# Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music

arXiv: https://arxiv.org/abs/2605.14765 · HTML: https://mlsanity.com/paper/2605.14765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 14 of 14)

- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [FMA: A Dataset For Music Analysis](https://mlsanity.com/paper/1612.01840/) (2016)
- [Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity](https://mlsanity.com/paper/1909.08494/) (2019)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [MARBLE: Music Audio Representation Benchmark for Universal Evaluation](https://mlsanity.com/paper/2306.10548/) (2023)
- [Music Source Separation with Band-Split RoPE Transformer](https://mlsanity.com/paper/2309.02612/) (2023)
- [Mel-Band RoFormer for Music Source Separation](https://mlsanity.com/paper/2310.01809/) (2023)
- [XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework](https://mlsanity.com/paper/2501.08809/) (2025)
- [Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models](https://mlsanity.com/paper/2502.07328/) (2025)
- [The Persian Piano Corpus: A Collection Of Instrument-Based Feature Extracted Data Considering Dastgah](https://mlsanity.com/paper/2311.11074/) (2023)
- [The IRMA Dataset: A Structured Audio-MIDI Corpus for Iranian Classical Music](https://mlsanity.com/paper/2508.19876/) (2025)
- [Persian Musical Instruments Classification Using Polyphonic Data Augmentation](https://mlsanity.com/paper/2511.05717/) (2025)
- [Radif Corpus: A Symbolic Dataset for Non-Metric Iranian Classical Music](https://mlsanity.com/paper/2507.10456/) (2025)

## Abstract (arXiv)

Persian music, with its unique tonalities, modal systems (Dastgah), and rhythmic structures, presents significant challenges for music generation models trained primarily on Western music. We address this gap by curating the first large-scale dataset of Persian songs, comprising over 900 hours high-quality audio samples across diverse sub-genres, including pop, traditional, and contemporary styles. This dataset captures the rich melodic and cultural diversity of Persian music and serves as the foundation for fine-tuning MusicGen, a state-of-the-art generative music model. We adapt MusicGen to this domain and evaluate its performance by utilizing subjective and objective metrics. To assess the semantic alignment between generated music and intended style tags, we report the proportion of relevant tags accurately reflected in the generated outputs. Our results demonstrate that the fine-tuned model produces compositions that more align with Persian stylistic conventions. This work introduces a new resource for generative music research and illustrates the adaptability of music generation models to underrepresented cultural and linguistic contexts.