CFMT: A Music Transcription Model using Conformer Architecture

Authors: Yulong Wang, Department of Software Engineering, Nankai University, China, 2120220692@mail.nankai.edu.cn Hailong Yu, Department of Software Engineering, Nankai University, China, 2120220695@mail.nankai.edu.cn Fengchi Sun, Department of Software Engineering, Nankai University, China, fengchisun@nankai.edu.cn Jianyu Zhou, Department of Software Engineering, Nankai University, China, jyzhou@nankai.edu.cn

Conference: ICIC 2024 Posters, Tianjin, China, August 5-8, 2024

Pages: 412-427

Keywords: Automatic music transcription, Conformer, Note events

DOI: 10.65286/icic.v20i2.47835

Abstract

Automatic music transcription is a fundamental process for converting audio recordings of musical compositions into symbolic representations. This study extends the current state of the art in automatic music transcription with a specific focus on leveraging conformer models, known for their
exceptional performance in speech recognition. Furthermore, this research introduces an innovative approach designed to address the longstanding challenge of missing note-end events, which has previously hindered the accurate
evaluation of Seq2Seq models using frame-wise metrics. Empirical findings
reveal that a slightly modified Conformer model surpasses existing models
across a spectrum of evaluation metrics, even outperforming models trained
on distinct iterations of the MAESTRO dataset. Notably, this research contributes
to the enhancement of frame-wise evaluation metrics for Seq2Seq models by
providing estimations of possible note lengths for ongoing musical notes, resulting in a substantial improvement in evaluation accuracy

BibTeX Citation:

@inproceedings{ICIC2024,
    author = {Yulong Wang, Department of Software Engineering, Nankai University, China, 2120220692@mail.nankai.edu.cn Hailong Yu, Department of Software Engineering, Nankai University, China, 2120220695@mail.nankai.edu.cn Fengchi Sun, Department of Software Engineering, Nankai University, China, fengchisun@nankai.edu.cn Jianyu Zhou, Department of Software Engineering, Nankai University, China, jyzhou@nankai.edu.cn},
    title = {CFMT: A Music Transcription Model using Conformer Architecture},
    booktitle = {Proceedings of the 20th International Conference on Intelligent Computing (ICIC 2024)},
    month = {August},
    date = {5-8},
    year = {2024},
    address = {Tianjin, China},
    pages = {412-427},
    note = {Poster Volume Ⅱ}
    doi = {10.65286/icic.v20i2.47835}
}