liveBook · Manning

Style

As explained in Learn Generative AI with PyTorch

A musical stylistic attribute that influences the character of generated pieces, distinct from the earlier visual-use sense.

Musical style is the characteristic way music is composed, performed, and experienced. It shapes a piece’s identity through influences such as genre, era, and the composer’s or performer’s approach. section 13.2.1

In MuseGAN, style is one of four latent noise inputs, alongside chords, melody, and groove. Its 32-dimensional vector is shared across every track and bar in the composition. section 13.2.1

Figure 13.5 Music generation using chords, style, melody, and groove. Each music composition consists of four tracks and spans two bars. We will extract four noise vectors from the latent space for this purpose. The first vector, representing chords, has a dimension of (1, 32). This vector will be processed through a temporal network to expand the chords into two (1, 32) vectors, corresponding to the two bars, with identical values across all tracks. The second vector, denoting style, also has a dimension of (1, 32) and remains constant across all tracks and bars. The third vector, melody, is shaped as (4, 32). It will be stretched through a temporal network into two (4, 32) vectors, resulting in eight (1, 32) vectors, each representing a unique track and bar combination. Lastly, the fourth vector, groove, with a dimension of (4, 32), will be applied to the four tracks, maintaining the same values for both bars.

See how the style vector is shared across the four tracks and two bars, unlike melody and groove inputs. section 13.2.1

How Learn Generative AI with PyTorch covers it

How deep it goes
Defines style through genre, era, and performer or composer approach, then assigns it a 32-dimensional vector shared across tracks and bars.
Examples
Uses jazz, classical, and rock as genre examples and shares one style vector across four tracks and two bars.
What you can do after
Understand how a shared style input contributes to generated music alongside chord, melody, and groove inputs.
How it connects
Connects style with chords, melody, groove, latent space, and the MuseGAN generator.

Also explained in

Compare how 7 books explain style →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Learn Generative AI with PyTorch. The section links point to the parts of the book it draws on.