Saved in:
Bibliographic Details
Main Authors: Zhang, Huan, Liang, Jinhua, Dixon, Simon
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.04518
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909262308966400
author Zhang, Huan
Liang, Jinhua
Dixon, Simon
author_facet Zhang, Huan
Liang, Jinhua
Dixon, Simon
contents Our study investigates an approach for understanding musical performances through the lens of audio encoding models, focusing on the domain of solo Western classical piano music. Compared to composition-level attribute understanding such as key or genre, we identify a knowledge gap in performance-level music understanding, and address three critical tasks: expertise ranking, difficulty estimation, and piano technique detection, introducing a comprehensive Pianism-Labelling Dataset (PLD) for this purpose. We leverage pre-trained audio encoders, specifically Jukebox, Audio-MAE, MERT, and DAC, demonstrating varied capabilities in tackling downstream tasks, to explore whether domain-specific fine-tuning enhances capability in capturing performance nuances. Our best approach achieved 93.6\% accuracy in expertise ranking, 33.7\% in difficulty estimation, and 46.7\% in technique detection, with Audio-MAE as the overall most effective encoder. Finally, we conducted a case study on Chopin Piano Competition data using trained models for expertise ranking, which highlights the challenge of accurately assessing top-tier performances.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04518
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano
Zhang, Huan
Liang, Jinhua
Dixon, Simon
Audio and Speech Processing
Our study investigates an approach for understanding musical performances through the lens of audio encoding models, focusing on the domain of solo Western classical piano music. Compared to composition-level attribute understanding such as key or genre, we identify a knowledge gap in performance-level music understanding, and address three critical tasks: expertise ranking, difficulty estimation, and piano technique detection, introducing a comprehensive Pianism-Labelling Dataset (PLD) for this purpose. We leverage pre-trained audio encoders, specifically Jukebox, Audio-MAE, MERT, and DAC, demonstrating varied capabilities in tackling downstream tasks, to explore whether domain-specific fine-tuning enhances capability in capturing performance nuances. Our best approach achieved 93.6\% accuracy in expertise ranking, 33.7\% in difficulty estimation, and 46.7\% in technique detection, with Audio-MAE as the overall most effective encoder. Finally, we conducted a case study on Chopin Piano Competition data using trained models for expertise ranking, which highlights the challenge of accurately assessing top-tier performances.
title From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano
topic Audio and Speech Processing
url https://arxiv.org/abs/2407.04518