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 2402.07599eess.AScs.SD
收藏

基于主动适应的交互式歌唱旋律提取

Interactive singing melody extraction based on active adaptation

Indian Institute of Technology Kanpur(印度理工学院坎普尔分校)

Kavya Ranjan Saxena, Vipul Arora

AI总结:

提出基于主动适应的交互式歌唱旋律提取方法,利用归一化真实类别概率置信度准则选择需人工标注的区域,并通过处理类别不平衡的元学习使模型适应目标域,同时发布了HAR数据集。

摘要:

从复调音频中提取主旋律是音乐信息检索和计算音乐学领域的基本任务之一。为了使用机器学习完成这一任务,需要大量带标注的音频数据来训练模型。然而,在一个领域(源域)数据上预训练的经典模型,例如特定歌手或流派的歌曲,在从其他领域(目标域)提取旋律时可能表现不佳。通过使用目标域中少量带标注数据来适应模型,可以提升此类模型的性能。在本工作中,我们提出了一种高效的交互式旋律适应方法。我们的方法使用基于归一化真实类别概率的置信度准则,选择目标音频中需要人工标注的区域。模型利用这些标注,通过元学习将自身适应到目标域。我们的方法还提供了一种新颖的元学习方法,用于处理类别不平衡问题,即在目标域中只有少数类别的少量代表性样本可用于适应。实验结果表明,所提出的方法优于其他自适应旋律提取基线。所提出的方法是模型无关的,因此可以应用于其他非自适应旋律提取模型以提升其性能。此外,我们发布了一个包含523个音频文件、时长约6.86小时的Hindustani Alankaar and Raga (HAR)数据集,用于歌唱旋律提取任务。

英文摘要:

Extraction of predominant pitch from polyphonic audio is one of the fundamental tasks in the field of music information retrieval and computational musicology. To accomplish this task using machine learning, a large amount of labeled audio data is required to train the model. However, a classical model pre-trained on data from one domain (source), e.g., songs of a particular singer or genre, may not perform comparatively well in extracting melody from other domains (target). The performance of such models can be boosted by adapting the model using very little annotated data from the target domain. In this work, we propose an efficient interactive melody adaptation method. Our method selects the regions in the target audio that require human annotation using a confidence criterion based on normalized true class probability. The annotations are used by the model to adapt itself to the target domain using meta-learning. Our method also provides a novel meta-learning approach that handles class imbalance, i.e., a few representative samples from a few classes are available for adaptation in the target domain. Experimental results show that the proposed method outperforms other adaptive melody extraction baselines. The proposed method is model-agnostic and hence can be applied to other non-adaptive melody extraction models to boost their performance. Also, we released a Hindustani Alankaar and Raga (HAR) dataset containing 523 audio files of about 6.86 hours of duration intended for singing melody extraction tasks.

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。

↑