Adversarial Learning For Improved Onsets And Frames Music Transcription

Abstract

Automatic music transcription is considered to be one of the hardest problems in music information retrieval, yet recent deep learning approaches have achieved substantial improvements on transcription performance. These approaches commonly employ supervised learning models that predict various time-frequency representations, by minimizing element-wise losses such as the cross entropy function. However, applying the loss in this manner assumes conditional independence of each label given the input, and thus cannot accurately express inter-label dependencies. To address this issue, we introduce an adversarial training scheme that operates directly on the time-frequency representations and makes the output distribution closer to the ground-truth. Through adversarial learning, we achieve a consistent improvement in both frame-level and note-level metrics over Onsets and Frames, a state-of-the-art music transcription model. Our results show that adversarial learning can significantly reduc

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykim2019adversarial

Related papers

• Annotation-free Automatic Music Transcription With Scalable Synthetic Data And Adversarial Domain Confusion (2023)4.52
• Invariances And Data Augmentation For Supervised Music Transcription (2017)11.08
• Audio-to-score Alignment Of Piano Music Using Rnn-based Automatic Music Transcription (2017)0.00
• Reconvat: A Semi-supervised Automatic Music Transcription Framework For Low-resource Real-world Data (2021)10.85
• Towards Efficient And Real-time Piano Transcription Using Neural Autoregressive Models (2024)5.84
• Piano Transcription By Hierarchical Language Modeling With Pretrained Roll-based Encoders (2025)4.52
• Targeted Adversarial Examples For Black Box Audio Systems (2018)15.75
• Learning Style-aware Symbolic Music Representations By Adversarial Autoencoders (2020)2.26