paper-with-me

홈 › Papers

Upsampling layers for music source separation

2021-11-23 · Jordi Pons, Joan Serrà, Santiago Pascual, Giulio Cengarle, Daniel Arteaga, Davide Scaini

Upsampling artifacts are caused by problematic upsampling layers and due to spectral replicas that emerge while upsampling. Also, depending on the used upsampling layer, such artifacts can either be tonal artifacts (additive high-frequency noise) or filtering artifacts (substractive, attenuating some bands). In this work we investigate the practical implications of having upsampling artifacts in the resulting audio, by studying how different artifacts interact and assessing their impact on the models' performance. To that end, we benchmark a large set of upsampling layers for music source separation: different transposed and subpixel convolution setups, different interpolation upsamplers (including two novel layers based on stretch and sinc interpolation), and different wavelet-based upsamplers (including a novel learnable wavelet layer). Our results show that filtering artifacts, associated with interpolation upsamplers, are perceptually preferrable, even if they tend to achieve worse objective scores.

📄 PDF Abstract BibTeX arXiv:2111.11773

Code (0)

등록된 구현이 없습니다.

Tasks

Music Source Separation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Denoising Auto-encoder with Recurrent Skip Connections and Residual Regression for Music Source Separation

2018-07-05 · Jen-Yu Liu, Yi-Hsuan Yang

Convolutional neural networks with skip connections have shown good performance in music source separation. In this work, we propose a denoising Auto-encoder with Recurrent skip Connections (ARC). We use 1D convolution a…

ARCDenoisingMusic Source Separationregression

Content based singing voice source separation via strong conditioning using aligned phonemes

2020-08-05 · Gabriel Meseguer-Brocal, Geoffroy Peeters

Informed source separation has recently gained renewed interest with the introduction of neural networks and the availability of large multitrack datasets containing both the mixture and the separated sources. These appr…

Information RetrievalMusic Information RetrievalRetrieval

Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet Transform

2020-01-28 · Tomohiko Nakamura, Hiroshi Saruwatari

We propose a time-domain audio source separation method using down-sampling (DS) and up-sampling (US) layers based on a discrete wavelet transform (DWT). The proposed method is based on one of the state-of-the-art deep n…

Audio Source SeparationMusic Source Separation

Pre-training Music Classification Models via Music Source Separation

2023-10-24 · Christos Garoufis, Athanasia Zlatintsi, Petros Maragos

In this paper, we study whether music source separation can be used as a pre-training strategy for music representation learning, targeted at music classification tasks. To this end, we first pre-train U-Net networks und…

ClassificationGenre classificationMusic Auto-TaggingMusic Classification+3

Dilated Convolution with Dilated GRU for Music Source Separation

2019-06-04 · Jen-Yu Liu, Yi-Hsuan Yang

Stacked dilated convolutions used in Wavenet have been shown effective for generating high-quality audios. By replacing pooling/striding with dilation in convolution layers, they can preserve high-resolution information …

Music Source Separation