Engineering:Nsynth Super
| Nsynth Super | |
|---|---|
 Nsynth Super Front Panel | |
| Manufacturer | |
| Dates | 2018 |
| Technical specifications | |
| Synthesis type | Neural Network Sample-based synthesis |
| Input/output | |
| Left-hand control | Pitch bend, ADSR |
| External control | MIDI |
Nsynth Super is an audio synthesizer released by Google in 2018.[1] It is designed to provide musicians with an accessible interface to the Nsynth algorithm, developed by the research group Magenta.[2] Design files, source code and internal components are released under an open source Apache License 2.0[3], enabling hobbyists and musicians to freely build and use the instrument.[4][5]
Reception
Online communities of Nsynth enthusiasts are gathering through online platforms such as Facebook and Discord,[6][7] while others are sharing their builds and insights on their personal blogs and forums. [8][9][10] The instrument was well-received by the electronic music community,[11][12] including features from notable artists, such as Grimes and Yacht, using Nsynth Super in their music productions.[13][14]
Functions
Algorithm
The instrument provides an accessible interface for the Nsynth algorithm, which generates sounds through a neural network based synthesis, employing a WaveNet-style autoencoder to learn its own temporal embeddings from four different sounds.[15] The research and development of the algorithm was part of a collaboration between Google Brain, Magenta and DeepMind.[16]
Interface
Users are able to select the source samples by rotating the four encoders located at the corners of the interface, then select the output through a central touch-sensitive interface. The output sample can be further tweaked by editing the ADSR envelope control through four dials on the bottom side of the top panel.[17]
References
- ↑ "Google built a musical instrument that uses AI and released the plans so you can make your own". 13 March 2018. https://www.cnbc.com/2018/03/13/google-launches-nsynth-super-ai-hardware-prototype.html.
- ↑ Jesse Engel, Cinjon Resnick, Adam Roberts, Sander Dieleman, Douglas Eck, Karen Simonyan, Mohammad Norouzi (2017). "Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders". arXiv:1704.01279 [cs.LG].CS1 maint: uses authors parameter (link)
- ↑ "googlecreativelab/open-nsynth-super". April 1, 2021. https://github.com/googlecreativelab/open-nsynth-super.
- ↑ Nast, Condé. "Google's open-source neural synth is creating totally new sounds". Wired UK. https://www.wired.co.uk/article/google-ai-nsynth-algorithm-music-creativity.
- ↑ "Open NSynth Super". https://hackaday.io/project/89396-open-nsynth-super.
- ↑ "Nynth Super Builders". https://www.facebook.com/groups/806994336150545/.
- ↑ "Nynth Super Builders". https://discord.com/invite/StJ84Hb.
- ↑ "Error: no
|title=specified when using {{Cite web}}". https://gearspace.com/board/electronic-music-instruments-and-electronic-music-production/1206371-nsynth-super-ai-powered-neural-synth-google.html. - ↑ "Building the open Nsynth Super". 21 August 2018. https://ditheringstudio.wordpress.com/2018/08/21/open-nsynth-super/.
- ↑ "Google Nsynth Super - I built something. It works.". https://www.youtube.com/watch?v=QKCRANEsWB8.
- ↑ "Google has designed a DIY controller for its AI synthesizer". 14 March 2018. https://www.factmag.com/2018/03/14/google-magenta-nsynth-super/.
- ↑ "How Machine Learning Will Revolutionize Music Production". 8 August 2018. https://medium.com/@sedwardscode/how-machine-learning-will-revolutionize-music-production-2e129533d603.
- ↑ "73 | Grimes (c) on Music, Creativity, and Digital Personae – Sean Carroll". https://www.preposterousuniverse.com/podcast/2019/11/18/73-grimes-c-on-music-creativity-and-digital-personae/.
- ↑ "Music and Machine Learning (Google I/O'19)". https://www.youtube.com/watch?v=pM9u9xcM_cs.
- ↑ Engel, Jesse; Resnick, Cinjon; Roberts, Adam; Dieleman, Sander; Eck, Douglas; Simonyan, Karen; Norouzi, Mohammad (2017). "Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders". arXiv:1704.01279 [cs.LG].
- ↑ "NSynth: Neural Audio Synthesis". https://magenta.tensorflow.org/nsynth.
- ↑ "Music with Artificial Intelligence". https://www.youtube.com/watch?v=AaALLWQmCdI.
Further Reading
Jesse Engel, Cinjon Resnick, Adam Roberts, Sander Dieleman, Douglas Eck, Karen Simonyan, Mohammad Norouzi (2017). "Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders". arXiv:1704.01279 [cs.LG].CS1 maint: uses authors parameter (link)
External links
 |  |
