# Revisiting the Onsets and Frames Model with Additive Attention

arXiv: https://arxiv.org/abs/2104.06607 · HTML: https://mlsanity.com/paper/2104.06607/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2021.

## Built on by (most cited first, 9 of 9)

- [HEAR: Holistic Evaluation of Audio Representations](https://mlsanity.com/paper/2203.03022/) (2022)
- [ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data](https://mlsanity.com/paper/2107.04954/) (2021)
- [DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability](https://mlsanity.com/paper/2210.05148/) (2022)
- [Jointist: Joint Learning for Multi-instrument Transcription and Its Applications](https://mlsanity.com/paper/2206.10805/) (2022)
- [Music Foundation Model as Generic Booster for Music Downstream Tasks](https://mlsanity.com/paper/2411.01135/) (2024)
- [AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios](https://mlsanity.com/paper/2302.10184/) (2023)
- [Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond](https://mlsanity.com/paper/2304.05032/) (2023)
- [Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training](https://mlsanity.com/paper/2302.00286/) (2023)
- [Deep-Learning Architectures for Multi-Pitch Estimation: Towards Reliable Evaluation](https://mlsanity.com/paper/2202.09198/) (2022)

## Abstract (arXiv)

Recent advances in automatic music transcription (AMT) have achieved highly accurate polyphonic piano transcription results by incorporating onset and offset detection. The existing literature, however, focuses mainly on the leverage of deep and complex models to achieve state-of-the-art (SOTA) accuracy, without understanding model behaviour. In this paper, we conduct a comprehensive examination of the Onsets-and-Frames AMT model, and pinpoint the essential components contributing to a strong AMT performance. This is achieved through exploitation of a modified additive attention mechanism. The experimental results suggest that the attention mechanism beyond a moderate temporal context does not benefit the model, and that rule-based post-processing is largely responsible for the SOTA performance. We also demonstrate that the onsets are the most significant attentive feature regardless of model complexity. The findings encourage AMT research to weigh more on both a robust onset detector and an effective post-processor.