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

TL;DR

This paper introduces NanyinHGNN, a novel graph neural network model that preserves and generates Nanyin music by leveraging a specialized dataset, tokenization, and domain-informed refinement, addressing challenges in cultural heritage preservation.

Contribution

It presents a new heterogeneous graph-based approach for Nanyin music generation, incorporating domain knowledge and a Pipa-centric dataset to improve authenticity and preservation.

Findings

Successfully generates authentic heterophonic Nanyin ensembles

Demonstrates effectiveness of domain-specific graph modeling in ethnomusicology

Mitigates data scarcity through domain-informed architecture

Abstract

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.