S. Rau, F. Heyen, and M. Sedlmair. Extended Abstracts for the Late-Breaking Demo Session of the 22nd Int. Society for Music Information Retrieval Conf. (ISMIR), ISMIR, (November 2021)
Abstract
We propose a visual approach for AI-assisted music composition, where the user interactively generates, selects, and adapts short melodies. Based on an entered start melody, we automatically generate multiple continuation samples. Repeating this step and in turn generating continuations for these samples results in a tree or graph of melodies. We visualize this structure with two visualizations, where nodes display the piano roll of the corresponding sample. By interacting with these visualizations, the user can quickly listen to, choose, and adapt melodies, to iteratively create a composition. A third visualization provides an overview over larger numbers of samples, allowing for insights into the AI's predictions and the sample space.
%0 Conference Paper
%1 simeon_rau_2021
%A Rau, Simeon
%A Heyen, Frank
%A Sedlmair, Michael
%B Extended Abstracts for the Late-Breaking Demo Session of the 22nd Int. Society for Music Information Retrieval Conf. (ISMIR)
%D 2021
%I ISMIR
%K cybervalley myown peerreviewed vis(us) visus visus:heyenfk visus:rausn visus:sedlmaml
%T Visual Support for Human-AI Co-Composition
%U https://archives.ismir.net/ismir2021/latebreaking/000014.pdf
%X We propose a visual approach for AI-assisted music composition, where the user interactively generates, selects, and adapts short melodies. Based on an entered start melody, we automatically generate multiple continuation samples. Repeating this step and in turn generating continuations for these samples results in a tree or graph of melodies. We visualize this structure with two visualizations, where nodes display the piano roll of the corresponding sample. By interacting with these visualizations, the user can quickly listen to, choose, and adapt melodies, to iteratively create a composition. A third visualization provides an overview over larger numbers of samples, allowing for insights into the AI's predictions and the sample space.
@inproceedings{simeon_rau_2021,
abstract = {We propose a visual approach for AI-assisted music composition, where the user interactively generates, selects, and adapts short melodies. Based on an entered start melody, we automatically generate multiple continuation samples. Repeating this step and in turn generating continuations for these samples results in a tree or graph of melodies. We visualize this structure with two visualizations, where nodes display the piano roll of the corresponding sample. By interacting with these visualizations, the user can quickly listen to, choose, and adapt melodies, to iteratively create a composition. A third visualization provides an overview over larger numbers of samples, allowing for insights into the AI's predictions and the sample space.},
added-at = {2023-03-06T17:02:25.000+0100},
author = {Rau, Simeon and Heyen, Frank and Sedlmair, Michael},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2425a202f1f2b57901730a205cd73639f/simeonrau},
booktitle = {Extended Abstracts for the Late-Breaking Demo Session of the 22nd Int. Society for Music Information Retrieval Conf. (ISMIR)},
interhash = {9555876aa0ebae610afa0697d9c7f8ee},
intrahash = {425a202f1f2b57901730a205cd73639f},
keywords = {cybervalley myown peerreviewed vis(us) visus visus:heyenfk visus:rausn visus:sedlmaml},
month = nov,
publisher = {ISMIR},
tags = {myown vis(us) visus:heyenfk visus:sedlmaml cybervalley peerreviewed visus visus:rausn sent:unibiblio for:visus},
timestamp = {2023-03-06T17:02:25.000+0100},
title = {Visual Support for Human-AI Co-Composition},
url = {https://archives.ismir.net/ismir2021/latebreaking/000014.pdf},
year = 2021
}
