A Data-Driven Methodology for Considering Feasibility and Pairwise Likelihood in Deep Learning Based Guitar Tablature Transcription Systems
This addresses the understudied issue of guitar tablature transcription for music information retrieval, offering a method to enhance model predictions using widely available symbolic data, but it is incremental as it builds on existing models.
The paper tackled the problem of guitar tablature transcription by using symbolic tablature data to estimate pairwise note likelihoods and incorporating an inhibition loss into a baseline model, resulting in more playable and consistent transcriptions with improved performance, though no concrete numbers were provided.
Guitar tablature transcription is an important but understudied problem within the field of music information retrieval. Traditional signal processing approaches offer only limited performance on the task, and there is little acoustic data with transcription labels for training machine learning models. However, guitar transcription labels alone are more widely available in the form of tablature, which is commonly shared among guitarists online. In this work, a collection of symbolic tablature is leveraged to estimate the pairwise likelihood of notes on the guitar. The output layer of a baseline tablature transcription model is reformulated, such that an inhibition loss can be incorporated to discourage the co-activation of unlikely note pairs. This naturally enforces playability constraints for guitar, and yields tablature which is more consistent with the symbolic data used to estimate pairwise likelihoods. With this methodology, we show that symbolic tablature can be used to shape the distribution of a tablature transcription model's predictions, even when little acoustic data is available.