paper-with-me

홈 › Papers

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

2026-05-14 · Mohammad Hossein Sameti, Diba Hadi Esfangereh, Sepehr Harfi Moridani, Leili Javidpour, Mahdieh Soleymani Baghshah 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.

📄 PDF Abstract BibTeX arXiv:2605.14765

Code (0)

등록된 구현이 없습니다.

Tasks

Music Generation

Similar Papers 제목 키워드 기반

Persian Musical Instruments Classification Using Polyphonic Data Augmentation

2025-11-07 · Diba Hadi Esfangereh, Mohammad Hossein Sameti, Sepehr Harfi Moridani, Leili Javidpour 외 arxiv

Musical instrument classification is essential for music information retrieval (MIR) and generative music systems. However, research on non-Western traditions, particularly Persian music, remains limited. We address this…

Instrument RecognitionInformation RetrievalData AugmentationMusic Generation

ELAB: Extensive LLM Alignment Benchmark in Persian Language

2025-04-17 · Zahra Pourbahman, Fatemeh Rajabi, Mohammadhossein Sadeghi, Omid Ghahroodi 외

This paper presents a comprehensive evaluation framework for aligning Persian Large Language Models (LLMs) with critical ethical dimensions, including safety, fairness, and social norms. It addresses the gaps in existing…

FairnessRed Teaming

PersianMedQA: Language-Centric Evaluation of LLMs in the Persian Medical Domain

2025-05-30 · Mohammad Javad Ranjbar Kalahroodi, Amirhossein Sheikholselami, Sepehr Karimi, Sepideh Ranjbar Kalahroodi 외

Large Language Models (LLMs) have achieved remarkable performance on a wide range of NLP benchmarks, often surpassing human-level accuracy. However, their reliability in high-stakes domains such as medicine, particularly…

Instruction FollowingMultiple-choice

PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark

2026-03-15 · Mohammad Javad Ranjbar Kalahroodi, Mohammad Amini, Parmis Bathayan, Heshaam Faili 외 arxiv

Persian poses unique audio understanding challenges through its classical poetry, traditional music, and pervasive code-switching - none captured by existing benchmarks. We introduce PARSA-Bench (Persian Audio Reasoning …

We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

2025-09-01 · Nikta Gohari Sadr, Sahar Heidariasl, Karine Megerdoomian, Laleh Seyyed-Kalantari 외 arxiv

Large language models (LLMs) struggle to navigate culturally specific communication norms, limiting their effectiveness in global contexts. We focus on Persian taarof, a social norm in Iranian interactions, which is a so…