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 2310.01353eess.AScs.SD
收藏

利用半监督学习扩大音乐信息检索训练规模

Scaling Up Music Information Retrieval Training with Semi-Supervised Learning

ByteDance(字节跳动)

Yun-Ning Hung, Ju-Chiang Wang, Minz Won, Duc Le

AI总结:

针对音乐信息检索标注数据稀缺问题,提出采用半监督师生训练方法,通过扩大无标注数据规模、迭代优化伪标签及扩展模型规模,在多项MIR任务上取得了当前最优结果。

摘要:

在数据驱动的音乐信息检索(MIR)时代,标注数据稀缺一直是制约MIR任务成功的主要问题之一。本研究采用半监督师生训练方法来提升MIR任务性能。训练阶段,我们将无标注音乐数据规模扩大至24万小时,远超所有公开MIR数据集。我们在含噪的师生训练过程中迭代生成并优化伪标签,同时探索知识扩展技术,将模型参数量从不足3M迭代扩大至近100M。实验中我们研究了数据规模与模型规模之间的性能关联。通过同时扩大模型规模和训练数据量,与采用监督训练或基于自监督预训练模型的方法相比,我们的模型在多项MIR任务上取得了当前最优(SOTA)结果。据我们所知,这是首次针对多种MIR任务研究同时扩大模型与训练数据规模效果的尝试。

英文摘要:

In the era of data-driven Music Information Retrieval (MIR), the scarcity of labeled data has been one of the major concerns to the success of an MIR task. In this work, we leverage the semi-supervised teacher-student training approach to improve MIR tasks. For training, we scale up the unlabeled music data to 240k hours, which is much larger than any public MIR datasets. We iteratively create and refine the pseudo-labels in the noisy teacher-student training process. Knowledge expansion is also explored to iteratively scale up the model sizes from as small as less than 3M to almost 100M parameters. We study the performance correlation between data size and model size in the experiments. By scaling up both model size and training data, our models achieve state-of-the-art results on several MIR tasks compared to models that are either trained in a supervised manner or based on a self-supervised pretrained model. To our knowledge, this is the first attempt to study the effects of scaling up both model and training data for a variety of MIR 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。

↑