A Data-Driven Analysis of Robust Automatic Piano Transcription
This addresses robustness issues in piano transcription for music technology applications, but is incremental as it builds on existing datasets and methods.
The study tackled overfitting in automatic piano transcription by analyzing training data and using data augmentation on re-performed MAESTRO dataset, achieving state-of-the-art note-onset accuracy of 88.4 F1-score on MAPS dataset without its training data.
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.