Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model
Abstract
Automated singing assessment is crucial for education and entertainment. However, existing systems face two fundamental limitations: reliance on reference tracks, which stifles creative expression, and the simplification of complex performances into non-diagnostic scores based solely on pitch and rhythm. We advocate for a shift from discriminative to descriptive evaluation, creating a complete ecosystem for reference-free, multi-dimensional assessment. First, we introduce Sing-MD, a large-scale dataset annotated by experts across four dimensions: breath control, timbre quality, emotional expression, and vocal technique. Our analysis reveals significant annotation inconsistencies among experts, challenging the validity of traditional accuracy-based metrics. Second, addressing the memory limitations of Multimodal Large Language Models (MLLMs) in analyzing full-length songs, we propose VocalVerse. This efficient hybrid architecture leverages a lightweight acoustic encoder to model global performance features and long-term dependencies. Third, to address automated metric shortcomings, we establish the H-TPR (Human-in-the-loop Tiered Perceptual Ranking) benchmark, which evaluates a model's ability to generate perceptually valid rankings rather than predicting noisy ground-truth scores.
Cite
@article{arxiv.2512.06999,
title = {Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model},
author = {Zihao Wang and Ruibin Yuan and Ziqi Geng and Hengjia Li and Xingwei Qu and Xinyi Li and Songye Chen and Haoying Fu and Roger B. Dannenberg and Kejun Zhang},
journal= {arXiv preprint arXiv:2512.06999},
year = {2025}
}
Comments
Accepted to ACMMM 2025 oral