AES E-Library

MA. A.. Martínez Ramírez, D. Stoller, and D. Moffat, "A Deep Learning Approach to Intelligent Drum Mixing With the Wave-U-Net," J. Audio Eng. Soc., vol. 69, no. 3, pp. 142-151, (2021 March.). doi: https://doi.org/10.17743/jaes.2020.0031 MA. A.. Martínez Ramírez, D. Stoller, and D. Moffat, "A Deep Learning Approach to Intelligent Drum Mixing With the Wave-U-Net," J. Audio Eng. Soc., vol. 69 Issue 3 pp. 142-151, (2021 March.). doi: https://doi.org/10.17743/jaes.2020.0031
Abstract: The development of intelligent music production tools has been of growing interest in recent years. Deep learning approaches have been shown as being a highly effective method for approximating individual audio effects. In this work, we propose an end-to-end deep neural network based on the Wave-U-Net to perform automatic mixing of drums. We follow an end-to-end approach where raw audio from the individual drum recordings is the input of the system and the waveform of the stereo mix is the output. We compare the system to existing machine learning approaches to intelligent drum mixing. Through a subjective listening test we explore the performance of these systems when processing various types of drum mixes. We report that the mixes generated by our model are virtually indistinguishable from professional human mixes while also outperforming previous intelligent mixing approaches.

@article{martínez ramírez2021a,
author={martínez ramírez, marco a. and stoller, daniel and moffat, david},
journal={journal of the audio engineering society},
title={a deep learning approach to intelligent drum mixing with the wave-u-net},
year={2021},
volume={69},
number={3},
pages={142-151},
doi={https://doi.org/10.17743/jaes.2020.0031},
month={march},} @article{martínez ramírez2021a,
author={martínez ramírez, marco a. and stoller, daniel and moffat, david},
journal={journal of the audio engineering society},
title={a deep learning approach to intelligent drum mixing with the wave-u-net},
year={2021},
volume={69},
number={3},
pages={142-151},
doi={https://doi.org/10.17743/jaes.2020.0031},
month={march},
abstract={the development of intelligent music production tools has been of growing interest in recent years. deep learning approaches have been shown as being a highly effective method for approximating individual audio effects. in this work, we propose an end-to-end deep neural network based on the wave-u-net to perform automatic mixing of drums. we follow an end-to-end approach where raw audio from the individual drum recordings is the input of the system and the waveform of the stereo mix is the output. we compare the system to existing machine learning approaches to intelligent drum mixing. through a subjective listening test we explore the performance of these systems when processing various types of drum mixes. we report that the mixes generated by our model are virtually indistinguishable from professional human mixes while also outperforming previous intelligent mixing approaches.},}

TY - paper
TI - A Deep Learning Approach to Intelligent Drum Mixing With the Wave-U-Net
SP - 142 EP - 151
AU - Martínez Ramírez, Marco A.
AU - Stoller, Daniel
AU - Moffat, David
PY - 2021
JO - Journal of the Audio Engineering Society
IS - 3
VO - 69
VL - 69
Y1 - March 2021 TY - paper
TI - A Deep Learning Approach to Intelligent Drum Mixing With the Wave-U-Net
SP - 142 EP - 151
AU - Martínez Ramírez, Marco A.
AU - Stoller, Daniel
AU - Moffat, David
PY - 2021
JO - Journal of the Audio Engineering Society
IS - 3
VO - 69
VL - 69
Y1 - March 2021
AB - The development of intelligent music production tools has been of growing interest in recent years. Deep learning approaches have been shown as being a highly effective method for approximating individual audio effects. In this work, we propose an end-to-end deep neural network based on the Wave-U-Net to perform automatic mixing of drums. We follow an end-to-end approach where raw audio from the individual drum recordings is the input of the system and the waveform of the stereo mix is the output. We compare the system to existing machine learning approaches to intelligent drum mixing. Through a subjective listening test we explore the performance of these systems when processing various types of drum mixes. We report that the mixes generated by our model are virtually indistinguishable from professional human mixes while also outperforming previous intelligent mixing approaches.