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

2025-04-10

AI Summary

Electric guitar audio transcription faces two key challenges: (1) the scarcity of diverse datasets covering multiple amplifier–cabinet configurations, and (2) strong nonlinear distortions introduced by the tone chain (amplifier, speaker cabinet, effects pedals), which are tightly coupled with playing content. To address these, we propose Tone-aware Transformer (TIT), featuring three core contributions: (1) EGDB-PG—the first publicly available dataset for generalized transcription, encompassing 12 mainstream amplifier–cabinet combinations; (2) a learnable tone embedding module that explicitly models timbral characteristics and disentangles them from note-level content; and (3) joint tone/content enhancement alongside audio normalization. Ablation studies and cross-amplifier benchmarking demonstrate TIT’s superior generalization: it achieves a 9.2% average accuracy gain over state-of-the-art models under multi-tone settings.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Natural Language Processing: Generation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Transcribing electric guitar recordings is challenging due to the scarcity of diverse datasets and the complex tone-related variations introduced by amplifiers, cabinets, and effect pedals. To address these issues, we introduce EGDB-PG, a novel dataset designed to capture a wide range of tone-related characteristics across various amplifier-cabinet configurations. In addition, we propose the Tone-informed Transformer (TIT), a Transformer-based transcription model enhanced with a tone embedding mechanism that leverages learned representations to improve the model's adaptability to tone-related nuances. Experiments demonstrate that TIT, trained on EGDB-PG, outperforms existing baselines across diverse amplifier types, with transcription accuracy improvements driven by the dataset's diversity and the tone embedding technique. Through detailed benchmarking and ablation studies, we evaluate the impact of tone augmentation, content augmentation, audio normalization, and tone embedding on transcription performance. This work advances electric guitar transcription by overcoming limitations in dataset diversity and tone modeling, providing a robust foundation for future research.

Problem

• Addressing electric guitar transcription challenges from tone variations
• Introducing EGDB-PG dataset for diverse amplifier-cabinet configurations
• Proposing Tone-informed Transformer for improved tone adaptability

Innovation

• Introduces EGDB-PG dataset for diverse tone variations
• Proposes Tone-informed Transformer with tone embeddings
• Combines dataset diversity and tone modeling enhancements