paper-with-me

Music Modeling

2개 벤치마크 · 논문 38편 · 이 태스크의 논문 보기 →

Benchmarks

JSB Chorales

결과 10개

Nottingham

결과 8개

Most implemented

LSTM: A Search Space Odyssey

2015-03-13 · 구현 17개

Music Transformer

2018-09-12 · 구현 12개

Counterpoint by Convolution

2019-03-18 · 구현 4개

Papers

Exploring LLMs for South Asian Music Understanding and Generation

2026-06-03 · Faria Binte Kader, Mohtasim Hadi Rafi, Shah Wasif Sajjad, Santu Karmaker arxiv

Recent advancements in Large Language Models (LLMs) have shown promising results in music understanding and generation tasks. However, existing works remain confined to Western tonal traditions, offering little insight i…

Music GenerationMusic Modeling

Depth-Structured Music Recurrence: Budgeted Recurrent Attention for Full-Piece Symbolic Music Modeling

2026-02-23 · Yungang Yi, Weihua Li, Matthew Kuo, Catherine Shi 외 arxiv

Long-context modeling is essential for symbolic music generation, since motif repetition and developmental variation can span thousands of musical events, yet practical workflows frequently rely on resource-limited hardw…

Music GenerationMusic Modeling

Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training

2025-12-02 · Hong-Jie You, Jie-Jing Shao, Xiao-Wen Yang, Lin-Han Jia 외 arxiv

Existing methods for expressive music performance rendering, a conditional generation task that aims to generate a human-like performance from a symbolic score, rely on supervised learning over small labeled datasets, wh…

Self-Supervised LearningMusic Modeling

HNote: Extending YNote with Hexadecimal Encoding for Fine-Tuning LLMs in Music Modeling

2025-09-30 · Hung-Ying Chu, Shao-Yu Wei, Guan-Wei Chen, Tzu-Wei Hung 외 arxiv

Recent advances in large language models (LLMs) have created new opportunities for symbolic music generation. However, existing formats such as MIDI, ABC, and MusicXML are either overly complex or structurally inconsiste…

Music GenerationMusic Modeling

SLEEPING-DISCO 9M: A large-scale pre-training dataset for generative music modeling

2025-06-17 · Tawsif Ahmed, Andrej Radonjic, Gollam Rabby

We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song. To the best of our knowledge, there are no open-source high-quality dataset representing popular and well-known songs for generative mu…

Music CaptioningMusic ModelingSinging Voice Synthesis

Frechet Music Distance: A Metric For Generative Symbolic Music Evaluation

2024-12-10 · Jan Retkowski, Jakub Stępniak, Mateusz Modrzejewski

In this paper we introduce the Frechet Music Distance (FMD), a novel evaluation metric for generative symbolic music models, inspired by the Frechet Inception Distance (FID) in computer vision and Frechet Audio Distance …

FADMusic GenerationMusic Modeling

전체 38편 보기 →