MUSIC: Metrics-based Understanding of Soundscapes in AI Composition
Keywords:
musical measures, musical instrument digital interface, pitch contour analysis, static velocity assessment, harmonic analysis, rhythmic correctness quantification, threshold value, harmonic compatibility, amplitude envelope evaluation, RMS Energy, zero-crossing analysis, music composition.Abstract
The present research explores into a multidimensional examination of AI-generated piano music, using various techniques that incorporates numerous musical measures. Pitch contour analysis, static velocity assessment, harmonic analysis, rhythmic correctness quantification with a threshold value, harmonic compatibility, liveliness evaluation, amplitude envelope evaluation, RMS Energy, and zero-crossing analysis are all part of the suggested technique. This investigation examines how these variables together help to understand the performance and divergence of AI-generated music compared to original works, using MIDI files as the foundation for AI-generated compositions. The results are more helpful to identify whether the music is AI generated or human. We give an original perspective on evaluating AI-generated music that exceeds existing methodologies, revealing insight on the expanding landscape of artificial creativity in music composition by using this complete methodology.
Downloads
References
M. Hilsdorf, “MusicLM — Has Google Solved AI Music Generation? - Towards Data Science,” Medium, Jun. 11, 2023. https://towardsdatascience.com/musiclm-has-google-solved-ai-musicgeneration-c6859e76bc3c
“MusicGen: Simple and Controllable Music Generation.” https://ai.honu.io/papers/musicgen/
“Open sourcing AudioCraft: Generative AI for audio made simple and available to all,” Meta, Aug. 02, 2023. https://ai.meta.com/blog/audiocraft-musicgen-audiogen-encodecgenerative-ai-audio/ (accessed Nov. 17, 2023).
H. ‐e. Schaefer, “Music-Evoked Emotions —Current Studies,” Frontiers in Neuroscience, Nov. 24, 2017. https://doi.org/10.3389/fnins.2017.00600
“Why Music Matters: The Cognitive Personalism of Reimer and Elliott.” https://cmed.ku.edu/private/daugherty.htmlXiong, Zeyu, Weitao Wang, Jing Yu, Yue Lin, and Ziyan Wang. "A Comprehensive Survey for Evaluation Methodologies of AI-Generated Music." arXiv preprint arXiv:2308.13736 (2023).
Li-Chia Yang and Alexander Lerch, “On the evaluation of generative models in music”, Neural Computing and Applications 32, 9(2020), 4773–4784.
Oded Ben-Tal, Matthew Tobias Harris, Bob L.T. Sturm, “How Music AI Is Useful: Engagements with Composers, Performers and Audiences”, Leonardo 2021, 54 (5): 510–516. doi: https://doi.org/10.1162/leon_a_01959
Joo-Wha Hong, Katrin Fischer, Yul Ha, Yilei Zeng, “Human, I wrote a song for you: An experiment testing the influence of machines’ attributes on the AI-composed music evaluation”, Computers in Human Behavior, Volume 131, 2022, 107239, ISSN 0747-5632, https://doi.org/10.1016/j.chb.2022.107239.
Xiong, Zeyu, et al. "A Comprehensive Survey for Evaluation Methodologies of AI-Generated Music." arXiv preprint arXiv:2308.13736 (2023).
Hyeshin Chu, Joohee Kim, Seongouk Kim, Hongkyu Lim, Hyunwook Lee, Seungmin Jin, Jongeun Lee, Taehwan Kim, and Sungahn Ko, “An Empirical Study on How People Perceive AI-generated Music”, In Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM '22), 2022, Association for Computing Machinery, New York, NY, USA, 304–314. https://doi.org/10.1145/3511808.3557235
D. P. Nicolalde Rodriguez, J. A. Apolinario and L. W. P. Biscainho, "Audio Authenticity: Detecting ENF Discontinuity With High Precision Phase Analysis", In IEEE Transactions on Information Forensics and Security, vol. 5, no. 3, pp. 534-543, Sept. 2010, doi: 10.1109/TIFS.2010.2051270.
Bachu, R. G., et al. "Separation of voiced and unvoiced using zero crossing rate and energy of the speech signal." American Society for Engineering Education (ASEE) zone conference proceedings. American Society for Engineering Education, 2008.
Kauppinen, Ismo, and Kari Roth. "Audio signal extrapolation–theory and applications." Proc. DAFx. 2002.
Luca Angioloni, Tijn Borghuis, Lorenzo Brusci, and Paolo Frasconi, “Conlon: A pseudo-song generator based on a new piano roll, wasserstein autoencoders, and optimal interpolations”, In Proceedings of the 21th International Society for Music Information Retrieval Conference ISMIR MTL2020, 2020, 876--883.
Mohit Dua, Rohit Yadav, Divya Mamgai, Sonali Brodiya, “An Improved RNN-LSTM based Novel Approach for Sheet Music Generation”, Procedia Computer Science, Volume 171, 2020, Pages 465-474, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2020.04.049.
E. Dervakos, G. Filandrianos and G. Stamou, "Heuristics for Evaluation of AI Generated Music," 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, 2021, pp.9164-9171, doi: 10.1109/ICPR48806.2021.9413310.
Bogdanov D, Wack N, Gómez E, Sankalp G, Herrera P, Mayor O, Roma G, Salamon J, Zapata J, Serra X, “Essentia: an audio analysis library for music information retrieval”, In: Britto A, Gouyon F, Dixon S, editors. 14th Conference of the International Society for Music Information Retrieval (ISMIR); 2013 Nov 4-8; Curitiba, Brazil. [place unknown]: ISMIR; 2013. p. 493-8.
M. F. McKinney and J. Breebaart, “Features for audio and music classification.,” in ISMIR, 2003, vol. 3, pp. 151–158.
T. Bertin-Mahieux, D. P. Ellis, B. Whitman, and P. Lamere, “The million song dataset,” in ISMIR 2011: Proceedings of the 12th International Society for Music Information Retrieval Conference, October 24-28, 2011, Miami, Florida. University of Miami, 2011, pp. 591–596.
McFee, Brian, et al. "librosa: Audio and music signal analysis in python."
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
