paper-with-me

홈 › Papers

Toward Fully Self-Supervised Multi-Pitch Estimation

2024-02-23 · Frank Cwitkowitz, Zhiyao Duan

Multi-pitch estimation is a decades-long research problem involving the detection of pitch activity associated with concurrent musical events within multi-instrument mixtures. Supervised learning techniques have demonstrated solid performance on more narrow characterizations of the task, but suffer from limitations concerning the shortage of large-scale and diverse polyphonic music datasets with multi-pitch annotations. We present a suite of self-supervised learning objectives for multi-pitch estimation, which encourage the concentration of support around harmonics, invariance to timbral transformations, and equivariance to geometric transformations. These objectives are sufficient to train an entirely convolutional autoencoder to produce multi-pitch salience-grams directly, without any fine-tuning. Despite training exclusively on a collection of synthetic single-note audio samples, our fully self-supervised framework generalizes to polyphonic music mixtures, and achieves performance comparable to supervised models trained on conventional multi-pitch datasets.

📄 PDF Abstract BibTeX arXiv:2402.15569

Code (1)

cwitkowitz/ss-mpe 공식 구현 pytorch

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

SPICE: Self-supervised Pitch Estimation

2019-10-25 · Beat Gfeller, Christian Frank, Dominik Roblek, Matt Sharifi 외

We propose a model to estimate the fundamental frequency in monophonic audio, often referred to as pitch estimation. We acknowledge the fact that obtaining ground truth annotations at the required temporal and frequency …

Self-Supervised LearningTranslation

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

2023-09-05 · Alain Riou, Stefan Lattner, Gaëtan Hadjeres, Geoffroy Peeters

In this paper, we address the problem of pitch estimation using Self Supervised Learning (SSL). The SSL paradigm we use is equivariance to pitch transposition, which enables our model to accurately perform pitch estimati…

Self-Supervised Learning

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

2025-08-02 · Alain Riou, Bernardo Torres, Ben Hayes, Stefan Lattner 외 arxiv

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 …

Self-Supervised Learning

Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport

2025-08-02 · Bernardo Torres, Alain Riou, Gaël Richard, Geoffroy Peeters arxiv

In this paper, we propose an Optimal Transport objective for learning one-dimensional translation-equivariant systems and demonstrate its applicability to single pitch estimation. Our method provides a theoretically grou…

Self-Supervised Learning

Tempo vs. Pitch: understanding self-supervised tempo estimation

2023-04-14 · Giovana Morais, Matthew E. P. Davies, Marcelo Queiroz, Magdalena Fuentes

Self-supervision methods learn representations by solving pretext tasks that do not require human-generated labels, alleviating the need for time-consuming annotations. These methods have been applied in computer vision,…

Information RetrievalMusic Information RetrievalRetrieval