Deep Unsupervised Drum Transcription
This addresses the need for scalable drum transcription tools in music processing by eliminating the reliance on labeled data, though it is incremental as it builds on existing unsupervised and deep learning approaches.
The authors tackled the problem of drum transcription without requiring ground-truth labels by introducing DrummerNet, an unsupervised system that learns from large unlabeled datasets and reconstructs audio to train the transcriber, achieving favorable performance compared to recent supervised and unsupervised methods.
We introduce DrummerNet, a drum transcription system that is trained in an unsupervised manner. DrummerNet does not require any ground-truth transcription and, with the data-scalability of deep neural networks, learns from a large unlabeled dataset. In DrummerNet, the target drum signal is first passed to a (trainable) transcriber, then reconstructed in a (fixed) synthesizer according to the transcription estimate. By training the system to minimize the distance between the input and the output audio signals, the transcriber learns to transcribe without ground truth transcription. Our experiment shows that DrummerNet performs favorably compared to many other recent drum transcription systems, both supervised and unsupervised.