Memória P&D Design

15º Congresso Brasileiro de Pesquisa e Desenvolvimento em Design

UFAM — Manaus (AM)

Outubro/2024

Aplicações da Inteligência Artificial Generativa em Sound Design: Uma Revisão Sistemática da Literatura

Applications of Generative Artificial Intelligence in Sound Design: A Systematic Literature Review

Lucas Lima
Rodrigo Larrazábal

Como citar

Lima, Lucas; Larrazábal, Rodrigo; "Aplicações da Inteligência Artificial Generativa em Sound Design: Uma Revisão Sistemática da Literatura", p. 4360-4380. PPG Design Caderno Científico, Manaus, 2024. Anais do XV Congresso Brasileiro de Pesquisa e Desenvolvimento em Design – P&D Design Manaus., DOI https://doi.org/10.29327/5457226.1-362

Resumo

Este artigo apresenta uma revisão sistemática da literatura sobre as aplicações da Inteligência Artificial Generativa (GenAI) no design de som. A GenAI tem revolucionado a criação de ambientes sonoros complexos e personalizados, otimizando tempo e recursos, além de expandir as possibilidades criativas dos designers. Este estudo analisa os principais benefícios e desafios da GenAI no design de som, com foco em setores como entretenimento, jogos eletrônicos e realidade virtual. A metodologia envolve uma revisão rigorosa de artigos publicados entre 2019 e 2024, utilizando bases de dados como IEEE Xplore, ScienceDirect, Springer Link e Scopus. Os resultados destacam a eficiência aumentada e a criatividade possibilitada pela GenAI, enquanto apontam a necessidade de mais pesquisas empíricas e a exploração de novas técnicas para superar desafios técnicos e garantir a qualidade dos conteúdos gerados.
Palavras-chave:

Inteligência Artificial Generativa, Design de Som, Revisão Sistemática

Abstract

This article presents a systematic literature review on the applications of Generative Artificial Intelligence (GenAI) in sound design. GenAI has revolutionized the creation of complex and personalized sound environments, optimizing time and resources, while expanding the creative possibilities for designers. This study analyzes the main benefits and challenges of GenAI in sound design, focusing on sectors such as entertainment, video games, and virtual reality. The methodology involves a rigorous review of articles published between 2019 and 2024, using databases such as IEEE Xplore, ScienceDirect, Springer Link, and Scopus. The results highlight increased efficiency and creativity enabled by GenAI, while pointing to the need for more empirical research and the exploration of new techniques to overcome technical challenges and ensure the quality of generated content.

Referências bibliográficas

  • WIN, Yuzana; LWIN, Htoo Pyae; MASADA, Tomonari. Myanmar Text-to-Speech System based on Tacotron - End-to-End Generative Model. In: INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY CONVERGENCE (ICTC), 2020, Jeju, South Korea. Anais [...]. Jeju: IEEE, 2020. p. 572-577.

  • ZHAO, Lanxin; LI, Dengshi; XIAO, Jing; ZHU, Chenyi. Noise Adaptive Speech Intelligibility Enhancement Based on Improved StarGAN. In: IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2023, Brisbane, Austrália. Anais [...]. Brisbane: IEEE, 2023. p. 1313-1318.

  • WANG, Wenchu. Research on AI Composition Based on Deep Learning Techniques. In: IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND COMPUTER APPLICATION (ICDSCA), 2023, Dalian, China. Proceedings [...]. Dalian: IEEE, 2023. p. 1486-1489.

  • GOIENETXEA, Izaro; MENDIALDUA, Iñigo; RODRÍGUEZ, Igor; SIERRA, Basilio. Statistics-Based Music Generation Approach Considering Both Rhythm and Melody Coherence. IEEE Access, v. 7, p. 183365-183381, 2019.

  • DAI, Jinhui; ZHANG, Yue; XIE, Pengcheng; XU, Xinzhou. Super-Resolution for Music Signals Using Generative Adversarial Networks. In: IEEE 4th INTERNATIONAL CONFERENCE ON BIG DATA AND ARTIFICIAL INTELLIGENCE (BDAI), 2021, Qingdao, China. Anais [...]. Qingdao: IEEE, 2021. p. 171-175.

  • REMESH, Athira; PAUL, Anna K.; SINITH, M. S. Symbolic Domain Music Generation System Based on LSTM Architecture. In: INTERNATIONAL CONFERENCE ON NEXT GENERATION INTELLIGENT SYSTEMS (ICNGIS), 2022, Kerala, India. Anais [...]. Kerala: IEEE, 2022. p. 1-6.

  • MANNONE, Maria; TURCHET, Luca. Theoretical Quantum Modeling of Improvisation in Networked Music Performances to Regulate the Behaviour of Artificial Musicians. In: INTERNATIONAL SYMPOSIUM ON THE INTERNET OF SOUNDS, 2023, Venice, Italy. Proceedings [...]. Venice: IEEE, 2023. p. 1-8.

  • FAN, Tsai-Jyun; LU, Chien-Yu; CHIU, Wei-Chen; SU, Li; LEE, Che-Rung. Timbre-Enhanced Multi-Modal Music Style Transfer with Domain Balance Loss. In: INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI), 2020, Hsinchu, Taiwan. Anais [...]. Hsinchu: IEEE, 2020. p. 102-107.

  • WILKINGHOFF, Kevin; KURTH, Frank. Why Do Angular Margin Losses Work Well for Semi-Supervised Anomalous Sound Detection. IEEE/ACM Transactions on Audio, Speech, and Language Processing, v. 32, p. 608-619, 2024.

  • MUSTAFA, Samir; ALI, Nabil; AHMED, Sara. Generative AI: A Systematic Review Using Topic Modeling. Data and Information Management, v. 5, n. 3, p. 224-239, 2024.

  • SHAHIN, Mohammad; CHEN, F. Frank; HOSSEINZADEH, Ali. Harnessing Customized AI to Create Voice of Customer via GPT3.5. Advanced Engineering Informatics, v. 61, 2024.

  • O'TOOLE, Katherine; HORVÁT, Emőke-Ágnes. Extending Human Creativity with AI. Journal of Creativity, v. 34, p. 100080, 2024.

  • MOYSIS, Lazaros et al. Music deep learning: deep learning methods for music signal processing—a review of the state-of-the-art. IEEE Transactions on Neural Networks and Learning Systems, v. 32, n. 1, p. 1-12, 2023.