arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.09060cs.SDcs.CVcs.IRcs.LGeess.AS
收藏

上下文感知音高韵律表征的自监督学习

Self-Supervised Learning of Context-Aware Pitch Prosody Representations

Stanford University(斯坦福大学)

Camille Noufi, Prateek Verma

摘要:

在音乐和演讲中,意义是在多层次的语境中产生的。例如,情感可以通过短的声音标记和较长时间窗口(如整个录音)上的声音模式来推断。在这封信中,我们专注于从这种语境的二分法中推断意义。我们展示了如何短唱声乐行的上下文表示可以隐式地从基频($F_0$)学习,从而被用作下游音乐信息检索(MIR)任务的一个有意义的特征空间。我们提出了三种自我监督的深度学习范式,它们利用这两个层次的上下文的伪任务学习来产生潜在的表示空间。我们通过将看不见的音高轮廓嵌入到每个空间中并进行下游分类任务来评估这些表示的有用性。我们的研究结果表明,上下文表示可以提高下游分类多达15%相比,使用传统的统计轮廓特征。

英文摘要:

In music and speech, meaning is derived at multiple levels of context. Affect, for example, can be inferred both by a short sound token and by sonic patterns over a longer temporal window such as an entire recording. In this letter, we focus on inferring meaning from this dichotomy of contexts. We show how contextual representations of short sung vocal lines can be implicitly learned from fundamental frequency ($F_0$) and thus be used as a meaningful feature space for downstream Music Information Retrieval (MIR) tasks. We propose three self-supervised deep learning paradigms which leverage pseudotask learning of these two levels of context to produce latent representation spaces. We evaluate the usefulness of these representations by embedding unseen pitch contours into each space and conducting downstream classification tasks. Our results show that contextual representation can enhance downstream classification by as much as 15\% as compared to using traditional statistical contour features.

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。

↑