arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.04079cs.SDcs.LGeess.AS
收藏

基于冲激不变卷积层的采样频率无关音频声源分离

Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method

The University of Tokyo(东京大学);Waseda University(早稻田大学);NTT Corporation(日本电信电话株式会社)

Koichi Saito, Tomohiko Nakamura, Kohei Yatabe, Yuma Koizumi, Hiroshi Saruwatari

摘要:

音频声源分离常被用作各种应用的预处理,其最终目标之一是构造一个能够处理多种音频信号的通用模型。由于作为音频信号种类之一的采样频率通常是特定于应用的,因此前面的音频声源分离模型应该能够处理目标应用中指定的所有采样频率的音频信号。然而,基于深度神经网络(DNN)的传统模型仅以训练数据指定的采样频率进行训练,并且不能保证它们以不可见的采样频率工作。在本文中,我们提出了一个能够通过单个DNN处理任意采样频率的卷积层。通过音乐声源分离实验,我们表明,所提出的层的引入,使传统的音频声源分离模型,即使是看不见的采样频率一致的工作。

英文摘要:

Audio source separation is often used as preprocessing of various applications, and one of its ultimate goals is to construct a single versatile model capable of dealing with the varieties of audio signals. Since sampling frequency, one of the audio signal varieties, is usually application specific, the preceding audio source separation model should be able to deal with audio signals of all sampling frequencies specified in the target applications. However, conventional models based on deep neural networks (DNNs) are trained only at the sampling frequency specified by the training data, and there are no guarantees that they work with unseen sampling frequencies. In this paper, we propose a convolution layer capable of handling arbitrary sampling frequencies by a single DNN. Through music source separation experiments, we show that the introduction of the proposed layer enables a conventional audio source separation model to consistently work with even unseen sampling frequencies.

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。

↑