A Study of Audio Mixing Methods for Piano Transcription in Violin-Piano Ensembles

While piano music transcription models have shown high performance for solo piano recordings, their performance de-grades when applied to ensemble recordings. This study aims to analyze the impact of different data augmentation methods on piano transcription performance, specifically focusing on mix...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1 - 5
Main Authors Kim, Hyemi, Park, Jiyun, Kwon, Taegyun, Jeong, Dasaem, Nam, Juhan
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.06.2023
Subjects
Acoustics
dataset
Focusing
Harmonic analysis
mixing audios
Piano transcription
Rendering (computer graphics)
Speech processing
violin-piano ensemble
Online AccessGet full text

Cover

More Information
Summary:While piano music transcription models have shown high performance for solo piano recordings, their performance de-grades when applied to ensemble recordings. This study aims to analyze the impact of different data augmentation methods on piano transcription performance, specifically focusing on mixing techniques applied to violin-piano ensembles. We apply mixing methods that consider both harmonic and temporal characteristics of the audio. To create datasets for this study, we generated the PFVN-synth dataset, which contains 7 hours of violin-piano ensemble audio by rendering MIDI files and corresponding labels, and also collected unaccompanied violin recordings and mixed them with the MAESTRO dataset. We evaluated the transcription results on both synthesized and real audio recordings datasets.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10095061