Skip to content
Preprint

Harmonica: Accurate and Lightweight Instrument-Agnostic Music Transcription

Sep 2026 · 0 citations · 34 references
Computer Science

TL;DR

Harmonica, a family of instrument-agnostic music transcription models built around multi-depth harmonic convolution, achieves the best performance among the evaluated models: the x-large model attains state-of-the-art performance in instrument-agnostic transcription, while the medium variant offers competitive accuracy with faster inference than all baselines.

Abstract

This paper introduces Harmonica, a family of instrument-agnostic music transcription models built around multi-depth harmonic convolution. At each model scale, Harmonica achieves the best performance among the evaluated models: the x-large model attains state-of-the-art performance in instrument-agnostic transcription, while the medium variant offers competitive accuracy with faster inference than all baselines. Pushing the limit of computational efficiency, the nano variant has only 26.3K parameters and runs at 1,622.5 times real time, yet achieves a frame F1 of 0.796 on the development set, 14.6 percentage points higher than Basic Pitch. We further demonstrate that multi-depth harmonic convolution effectively exploits harmonic information to benefit transcription performance through comparative experiments with existing harmonic aggregation methods, including harmonic stacking, harmonic attention, single-depth harmonic convolution, and the HD-Conv layer.

View source

Similar papers

#graph neural networks Open access Sep 2026

Multi-instrument music score transcription, symbolic generation, and harmony analysis based on multi-scale residual neural networks

The results demonstrate that the contribution lies in music-specific cross-module coupling and constrained symbolic reconstruction rather than in introducing residual, graph, recurrent, or dilated convolution as isolated operators.

Huai-Shun Ou, Yang-Nan Yang, Yun-Yao Wang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Hi-Singers: A Comprehensive High-Quality Dataset for Expressive Audio-Driven Singing Head Synthesis

State-of-the-art models for audio-driven digital human generation have achieved photo-realistic results in talking-head synthesis. However, extending these models to singing-head synthesis remains challenging due to a significant Domain Gap: singing requires more exaggerated expressions, vivid jaw openings, and precise...

Yi-Chi Zhang, Hui Zhang, Guan-Jun Liu et al. · 0 citations
Preprint Oct 2026

Phase-Based Onset Enhancement for Piano Transcription in Ensemble Settings

Piano transcription models have achieved very high performance in recent state-of-the-art systems, but their performance tends to degrade in ensemble settings where the piano is played alongside other instruments. While some approaches attempt to address this issue by incorporating multi-instrumental datasets, the prob...

Hyemi Kim, Jiyun Park, Juhan Nam · 0 citations
Preprint Sep 2026

StepAudio 3 Music Technical Report

This work introduces StepAudio 3 Music, a large-scale, long-form music generation model that supports explicit musical planning and open-domain text-controlled generation, and achieves the highest AudioBox Content Enjoyment, Content Usefulness, and Production Quality scores and the highest MuQ-MuLan similarity among th...

Chengli Feng, Zhi-Yue Wu, Jia-Hao Song et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.