Onsets and Frames: Dual-Objective Piano Transcription

Abstract

We advance the state of the art in polyphonic piano music transcription by using a deep convolutional and recurrent neural network which is trained to jointly predict onsets and frames. Our model predicts pitch onset events and then uses those predictions to condition framewise pitch predictions. During inference, we restrict the predictions from the framewise detector by not allowing a new note to start unless the onset detector also agrees that an onset for that pitch is present in the frame. We focus on improving onsets and offsets together instead of either in isolation as we believe this correlates better with human musical perception. Our approach results in over a 100% relative improvement in note F1 score (with offsets) on the MAPS dataset. Furthermore, we extend the model to predict relative velocities of normalized audio which results in more natural-sounding transcriptions.

arXiv commentExamples available at https://goo.gl/magenta/onsets-frames-examples

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• WaveNet: A Generative Model for Raw Audio
• Learning Features of Music from Scratch
• On the Potential of Simple Framewise Approaches to Piano Transcription

Cited by in corpus (6)

• Audeo: Audio Generation for a Silent Performance Video
• MT3: Multi-Task Multitrack Music Transcription
• Data-driven Design: A Case for Maximalist Game Design
• A Hybrid Approach to Audio-to-Score Alignment
• Modeling Musical Onset Probabilities via Neural Distribution Learning
• Real-time error correction and performance aid for MIDI instruments