-
Given a current sequence, predict the score for the next note, then do a prediction for each step you want to generate.
- (1) RNNs operate on sequences of vectors, for the input and output, which is good for sequential data such as a music score, and (2) keep an internal state composed of the previous output steps, which is good for doing a prediction based on past inputs, not only the current input.
- (1) First, the hidden layer will get h(t + 1), which is the output of the previous hidden layer, and (2) it will also receive x(t + 2), which is the input of the current step.
- The number of bars generated will be 2 bars, or 32 steps, since we have 16 steps per bar. At 80 QPM, each step takes 0.1875 seconds, because you take the number of seconds in a minute, divide by the QPM, and divide by the number of steps per quarter: 60...
- Tech Categories
- Best Sellers
- New Releases
- Books
- Videos
- Audiobooks
Tech Categories Popular Audiobooks
- Articles
- Newsletters
- Free Learning
You're reading from Hands-On Music Generation with Magenta
Alexandre DuBreuil is a software engineer and generative music artist. Through collaborations with bands and artists, he has worked on many generative art projects, such as generative video systems for music bands in concerts that create visuals based on the underlying musical structure, a generative drawing software that creates new content based on a previous artist's work, and generative music exhibits in which the generation is based on real-time events and data. Machine learning has a central role in his music generation projects, and Alexandre has been using Magenta since its release for inspiration, music production, and as the cornerstone for making autonomous music generation systems that create endless soundscapes.
Read more about Alexandre DuBreuil
Unlock this book and the full library FREE for 7 days
Author (1)
Alexandre DuBreuil is a software engineer and generative music artist. Through collaborations with bands and artists, he has worked on many generative art projects, such as generative video systems for music bands in concerts that create visuals based on the underlying musical structure, a generative drawing software that creates new content based on a previous artist's work, and generative music exhibits in which the generation is based on real-time events and data. Machine learning has a central role in his music generation projects, and Alexandre has been using Magenta since its release for inspiration, music production, and as the cornerstone for making autonomous music generation systems that create endless soundscapes.
Read more about Alexandre DuBreuil