A Data-Driven Analysis of Robust Automatic Piano Transcription
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916112809066496 |
|---|---|
| author | Edwards, Drew Dixon, Simon Benetos, Emmanouil Maezawa, Akira Kusaka, Yuta |
| author_facet | Edwards, Drew Dixon, Simon Benetos, Emmanouil Maezawa, Akira Kusaka, Yuta |
| contents | Algorithms for automatic piano transcription have improved dramatically in recent years due to new datasets and modeling techniques. Recent developments have focused primarily on adapting new neural network architectures, such as the Transformer and Perceiver, in order to yield more accurate systems. In this work, we study transcription systems from the perspective of their training data. By measuring their performance on out-of-distribution annotated piano data, we show how these models can severely overfit to acoustic properties of the training data. We create a new set of audio for the MAESTRO dataset, captured automatically in a professional studio recording environment via Yamaha Disklavier playback. Using various data augmentation techniques when training with the original and re-performed versions of the MAESTRO dataset, we achieve state-of-the-art note-onset accuracy of 88.4 F1-score on the MAPS dataset, without seeing any of its training data. We subsequently analyze these data augmentation techniques in a series of ablation studies to better understand their influence on the resulting models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01424 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Data-Driven Analysis of Robust Automatic Piano Transcription Edwards, Drew Dixon, Simon Benetos, Emmanouil Maezawa, Akira Kusaka, Yuta Sound Machine Learning Audio and Speech Processing Algorithms for automatic piano transcription have improved dramatically in recent years due to new datasets and modeling techniques. Recent developments have focused primarily on adapting new neural network architectures, such as the Transformer and Perceiver, in order to yield more accurate systems. In this work, we study transcription systems from the perspective of their training data. By measuring their performance on out-of-distribution annotated piano data, we show how these models can severely overfit to acoustic properties of the training data. We create a new set of audio for the MAESTRO dataset, captured automatically in a professional studio recording environment via Yamaha Disklavier playback. Using various data augmentation techniques when training with the original and re-performed versions of the MAESTRO dataset, we achieve state-of-the-art note-onset accuracy of 88.4 F1-score on the MAPS dataset, without seeing any of its training data. We subsequently analyze these data augmentation techniques in a series of ablation studies to better understand their influence on the resulting models. |
| title | A Data-Driven Analysis of Robust Automatic Piano Transcription |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.01424 |