Real-Time Automatic Drum Transcription Using Dynamic Few-Shot Learning
Philipp Weber, Christian Uhle, Meinard Müller, Matthias Lang · 2024
This paper proposes the application of dynamic few-shot learning for automatic drum transcription (ADT). The contributions of this work are threefold. First, we adapt dynamic few-shot learning to improve the classification of superimposed events. Secondly, we introduce a novel method for generating training data for ADT. Thirdly, we demonstrate how our model can be applied in real-time without strongly deteriorating the classification performance. We evaluate transcription performance in the presence of melodic instruments for 10 drum classes on three publicly available test datasets and achieve state-of-the-art performance. We show that new drum classes can be learned and performance for known classes can be improved by providing some examples of that respective class during test time.