# Deep-Learning Architectures for Multi-Pitch Estimation: Towards Reliable Evaluation

arXiv: https://arxiv.org/abs/2202.09198 · HTML: https://mlsanity.com/paper/2202.09198/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 18 Feb 2022.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [Onsets and Frames: Dual-Objective Piano Transcription](https://mlsanity.com/paper/1710.11153/) (2017)
- [MT3: Multi-Task Multitrack Music Transcription](https://mlsanity.com/paper/2111.03017/) (2021)
- [Learning Features of Music from Scratch](https://mlsanity.com/paper/1611.09827/) (2016)
- [Sequence-to-Sequence Piano Transcription with Transformers](https://mlsanity.com/paper/2107.09142/) (2021)
- [On the Potential of Simple Framewise Approaches to Piano Transcription](https://mlsanity.com/paper/1612.05153/) (2016)
- [ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data](https://mlsanity.com/paper/2107.04954/) (2021)
- [Invariances and Data Augmentation for Supervised Music Transcription](https://mlsanity.com/paper/1711.04845/) (2017)
- [The Effect of Spectrogram Reconstruction on Automatic Music Transcription: An Alternative Approach to Improve Transcription Accuracy](https://mlsanity.com/paper/2010.09969/) (2020)
- [Revisiting the Onsets and Frames Model with Additive Attention](https://mlsanity.com/paper/2104.06607/) (2021)
- [A Streamlined Encoder/Decoder Architecture for Melody Extraction](https://mlsanity.com/paper/1810.12947/) (2018)
- [Polyphonic Pitch Tracking with Deep Layered Learning](https://mlsanity.com/paper/1804.02918/) (2018)

## Built on by (most cited first, 1 of 1)

- [PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective](https://mlsanity.com/paper/2508.01488/) (2025)

## Abstract (arXiv)

Extracting pitch information from music recordings is a challenging but important problem in music signal processing. Frame-wise transcription or multi-pitch estimation aims for detecting the simultaneous activity of pitches in polyphonic music recordings and has recently seen major improvements thanks to deep-learning techniques, with a variety of proposed network architectures. In this paper, we realize different architectures based on CNNs, the U-net structure, and self-attention components. We propose several modifications to these architectures including self-attention modules for skip connections, recurrent layers to replace the self-attention, and a multi-task strategy with simultaneous prediction of the degree of polyphony. We compare variants of these architectures in different sizes for multi-pitch estimation, focusing on Western classical music beyond the piano-solo scenario using the MusicNet and Schubert Winterreise datasets. Our experiments indicate that most architectures yield competitive results and that larger model variants seem to be beneficial. However, we find that these results substantially depend on randomization effects and the particular choice of the training-test split, which questions the claim of superiority for particular architectures given only small improvements. We therefore investigate the influence of dataset splits in the presence of several movements of a work cycle (cross-version evaluation) and propose a best-practice splitting strategy for MusicNet, which weakens the influence of individual test tracks and suppresses overfitting to specific works and recording conditions. A final evaluation on a mixed dataset suggests that improvements on one specific dataset do not necessarily generalize to other scenarios, thus emphasizing the need for further high-quality multi-pitch datasets in order to reliably measure progress in music transcription tasks.