Oral Tradition-Encoded NanyinHGNN: Integrating Nanyin Music Preservation and Generation through a Pipa-Centric Dataset

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiahou, Jianbing, Zhai, Weixi, Cui, Xu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917050999373824
author Xiahou, Jianbing
Zhai, Weixi
Cui, Xu
author_facet Xiahou, Jianbing
Zhai, Weixi
Cui, Xu
contents We propose NanyinHGNN, a heterogeneous graph network model for generating Nanyin instrumental music. As a UNESCO-recognized intangible cultural heritage, Nanyin follows a heterophonic tradition centered around the pipa, where core melodies are notated in traditional notation while ornamentations are passed down orally, presenting challenges for both preservation and contemporary innovation. To address this, we construct a Pipa-Centric MIDI dataset, develop NanyinTok as a specialized tokenization method, and convert symbolic sequences into graph structures using a Graph Converter to ensure that key musical features are preserved. Our key innovation reformulates ornamentation generation as the creation of ornamentation nodes within a heterogeneous graph. First, a graph neural network generates melodic outlines optimized for ornamentations. Then, a rule-guided system informed by Nanyin performance practices refines these outlines into complete ornamentations without requiring explicit ornamentation annotations during training. Experimental results demonstrate that our model successfully generates authentic heterophonic ensembles featuring four traditional instruments. These findings validate that integrating domain-specific knowledge into model architecture can effectively mitigate data scarcity challenges in computational ethnomusicology.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26817
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Oral Tradition-Encoded NanyinHGNN: Integrating Nanyin Music Preservation and Generation through a Pipa-Centric Dataset
Xiahou, Jianbing
Zhai, Weixi
Cui, Xu
Sound
Audio and Speech Processing
We propose NanyinHGNN, a heterogeneous graph network model for generating Nanyin instrumental music. As a UNESCO-recognized intangible cultural heritage, Nanyin follows a heterophonic tradition centered around the pipa, where core melodies are notated in traditional notation while ornamentations are passed down orally, presenting challenges for both preservation and contemporary innovation. To address this, we construct a Pipa-Centric MIDI dataset, develop NanyinTok as a specialized tokenization method, and convert symbolic sequences into graph structures using a Graph Converter to ensure that key musical features are preserved. Our key innovation reformulates ornamentation generation as the creation of ornamentation nodes within a heterogeneous graph. First, a graph neural network generates melodic outlines optimized for ornamentations. Then, a rule-guided system informed by Nanyin performance practices refines these outlines into complete ornamentations without requiring explicit ornamentation annotations during training. Experimental results demonstrate that our model successfully generates authentic heterophonic ensembles featuring four traditional instruments. These findings validate that integrating domain-specific knowledge into model architecture can effectively mitigate data scarcity challenges in computational ethnomusicology.
title Oral Tradition-Encoded NanyinHGNN: Integrating Nanyin Music Preservation and Generation through a Pipa-Centric Dataset
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2510.26817