arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.06148eess.AScs.LGcs.SDeess.SP
收藏

一种通用的深度学习方法来建模时变音频效果

A general-purpose deep learning approach to model time-varying audio effects

Queen Mary University of London(伦敦玛丽女王大学)

Marco A. Martínez Ramírez, Emmanouil Benetos, Joshua D. Reiss

摘要:

其参数随时间周期性地修改的音频处理器通常被称为时变或基于调制的音频效果。大多数现有的建模方法,这些类型的效果单位往往是一个非常具体的电路优化,不能有效地推广到其他随时间变化的影响。基于卷积和递归神经网络,我们提出了一种深度学习架构,用于具有长期记忆的音频处理器的通用黑盒建模。我们探索了深度神经网络学习这种长时间依赖性的能力,并展示了网络对各种线性和非线性、时变和时不变音频效果的建模。为了衡量该模型的性能,我们提出了一个客观的度量调制频率感知的心理声学的基础上。我们还分析了模型实际上在学习什么,以及给定的任务是如何完成的。

英文摘要:

Audio processors whose parameters are modified periodically over time are often referred as time-varying or modulation based audio effects. Most existing methods for modeling these type of effect units are often optimized to a very specific circuit and cannot be efficiently generalized to other time-varying effects. Based on convolutional and recurrent neural networks, we propose a deep learning architecture for generic black-box modeling of audio processors with long-term memory. We explore the capabilities of deep neural networks to learn such long temporal dependencies and we show the network modeling various linear and nonlinear, time-varying and time-invariant audio effects. In order to measure the performance of the model, we propose an objective metric based on the psychoacoustics of modulation frequency perception. We also analyze what the model is actually learning and how the given task is accomplished.

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。

↑