# Exploring System Adaptations For Minimum Latency Real-Time Piano Transcription

arXiv: https://arxiv.org/abs/2509.07586 · HTML: https://mlsanity.com/paper/2509.07586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 11 of 11)

- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times](https://mlsanity.com/paper/2010.01815/) (2020)
- [A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation](https://mlsanity.com/paper/2203.09893/) (2022)
- [Beat this! Accurate beat tracking without DBN postprocessing](https://mlsanity.com/paper/2407.21658/) (2024)
- [Deep Polyphonic ADSR Piano Note Transcription](https://mlsanity.com/paper/1906.09165/) (2019)
- [Polyphonic Piano Transcription Using Autoregressive Multi-State Note Model](https://mlsanity.com/paper/2010.01104/) (2020)
- [Problems and Prospects for Intimate Musical Control of Computers](https://mlsanity.com/paper/2010.01570/) (2020)
- [Onsets and Velocities: Affordable Real-Time Piano Transcription Using Convolutional Neural Networks](https://mlsanity.com/paper/2303.04485/) (2023)
- [Improving Networked Music Performance Systems Using Application-Network Collaboration](https://mlsanity.com/paper/1808.09405/) (2018)
- [Designing Neural Synthesizers for Low-Latency Interaction](https://mlsanity.com/paper/2503.11562/) (2025)

## Abstract (arXiv)

Advances in neural network design and the availability of large-scale labeled datasets have driven major improvements in piano transcription. Existing approaches target either offline applications, with no restrictions on computational demands, or online transcription, with delays of 128-320 ms. However, most real-time musical applications require latencies below 30 ms. In this work, we investigate whether and how the current state-of-the-art online transcription model can be adapted for real-time piano transcription. Specifically, we eliminate all non-causal processing, and reduce computational load through shared computations across core model components and variations in model size. Additionally, we explore different pre- and postprocessing strategies, and related label encoding schemes, and discuss their suitability for real-time transcription. Evaluating the adaptions on the MAESTRO dataset, we find a drop in transcription accuracy due to strictly causal processing as well as a tradeoff between the preprocessing latency and prediction accuracy. We release our system as a baseline to support researchers in designing models towards minimum latency real-time transcription.