PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective

TL;DR

PESTO is a lightweight, self-supervised, real-time pitch estimation model that uses a transposition-equivariant objective and a Siamese architecture to outperform baselines and generalize across datasets.

Contribution

Introduces PESTO, a self-supervised, transposition-equivariant pitch estimation method with a novel training objective and streamable implementation for real-time use.

Findings

Outperforms self-supervised baselines in pitch estimation.

Competitively matches supervised methods across datasets.

Achieves low latency (<10 ms) suitable for real-time applications.

Abstract

In this paper, we introduce PESTO, a self-supervised learning approach for single-pitch estimation using a Siamese architecture. Our model processes individual frames of a Variable-$Q$ Transform (VQT) and predicts pitch distributions. The neural network is designed to be equivariant to translations, notably thanks to a Toeplitz fully-connected layer. In addition, we construct pitch-shifted pairs by translating and cropping the VQT frames and train our model with a novel class-based transposition-equivariant objective, eliminating the need for annotated data. Thanks to this architecture and training objective, our model achieves remarkable performances while being very lightweight ($130$k parameters). Evaluations on music and speech datasets (MIR-1K, MDB-stem-synth, and PTDB) demonstrate that PESTO not only outperforms self-supervised baselines but also competes with supervised methods, exhibiting superior cross-dataset generalization. Finally, we enhance PESTO's practical utility by developing a streamable VQT implementation using cached convolutions. Combined with our model's low latency (less than 10 ms) and minimal parameter count, this makes PESTO particularly suitable for real-time applications.