synthesis   2873

« earlier    

Generate your own sounds with NSynth
NSynth is, in my opinion, one of the most exciting developments in audio synthesis since granular and concatenative synthesis. It is one of the only neural networks capable of learning and directly generating raw audio samples. Since the release of WaveNet in 2016, Google Brain’s Magenta and DeepMind have gone on to explore what’s possible with this model in the musical domain. They’ve built an enormous dataset of musical notes and also released a model trained on all of this data. That means you can encode your own audio using their model, and then use the encoding to produce fun and bizarre new explorations of sound.
nsynth  ML  AI  Tensorflow  music  synthesis 
yesterday by euler
Generate your own sounds with NSynth
NSynth is, in my opinion, one of the most exciting developments in audio synthesis since granular and concatenative synthesis. It is one of the only neural networks capable of learning and directly generating raw audio samples. Since the release of WaveNet in 2016, Google Brain’s Magenta and DeepMind have gone on to explore what’s possible with this model in the musical domain. They’ve built an enormous dataset of musical notes and also released a model trained on all of this data. That means you can encode your own audio using their model, and then use the encoding to produce fun and bizarre new explorations of sound.

Since NSynth is such a large model, naively generating audio would take a few minutes per sample, making it pretty much a nonstarter for creative exploration. Luckily, there is plenty of knowledge floating out there about how to make the WaveNet decoder faster1. As part of development for my course on Creative Applications of Deep Learning, I spent a few days implementing a faster sampler in NSynth, submitted a pull request to the Magenta folks, and it’s now part of the official repo. The whole team was incredibly supportive and guided me through the entire process, offering a ton of feedback. I’d highly encourage you to reach out via GitHub or the Magenta Google Group with any questions if you are interested in contributing to the project.
music  synthesis 
6 days ago by tonyyet
How to make an old-school garage bass - YouTube
Get a Prodigy - Full Throttle-style bass sound, part 1 of 2. Program a classic rave '90s rave/garage bass. From Computer Music.
sounddesign  bass  production  synthesis 
14 days ago by meeb

« earlier    

related tags

a  accretion  acm  acmtariat  activities  ai  analogkeys  analysis  and  andy  api  app  applications  apps  arduino  are:  arrows  art  article  atmel  atoms  attiny  attiny85  audio-generation  audio  automatonism  awesome  bass  big-picture  bio  biology  boltzmann  book  broad  c++  c  canada  capital  characterization  cheatsheet  chemistry  clarity  closure  collected  collection_  company  concept  conceptual-vocab  copying  csound  curiosity  curtisroads  data  data_  dds  deep-learning  deeplearning  delicious  demo  derek  design  drum  drums  dynamical  econ-productivity  economics  electornic  electromag  electronic  electronics  elektron  embedded  emotions  emulation  encyclopedic  enquiries_  examples  experimental  explanation  exposition  fake  farnel  formant  fourier  from  fun  funny  gamedev  generation  generative  generator  geometry  grain  granular  gravity  growth-econ  harddrive  hi-order-bits  history  holzer  html5  human  identify  identity  ieee  image-processing  impersonate  init  instrument  integral  intended  interactive  interface  ios  is  javascript  js  juce  labor  learning  lens  levers  library  linear-algebra  linear-models  linguistics  links  linux  list  mac  machine-learning  machine  machinelearning  macos  making  malbec  math.ca  math.cv  math  max-msp  mechanics  medicine  metabuch  midi  minimum-viable  ml  model-class  model  modular  montreal  motivation  mouth  music  musicproduction  n-synth  neuralnetwork  nibble  noise  nsynth  ocaml  octatrack  of  one-name  online  optimization  org:bleg  org:edu  organelle  osx  overflow  paper  patch  pc  pd  pdf  performance  phonetics  physical  physics  pillars  pink  pippi  plugin  preserving  pro-apps  probability  procgen  production  program  programming  properties  publication  publicising  pure  puredata  python  q-n-a  quantum  reasoning  recording  reference  relativity  repository  research  responding  rytm  s:*  sample  science  security  sequencer  seven  simulation  singing  skeleton  software  sophenia  sound  sounddesign  space  speech-synthesis  speech  stat-mech  studies’  study.  study  study_  summary  synth  synthesizer  synthetic  teaching  tech  tensorflow  testing  text-to-speech  text  texture  the  thermo  these  tidbits  to  toread  towatch  trees  trombone  tts  tuning  tutorial  ui  upic  vector  video  visual-understanding  visual  vocal-tract  vocal  voice  waves  wavetable  web-audio  wiki  wikipedia  windows  wisdom  within  xenakis  your    ‘seven  🎩  🔬 

Copy this bookmark:



description:


tags: