We wouldn’t consider every possible combination of piano notes musical, just like not every random combination of letters is a sentence. The decoder network is attempting to reconstruct a piano improvisation that actually never took place. When you play on Piano Genie’s keyboard, the decoder receives your sequence of key presses and tries to decode it into a piano melody. Once the encoder and decoder learned to perform both tasks well enough, the authors of Piano Genie took the decoder (by itself) and connected its input to the 8 colored on-screen buttons. You can see they both share similar shapes. Below, the sequence generated by the encoder using 8 different symbols. The top image shows a piano roll visualization of a real performance. The encoder was also evaluated based on how similar the “shape” of the 8 note sequence was to the original (for instance, if the notes in the melody went up and then down, the numbers of the encoded sequence should go up and then down as well). The networks were evaluated by looking at how closely the output of the decoder matched the original melody. This is the role of AI: by training them, the neural networks can find the best way to do this conversion.īoth the encoder and decoder networks in Piano Genie were trained simultaneously using the 1400 piano performances mentioned. There’s not a unique way to encode the notes using 8 different values so they can later be decoded back and the creators of Piano Genie didn’t know which one was the best. We can decode it back to something that hopefully sounds similar, but will probably not be the same. When the notes of a melody are encoded using only 8 symbols it means that after each note there are only eight possible ways to continue. With a full piano each note of a melody can be any of 88 available pitches. Of course it’s not always possible to perfectly recover the original melody once it passes through the encoder and decoder. By connecting the encoder and decoder together the melody passes through a sort of funnel. The decoder reverses the process by taking this simplified sequence and outputting a melody that once again uses the different 88 notes a piano can produce. The encoder receives a melody (a sequence of notes) represented as the numbers 1-88 (the keys of the piano) as input and produces a sequence with the same length but using only the numbers 1 through 8. The Piano Genie AI was built by first creating two separate neural networks: an encoder and a decoder. They’re used for a very large variety of tasks such as image and voice recognition, playing games, developing drugs and vaccines, driving cars, or even creating music. Neural networks, on the other hand, are commonly used for tasks where describing the decision making process is not possible because of its complexity. The network learns to give “intelligent” responses through a training process: it receives many examples of input, has its performance evaluated on each, and then is given feedback so it can improve over time.įor a long time most AI systems required the programmer to precisely describe how to perform a task to the computer. signals from the nervous system) and produce an appropriate output (e.g. Similar to how groups of neurons work, they take an input (e.g. Neural Networks are AI systems inspired by biological brains. We can say that through this training it learned on its own, and by example, what piano music should sound like. Its AI is based on a neural network that was trained with 1400 performances from the International Piano e-Competition. Piano Genie was programmed without coding in any theoretical rules about harmony or composition. The Piano Genie AI will assist you by choosing which piano keys to play to make you sound more like a professional player. When playing you decide the timing of the notes and have some control over the “shape” of the melody: whether it should move up or down in pitch, and by how much.
0 Comments
Leave a Reply. |