Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Thesis . 2018
License: CC BY
Data sources: Datacite
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Other literature type . 2018
License: CC BY
Data sources: ZENODO
versions View all 2 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

A Wavenet For Music Source Separation

Authors: Francesc Lluís Salvadó;

A Wavenet For Music Source Separation

Abstract

Currently, most successful source separation techniques use magnitude spectrograms as input, and are therefore by default discarding part of the signal: the phase. In order to avoid discarding potentially useful information, we propose an end-to-end learning model based on Wavenet for music source separation. As a result, the model we propose directly operates over the waveform, enabling, in that way, to consider any information available in the raw audio signal. Provided that the original Wavenet model operates sequentially (i.e., is not parallelizable and hence slow), in this work we make use of a discriminative non-causal adaptation of Wavenet capable to predict more than one sample at a time, thus permitting to overcome the undesirable time-complexity that the original Wavenet model has. Further, we investigate several data augmentation techniques and architectural changes to provide some insights on which are the most sensitive hyper-parameters for this family of Wavenet-like models. Our experimental results show that it is possible to approach the problem of music source separation in a end-to-end learning fashion, since our model performs on par with DeepConvSep, a state-of-the-art method based on processing magnitude spectrograms.

2.2 NMF applied to the spectrogram of a short piano sequence composed of four notes [1]. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.3 Example of a neural network. Each circular node represents an arti cial neuron and an arrow represents a connection from the output of one neuron to the input of another. . . . . . . . . . . . . . . . . . . . . . . 17 2.4 Arti cial neuron model . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 2.5 DeepConvSep Network Architecture . . . . . . . . . . . . . . . . . . . . 20 2.6 a) Residual layer. b) Dilated convolutions . . . . . . . . . . . . . . . . 22 2.7 Visualization of a stack of non-causal convolutional layers . . . . . . . . 24 2.8 Target eld prediction . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 3.1 Musdb18 dataset multitrack format . . . . . . . . . . . . . . . . . . . . 26 3.2 Circular shifting diagram . . . . . . . . . . . . . . . . . . . . . . . . . . 30 3.3 Forcing singing voice diagram . . . . . . . . . . . . . . . . . . . . . . . 30 3.6 Ensuring singing voice diagram . . . . . . . . . . . . . . . . . . . . . . 38 [1] Cedric Fevotte, Emmanuel Vincent, and Alexey Ozerov. Single-channel audio source separation with nmf: divergences, constraints and algorithms. In Audio Source Separation, pages 1{24. Springer, 2018.

[10] Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, Dinei Flor^encio, and Mark Hasegawa-Johnson. Speech enhancement using bayesian wavenet. In Proc. Interspeech, pages 2013{2017, 2017.

[28] Nathanael Perraudin, Peter Balazs, and Peter L S ndergaard. A fast gri n-lim algorithm. In Applications of Signal Processing to Audio and Acoustics (WASPAA), 2013 IEEE Workshop on, pages 1{4. IEEE, 2013.

[36] Jong Wook Kim, Justin Salamon, Peter Li, and Juan Pablo Bello. Crepe: A convolutional representation for pitch estimation. arXiv preprint arXiv:1802.06182, 2018.

[37] Daniel Stoller, Sebastian Ewert, and Simon Dixon. Wave-u-net: A multiscale neural network for end-to-end audio source separation. arXiv preprint arXiv:1806.03185, 2018.

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 418
    download downloads 242
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    Powered byBIP!BIP!
  • 418
    views
    242
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
418
242
Green
Related to Research communities