publication . Other literature type . Doctoral thesis . 2018

A Wavenet For Music Source Separation

Salvadó, Francesc Lluís;
Open Access
  • Published: 31 Aug 2018
  • Publisher: Zenodo
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 pred...
Download fromView all 3 versions
Other literature type . 2018
Provider: Datacite
Doctoral thesis . 2018
Provider: ZENODO
Other literature type . 2018
Provider: Datacite
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue