towards automatic transcription of polyphonic electric guitar music:a new dataset and a multi-loss transformer model
This work addresses transcription for electric guitar music, which is incremental as it builds on existing piano transcription models with a new dataset and method.
The authors tackled the problem of automatic transcription of polyphonic electric guitar music by introducing a new dataset (EGDB) and a multi-loss Transformer model, achieving results that demonstrate the influence of timbre on accuracy and the potential of multiple losses, though with room for improvement.
In this paper, we propose a new dataset named EGDB, that con-tains transcriptions of the electric guitar performance of 240 tab-latures rendered with different tones. Moreover, we benchmark theperformance of two well-known transcription models proposed orig-inally for the piano on this dataset, along with a multi-loss Trans-former model that we newly propose. Our evaluation on this datasetand a separate set of real-world recordings demonstrate the influenceof timbre on the accuracy of guitar sheet transcription, the potentialof using multiple losses for Transformers, as well as the room forfurther improvement for this task.