名为困难样本动态权重(Dynamic Weights on Hard Samples,DWHS)的动态加权方法,分别解决标注数据不足和联合学习优化问题。在公开音乐数据集上的实验结果表明,MAJL在两项任务上均优于最先进方法,音乐源分离的信号失真比(Signal-to-Distortion Ratio,SDR)显著提升0.92,音高估计的原始音高准确率(Raw Pitch Accuracy,RPA)显著提升2.71%。此外,综合研究不仅验证了MAJL各组件的有效性,还表明MAJL在适配不同模型架构方面具有很强的通用性。

英文摘要:

Music source separation and pitch estimation are two vital tasks in music information retrieval. Typically, the input of pitch estimation is obtained from the output of music source separation. Therefore, existing methods have tried to perform these two tasks simultaneously, so as to leverage the mutually beneficial relationship between both tasks. However, these methods still face two critical challenges that limit the improvement of both tasks: the lack of labeled data and joint learning optimization. To address these challenges, we propose a Model-Agnostic Joint Learning (MAJL) framework for both tasks. MAJL is a generic framework and can use variant models for each task. It includes a two-stage training method and a dynamic weighting method named Dynamic Weights on Hard Samples (DWHS), which addresses the lack of labeled data and joint learning optimization, respectively. Experimental results on public music datasets show that MAJL outperforms state-of-the-art methods on both tasks, with significant improvements of 0.92 in Signal-to-Distortion Ratio (SDR) for music source separation and 2.71% in Raw Pitch Accuracy (RPA) for pitch estimation. Furthermore, comprehensive studies not only validate the effectiveness of each component of MAJL, but also indicate the great generality of MAJL in adapting to different model architectures.

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。

↑