О модульном подходе к музыкальному творчеству с поддержкой искусственного интеллекта
Аннотация
В последнее время системы музыкального творчества с использованием искусственного интеллекта стремительно развиваются. Быстрый рост методов машинного обучения уже привел к появлению множества мощных решений в области синтеза звука, генеративных технологий, извлечения информации из музыки и других направлений. Доступность вычислительных ресурсов способствует прогрессу в разработке решений для обработки необработанного аудио. Декомпозиция задач может снижать сложность предлагаемых решений, обеспечивая повышение качества на каждом этапе производства.
Литература
I. Gorbunova, “The integrative model for the semantic space of music and a contemporary musical educational process: the scientific and creative heritage of Mikhail Borisovich Ignatyev,” Educa¸c˜ao, vol. 46, pp. 1–23, 2021; doi:10.5902/1984644453329
I. B. Gorbunova and M. S. Zalivadny, “The Trans-Disciplinary Approach to the Study of Musical Phenomena: The Information Theory and Its Impact on Various Fields of Musicology,” Problemy muzykal’noi nauki / Music Scholarship, no. 2, pp. 180–199, 2024 (in Russian); doi:10.56620/2782-3598.2024.2.180-199
I. Gorbunovа and A. Govorova, “Music Computer Technologies in Informatics and Music Studies at Schools for Children with Deep Visual Impairments: From the Experience,” Informatics in Schools. Fundamentals of Computer Science and Software Engineering, pp. 381–389, 2018; doi:10.1007/978-3-030-02750-6_29
E. N. Bazhukova et al., Muzykal’naya informatika: uchebnoe posobie [Musical informatics: a tutorial], St. Petersburg, Russia: Lan’. Planeta muzyki, 2023 (in Russian).
I. B. Gorbunova, Informatsionnye tekhnologii v muzyke. Kn. 1: Muzykal’nye sintezatory: uchebnoe posobie [Information Technology in Music. Book 1: Music Synthesizers: A Tutorial], Moscow: LENAND, URSS, 2024 (in Russian).
I. B. Gorbunova, Informatsionnye tekhnologii v muzyke. Kn. 2: Muzykal’nye sintezatory: uchebnoe posobie [Information Technology in Music. Book 1: Music Synthesizers: A Tutorial], Moscow: LENAND, URSS, 2024 (in Russian).
I. B. Gorbunova and S. V. Chibirev, “Modeling the Process of Musical Creativity in Musical Instrument Digital Interface Format,” Opcion, vol. 35, no. Special Issue 22, pp. 392–409, 2019.
S. Chibirev and I. Gorbunova, “Computer Modeling in Musical Creative Work: An Interdisciplinary Research Example,” Lecture Notes in Networks and Systems, vol. 345, pp. 474–483, 2022; doi:10.1007/978-3-030-89708-6_40
I. B. Gorbunova et al., “Opyt komp’yuternogo modelirovaniya proizvedenii muzykal’nogo tvorchestva na osnove kompleksnogo issledovaniya zakonomernostei muzyki” [Experience of computer modeling of musical works based on a comprehensive study of musical patterns], in Muzyka, matematika, informatika: kompleksnaya model’ semanticheskogo prostranstva muzyki: monograph, I. B. Gorbunova et al. eds., pp. 159–252, St. Petersburg, Russia: Lan’. Planeta muzyki, 2024 (in Russian).
A. Kirke and E. R. Miranda, “Performance Creativity in Computer Systems for Expressive Performance of Music,” E. R. Miranda ed., in Handbook of Artificial Intelligence for Music, Springer, Cham., 2021.
C.-C. Chang and L. Su, “Beast: Online Joint Beat and Downbeat Tracking Based on Streaming Transformer,” in Proc. of ICASSP 2024 — 2024 IEEE Int. Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 396–400, 2024; doi:10.1109/icassp48485.2024.10446611
S. Boeck, F. Krebs, and G. Widmer “Joint Beat and Downbeat Tracking with Recurrent Neural Networks,” in Proc. of the 17th International Society for Music Information Retrieval Conference (ISMIR), pp. 255–261, 2016.
J.-Y. Hsu and L. Su, “VOCANO: A Note Transcription Framework for Singing Voice in Polyphonic Music,” in Proc. of the Int. Society of Music Information Retrieval Conference (ISMIR), pp. 295–300, 2021.
I.-C.Wei, C.-W. Wu, and L. Su, “Improving Automatic Drum Transcription Using Large Scale Audio-to-Midi Aligned Data,” in Proc. of 2021 IEEE Int. Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 246–250, 2021.
Y.-T. Wu, B. Chen, and L. Su, “Multi-Instrument Automatic Music Transcription With Self-Attention-Based Instance Segmentation,” in Proc. of IEEE/ACM Transactions on Audio, Speech, and Language, vol. 28, pp. 2796–2809, 2020, doi:10.1109/taslp.2020.3030482
Y.-S. Huang, S.-Y. Chou, and Y.-H. Yang, “Pop Music Highlighter: Marking the Emotion Keypoints,” Transactions of the International Society for Music Information Retrieval, vol. 1, no. 1, pp. 68–78, 2018; doi:10.5334/tismir.14
J.-C.Wang et al., “Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-Task Learning,” in Proc. of ICASSP 2021 — 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 566–570, 2021; doi:10.1109/icassp39728.2021.9413773
O. Nieto and J. P. Bello, “Systematic Exploration of Computational Music Structure Research,” in Proc. of the 17th International Society for Music Information Retrieval Conference (ISMIR), New York City, NY, USA, 2016.
K. Pyrovolakis, P. Tzouveli, and G. Stamou, “Mood Detection Analyzing Lyrics and Audio Signal Based on Deep Learning Architectures,” in Proc. of 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9363–9370, 2021.
O. Aker, “AI-Assisted Music Mastering: An Exploration of Human and AI Practices in Contemporary Music Production,” Understanding Generative AI in a Cultural Context, pp. 17–50, 2024; doi:10.4018/979-8-3693-7235-7.ch002
D. Koszewski et al., “Automatic music signal mixing system based on one-dimensionalWave-U-Net autoencoders,” EURASIP Journal on Audio, Speech, and Music Processing, no. 1, pp. 1–17, 2023; doi:10.1186/s13636-022-00266-3
A. Othman, ChatGPT + SUNO: A Beginner’s Guide to AI-Assisted Songwriting and Music Production, 2024; doi:10.13140/RG.2.2.33670.48960
Y. Li and X. Liu, “An Intelligent Music Production Technology Based on Generation Confrontation Mechanism,” Computational Intelligence and Neuroscience, pp. 1–10, 2022; doi:10.1155/2022/5083146
S. Stojak and A. Hofmann, eds., Proceedings of the 7th International Csound Conference, Vienna: University of Music and Performing Arts Vienna, 2024; doi:10.21939/icsc2024
S. Boeck et al., “madmom: A New Python Audio and Music Signal Processing Library,” in Extended abstracts for the Late-Breaking Demo Session of the 17th International Society for Music Information Retrieval Conference, pp. 1174–1178, 2016; doi:10.1145/2964284.2973795
V. Jayaram, “Finding Choruses in Songs with Python,” in towardsdatascience.com, 2024. [Online]. Available: https://towardsdatascience.com/finding-choruses-in-songs-with-python-a925165f94a8
Материал публикуется под лицензией:
