Missing Melodies: AI Music Generation and its "Nearly" Complete Omission of the Global South

• URL: http://arxiv.org/abs/2412.04100v3
• Date: Mon, 25 Aug 2025 16:00:21 GMT
• Title: Missing Melodies: AI Music Generation and its "Nearly" Complete Omission of the Global South
• Authors: Atharva Mehta, Shivam Chauhan, Monojit Choudhury,
• Abstract summary: We conducted an analysis of over one million hours of audio datasets used in AI music generation research.<n>We identified a critical gap in the fair representation and inclusion of the musical genres of the Global South in AI research.<n>Around 40% of these datasets include some form of non-Western music, genres from the Global South account for only 14.6% of the data.
• Score: 14.147521533363028
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in generative AI have sparked renewed interest and expanded possibilities for music generation. However, the performance and versatility of these systems across musical genres are heavily influenced by the availability of training data. We conducted an extensive analysis of over one million hours of audio datasets used in AI music generation research and manually reviewed more than 200 papers from eleven prominent AI and music conferences and organizations (AAAI, ACM, EUSIPCO, EURASIP, ICASSP, ICML, IJCAI, ISMIR, NeurIPS, NIME, SMC) to identify a critical gap in the fair representation and inclusion of the musical genres of the Global South in AI research. Our findings reveal a stark imbalance: approximately 86% of the total dataset hours and over 93% of researchers focus primarily on music from the Global North. However, around 40% of these datasets include some form of non-Western music, genres from the Global South account for only 14.6% of the data. Furthermore, approximately 51% of the papers surveyed concentrate on symbolic music generation, a method that often fails to capture the cultural nuances inherent in music from regions such as South Asia, the Middle East, and Africa. As AI increasingly shapes the creation and dissemination of music, the significant underrepresentation of music genres in datasets and research presents a serious threat to global musical diversity. We also propose some important steps to mitigate these risks and foster a more inclusive future for AI-driven music generation.

Related papers

• Who Gets Heard? Rethinking Fairness in AI for Music Systems [27.73654834833813]
  We raise concerns about cultural and genre biases in AI for music systems.<n>These biases affect stakeholders including creators, distributors, and listeners shaping representation in AI for music.<n>We offer recommendations at dataset, model and interface level in music-AI systems.
  arXiv  Detail & Related papers  (2025-11-08T10:03:22Z)
• Bias beyond Borders: Global Inequalities in AI-Generated Music [39.80452596611506]
  GlobalDISCO is a large-scale dataset consisting of 73k music tracks generated by state-of-the-art commercial generative music models.<n>The dataset spans 147 languages and includes musical style prompts extracted from MusicBrainz and Wikipedia.<n>The dataset is globally balanced, representing musical styles from artists across 79 countries and five continents.
  arXiv  Detail & Related papers  (2025-10-02T12:33:10Z)
• Music for All: Exploring Multicultural Representations in Music Generation Models [13.568559786822457]
  We present a study of the datasets and research papers for music generation. We find that only 5.7% of the total hours of existing music datasets come from non-Western genres.
  arXiv  Detail & Related papers  (2025-02-11T07:46:29Z)
• Decoding Musical Evolution Through Network Science [39.58317527488534]
  We use Network Science to analyze musical complexity. We represent each composition as a weighted directed network to study its structural properties. Results show that Classical and Jazz compositions have higher complexity and melodic diversity than recently developed genres.
  arXiv  Detail & Related papers  (2025-01-13T18:39:44Z)
• A Survey of Foundation Models for Music Understanding [60.83532699497597]
  This work is one of the early reviews of the intersection of AI techniques and music understanding. We investigated, analyzed, and tested recent large-scale music foundation models in respect of their music comprehension abilities.
  arXiv  Detail & Related papers  (2024-09-15T03:34:14Z)
• Prevailing Research Areas for Music AI in the Era of Foundation Models [10.245601263106844]
  As AI-generated and AI-augmented music become increasingly mainstream, many researchers in the music AI community may wonder: what research frontiers remain unexplored?<n>This paper outlines several key areas within music AI research that present significant opportunities for further investigation.
  arXiv  Detail & Related papers  (2024-09-14T09:06:43Z)
• Foundation Models for Music: A Survey [77.77088584651268]
  Foundations models (FMs) have profoundly impacted diverse sectors, including music. This comprehensive review examines state-of-the-art (SOTA) pre-trained models and foundation models in music.
  arXiv  Detail & Related papers  (2024-08-26T15:13:14Z)
• Reducing Barriers to the Use of Marginalised Music Genres in AI [7.140590440016289]
  This project aims to explore the eXplainable AI (XAI) challenges and opportunities associated with reducing barriers to using marginalised genres of music with AI models. XAI opportunities identified included topics of improving transparency and control of AI models, explaining the ethics and bias of AI models, fine tuning large models with small datasets to reduce bias, and explaining style-transfer opportunities with AI models. We are now building on this project to bring together a global International Responsible AI Music community and invite people to join our network.
  arXiv  Detail & Related papers  (2024-07-18T12:10:04Z)
• MuPT: A Generative Symbolic Music Pretrained Transformer [56.09299510129221]
  We explore the application of Large Language Models (LLMs) to the pre-training of music. To address the challenges associated with misaligned measures from different tracks during generation, we propose a Synchronized Multi-Track ABC Notation (SMT-ABC Notation) Our contributions include a series of models capable of handling up to 8192 tokens, covering 90% of the symbolic music data in our training set.
  arXiv  Detail & Related papers  (2024-04-09T15:35:52Z)
• Analyzing Musical Characteristics of National Anthems in Relation to Global Indices [0.0]
  We analyze national anthem musical data to determine whether certain musical characteristics are associated with peace, happiness, suicide rate, crime rate, etc. Our findings indicate that there may be a correlation between the musical characteristics of national anthems and the indices we investigated.
  arXiv  Detail & Related papers  (2024-04-04T17:25:31Z)
• Can MusicGen Create Training Data for MIR Tasks? [3.8980564330208662]
  We are investigating the broader concept of using AI-based generative music systems to generate training data for Music Information Retrieval tasks. We constructed over 50 000 genre- conditioned textual descriptions and generated a collection of music excerpts that covers five musical genres. Preliminary results show that the proposed model can learn genre-specific characteristics from artificial music tracks that generalise well to real-world music recordings.
  arXiv  Detail & Related papers  (2023-11-15T16:41:56Z)
• MARBLE: Music Audio Representation Benchmark for Universal Evaluation [79.25065218663458]
  We introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 14 tasks on 8 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines.
  arXiv  Detail & Related papers  (2023-06-18T12:56:46Z)
• Universality of preference behaviors in online music-listener bipartite networks: A Big Data analysis [4.062544367625752]
  We investigate the formation of musical preferences of millions of users of the NetEase Cloud Music (NCM), one of the largest online music platforms in China. Our analyses address the decay patterns of music influence, users' sensitivity to music, age and gender differences, and their relationship to regional economic indicators.
  arXiv  Detail & Related papers  (2022-12-26T12:50:56Z)
• A Dataset for Greek Traditional and Folk Music: Lyra [69.07390994897443]
  This paper presents a dataset for Greek Traditional and Folk music that includes 1570 pieces, summing in around 80 hours of data. The dataset incorporates YouTube timestamped links for retrieving audio and video, along with rich metadata information with regards to instrumentation, geography and genre.
  arXiv  Detail & Related papers  (2022-11-21T14:15:43Z)
• A Review of Intelligent Music Generation Systems [4.287960539882345]
  ChatGPT has significantly reduced the barrier to entry for non-professionals in creative endeavors. Modern generative algorithms can extract patterns implicit in a piece of music based on rule constraints or a musical corpus.
  arXiv  Detail & Related papers  (2022-11-16T13:43:16Z)
• Artificial Musical Intelligence: A Survey [51.477064918121336]
  Music has become an increasingly prevalent domain of machine learning and artificial intelligence research. This article provides a definition of musical intelligence, introduces a taxonomy of its constituent components, and surveys the wide range of AI methods that can be, and have been, brought to bear in its pursuit.
  arXiv  Detail & Related papers  (2020-06-17T04:46:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.