If you still think engineers have no talent in pick up hot chicks, then you are wrong.
Not long ago, several Facebook programmers recently created a musical artifact that can play a piece of music on six different instruments. Then Google’s technology leaders did not want to be outdone. They used AI to create a music synthesizer and officially joined the professional pick up hot chicks club.
A Quick Guide to Code Musicians
As we all know, CNN can reconstruct the style of pictures, such as making some filters to make your selfie look like Van Gogh’s works. The industry also calls this convoluted neural network Nural.
Inspired by this, engineers tried to apply CNN to music, hoping to do something big, such as making AI play music with whistles like humans.
Brother, brother, seriously coding’s state is very similar to Lang Lang’s.
In practice, everyone knows that AI can’t read notes directly, so the notes must first be converted into a pattern that the machine can recognize, then decoded and reconstructed by CNN, and a new file is generated.
After constant debugging, they have been able to play the same tune with 6 different styles of musical instruments, including imitating human whistling.
Google’s Little Brother How to Make AI Music
At present, the program developed by FaceBook’s younger brother can only switch music styles. It doesn’t sound romantic enough. Google engineers immediately released pick up hot chicks’s big move:
“Create a unique voice for your sister. 」
Magenta is an AI project initiated by Google and combined with music, specifically exploring how to apply machine learning to music creation. They released NSynth (Neural Synthesizer), the main author of this project is Yotam Mann, who relies on deep neural networks to learn the features of sound and generate an unprecedented sound based on these features.
Yotam thinks that the reason why classical musical instruments are popular is that both piano and guitar, or erhu, have their own unique timbre and range. However, the NSynth that he wrote did not simply mix the sounds together, nor did he reconstruct the music style.
Instead, it uses the acoustic characteristics of the original sound to synthesize a brand-new sound, such as matching flute and piano sound in proportion to create a new sound.
In the NSythTH algorithm established by Yotam, a compressed sound (represented by z) is first generated. Then, the decoder network converts it into echo, and trains the whole system to make the output sound as close to the real sound as possible.
In order to reduce the use threshold of NSynth, Magenta and Google Creative Lab jointly created NSynth Super, an open source music synthesis hardware product.
With more than 100,000 voices preloaded, NSynth Super has created many voices through algorithms. You can select these voices through the dial. Of course, you can also create new sounds through the touch screen.
At present, many professional music producers are already using this product. Artistic creation needs inspiration, and this brand-new sound synthesis will also provide some different inspiration to creators in terms of playability and creativity.
If you are interested in NSynth Super source code, schematic diagram and design template, you can find demo at GitHub.
Yotam Mann is the little brother with deep feeling in his eyes. I heard that he has hardly ever been single.
Encyclopedia of Super Nerve
[gzdretd] adj.v. expansion
Fundamental frequency fundamental frequency
Intuitive parameters intuitive parameters
Single dog single dog