PESTO: Real‑Time Pitch Estimation with Self‑Supervised Transposition‑Equivariant Objective

作者：Alain Riou, Bernardo Torres, Ben J. Hayes, Stefan Lattner, Gaëtan Hadjeres, Gaël Richard, Geoffroy Peeters · 发表于：Transactions of the International Society for Music Information Retrieval · 年份：2025 · DOI：10.5334/tismir.251 · 被引用次数：5 · 研究领域：Music and Audio Processing、Speech and Audio Processing、Music Technology and Sound Studies

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 performance 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.