arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.03229cs.SDcs.LGeess.AS
收藏

多任务自监督预训练的音乐分类

Multi-Task Self-Supervised Pre-Training for Music Classification

Amazon(亚马逊)

Ho-Hsiang Wu, Chieh-Chi Kao, Qingming Tang, Ming Sun, Brian McFee, Juan Pablo Bello, Chao Wang

摘要:

深度学习非常需要数据,而监督学习尤其需要大量的标记数据才能很好地工作。机器听力研究通常会遇到有限的标记数据问题,因为人类注释的获取成本很高,而音频注释既耗时又不直观。此外,从标记数据集学习的模型通常会嵌入特定于该特定数据集的偏见。因此,无监督学习技术成为解决机器听力问题的热门方法。特别地,利用多个手工制作的音频特征的重建的自监督学习技术在应用于语音领域(诸如情感识别和自动语音识别(ASR))时已经显示出有希望的结果。在本文中,我们将自我监督和多任务学习方法应用于预训练音乐编码器,并探索各种设计选择,包括编码器架构,加权机制,以结合多个任务的损失,以及工作人员对借口任务的选择。我们研究这些设计选择如何与各种下游音乐分类任务相互作用。我们发现,使用各种音乐特定的工人与加权机制,以平衡损失在预训练有助于改善和推广到下游的任务。

英文摘要:

Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well. Machine listening research often suffers from limited labeled data problem, as human annotations are costly to acquire, and annotations for audio are time consuming and less intuitive. Besides, models learned from labeled dataset often embed biases specific to that particular dataset. Therefore, unsupervised learning techniques become popular approaches in solving machine listening problems. Particularly, a self-supervised learning technique utilizing reconstructions of multiple hand-crafted audio features has shown promising results when it is applied to speech domain such as emotion recognition and automatic speech recognition (ASR). In this paper, we apply self-supervised and multi-task learning methods for pre-training music encoders, and explore various design choices including encoder architectures, weighting mechanisms to combine losses from multiple tasks, and worker selections of pretext tasks. We investigate how these design choices interact with various downstream music classification tasks. We find that using various music specific workers altogether with weighting mechanisms to balance the losses during pre-training helps improve and generalize to the downstream 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。

↑