arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.12615cs.CL
收藏

一个通用的Rap歌词韵律增强表示学习框架

A General Framework for Learning Prosodic-Enhanced Representation of Rap Lyrics

College of Computer Science, Nankai University(南开大学计算机学院);College of Mathematics and Statistics Science, Ludong University(鲁东大学数学与统计科学学院);Advanced Analytics Institute, University of Technology Sydney(悉尼科技大学高级分析学院)

Hongru Liang, Haozheng Wang, Qian Li, Jun Wang, Guandong Xu, Jiawei Chen, Jin-Mao Wei, Zhenglu Yang

摘要:

由于万维网上有着丰富的数字音乐资源,因此对说唱歌词的学习和分析是音乐推荐、自动音乐分类、音乐信息检索等Web应用的重要基础。虽然许多研究已经探讨了这一主题,在这一领域的知识是远远不能令人满意的,因为关键的问题,如韵律信息及其有效的表示,以及适当的整合各种功能,通常被忽视。在本文中,我们提出了一个分层注意变分自编码器框架(HAVAE),它同时考虑说唱歌词表示学习的语义和韵律特征。具体地说,韵律特征的表示采用了一种新颖而有效的策略- rhyme2vec)。此外,提出了一种特征聚合策略,以适当地整合各种特征,并产生韵律增强表示。全面的实证评估表明,在不同的说唱歌词学习任务中,所提出的框架在各种指标下的表现优于最先进的方法。

英文摘要:

Learning and analyzing rap lyrics is a significant basis for many web applications, such as music recommendation, automatic music categorization, and music information retrieval, due to the abundant source of digital music in the World Wide Web. Although numerous studies have explored the topic, knowledge in this field is far from satisfactory, because critical issues, such as prosodic information and its effective representation, as well as appropriate integration of various features, are usually ignored. In this paper, we propose a hierarchical attention variational autoencoder framework (HAVAE), which simultaneously consider semantic and prosodic features for rap lyrics representation learning. Specifically, the representation of the prosodic features is encoded by phonetic transcriptions with a novel and effective strategy~(i.e., rhyme2vec). Moreover, a feature aggregation strategy is proposed to appropriately integrate various features and generate prosodic-enhanced representation. A comprehensive empirical evaluation demonstrates that the proposed framework outperforms the state-of-the-art approaches under various metrics in different rap lyrics learning 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。

↑