arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.09025cs.SDcs.LGeess.AS
收藏

CoverHunter:基于精细化注意力与对齐的翻唱歌曲识别

CoverHunter: Cover Song Identification with Refined Attention and Alignments

Huya Inc(虎牙公司)

Feng Liu, Deyi Tuo, Yinan Xu, Xintong Han

AI总结:

本研究提出翻唱歌曲识别系统CoverHunter,通过Conformer结构、时间注意力池化与由粗到精训练策略提升特征表达,在标准数据集上取得了优于现有最优方法的性能。

摘要:

翻唱歌曲识别(CSI)旨在针对给定的查询曲目,在参考锚点库中找出同一音乐的不同版本。本文提出了一种名为CoverHunter的新型系统,通过借助精细化注意力与对齐机制挖掘更丰富的特征,弥补了现有检测方案的不足。CoverHunter包含三个核心模块:1)卷积增强Transformer(即Conformer)结构,可同时捕捉局部与全局特征交互,区别于以往主要依赖卷积神经网络的方法;2)基于注意力的时间池化模块,进一步在时间维度上利用注意力机制;3)一种新型的由粗到精训练策略,先训练网络实现歌曲片段的粗略对齐,再通过在对齐后的片段上训练来优化网络。同时,我们还总结了系统中用到的若干有助于提升效果的重要训练技巧。在多个标准CSI数据集上的实验表明,在嵌入维度为128的设置下,我们的方法较现有最优方法实现了显著提升(在SHS100K-TEST上提升2.3%,在DaTacos上提升17.7%)。

英文摘要:

Abstract: Cover song identification (CSI) focuses on finding the same music with different versions in reference anchors given a query track. In this paper, we propose a novel system named CoverHunter that overcomes the shortcomings of existing detection schemes by exploring richer features with refined attention and alignments. CoverHunter contains three key modules: 1) A convolution-augmented transformer (i.e., Conformer) structure that captures both local and global feature interactions in contrast to previous methods mainly relying on convolutional neural networks; 2) An attention-based time pooling module that further exploits the attention in the time dimension; 3) A novel coarse-to-fine training scheme that first trains a network to roughly align the song chunks and then refines the network by training on the aligned chunks. At the same time, we also summarize some important training tricks used in our system that help achieve better results. Experiments on several standard CSI datasets show that our method significantly improves over state-of-the-art methods with an embedding size of 128 (2.3% on SHS100K-TEST and 17.7% on DaTacos).

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。

↑