Towards Generalizability to Tone and Content Variations in the Transcription of Amplifier Rendered Electric Guitar Audio

Electric guitar recordings pose unique challenges for automatic music transcription due to the rich tone-related variations arisen from the employed guitar amplifiers, cabinets, and effect pedals, which collectively alter the sound character the guitar produces. Transcription models trained on small datasets with a limited palette of guitar tones may not generalize well to unseen tones. Due to the scarcity of labeled data, however, little work has thoroughly studied the effect of tones in electric guitar transcription. In this paper, we present a prototype benchmark and evaluation protocol for electric guitar transcription, training our transcription models using up to 256 presets of commercial-grade amplifier-cabinet combinations with different gain ranges, and testing the models on an unseen set of 6 out-of-domain presets. Moreover, we propose a new Transformer-based transcription model named tone-informed hierarchy Transformer (Ti-hFT) that incorporates representations of guitar tones as conditions to improve the model's adaptability to tone-related nuances. Experiments demonstrate the effectiveness of this tone-informed model over baselines and prior models, as well as the importance of increasing the tone and content variation of the training data for better generalizability.