{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-a-latent-space-of-multitrack","title":"Learning a Latent Space of Multitrack Measures","arxiv_id":"1806.00195","date":"2018-06-01","proceeding":null,"authors":["Ian Simon","Adam Roberts","Colin Raffel","Jesse Engel","Curtis Hawthorne","Douglas Eck"],"abstract":"Discovering and exploring the underlying structure of multi-instrumental\nmusic using learning-based approaches remains an open problem. We extend the\nrecent MusicVAE model to represent multitrack polyphonic measures as vectors in\na latent space. Our approach enables several useful operations such as\ngenerating plausible measures from scratch, interpolating between measures in a\nmusically meaningful way, and manipulating specific musical attributes. We also\nintroduce chord conditioning, which allows all of these operations to be\nperformed while keeping harmony fixed, and allows chords to be changed while\nmaintaining musical \"style\". By generating a sequence of measures over a\npredefined chord progression, our model can produce music with convincing\nlong-term structure. We demonstrate that our latent space model makes it\npossible to intuitively control and generate musical sequences with rich\ninstrumentation (see https://goo.gl/s2N7dV for generated audio).","url_abs":"http://arxiv.org/abs/1806.00195v1","url_pdf":"http://arxiv.org/pdf/1806.00195v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-a-latent-space-of-multitrack","repo_url":"https://github.com/tensorflow/magenta","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}