Humming2Music: Being A Composer As Long As You Can Humming
Yao Qiu, Jinchao Zhang, Huiying Ren, Yong Shan, Jie Zhou
Abstract
Creating a piece of music is difficult for people who have never been trained to compose. We present an automatic music generation system to lower the threshold of creating music. The system takes the user's humming as input and creates full music based on the humming melody. The system consists of five modules: 1) humming transcription, 2) melody generation, 3) broken chord generation, 4) accompaniment generation, and 5) audio synthesis. The first module transcribes the user's humming audio to a score, and then the melody generation module composes a complete melody based on the user's humming melody. After that, the third module will generate a broken chord track to accompany the full melody, and the fourth module will create more accompanying tracks. Finally, the audio synthesis module mixes all the tracks to generate the music. Through the user experiment, our system can generate high-quality music with natural expression based on the user's humming input.
BibTeX
@inproceedings{ijcai2023p840,
title = {Humming2Music: Being A Composer As Long As You Can Humming},
author = {Qiu, Yao and Zhang, Jinchao and Ren, Huiying and Shan, Yong and Zhou, Jie},
booktitle = {Proceedings of the Thirty-Second International Joint Conference on
Artificial Intelligence, {IJCAI-23}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Edith Elkind},
pages = {7163--7166},
year = {2023},
month = {8},
note = {Demo Track},
doi = {10.24963/ijcai.2023/840},
url = {https://doi.org/10.24963/ijcai.2023/840},
}