Lightweight Self-Supervised Detection of Fundamental Frequency and Accurate Probability of Voicing in Monophonic Music

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bitra, Venkat Suprabath, Beigi, Homayoon
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908772680597504
author Bitra, Venkat Suprabath
Beigi, Homayoon
author_facet Bitra, Venkat Suprabath
Beigi, Homayoon
contents Reliable fundamental frequency (F 0) and voicing estimation is essential for neural synthesis, yet many pitch extractors depend on large labeled corpora and degrade under realistic recording artifacts. We propose a lightweight, fully self-supervised framework for joint F 0 estimation and voicing inference, designed for rapid single-instrument training from limited audio. Using transposition-equivariant learning on CQT features, we introduce an EM-style iterative reweighting scheme that uses Shift Cross-Entropy (SCE) consistency as a reliability signal to suppress uninformative noisy/unvoiced frames. The resulting weights provide confidence scores that enable pseudo-labeling for a separate lightweight voicing classifier without manual annotations. Trained on MedleyDB and evaluated on MDB-stem-synth ground truth, our method achieves competitive cross-corpus performance (RPA 95.84, RCA 96.24) and demonstrates cross-instrument generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11768
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Lightweight Self-Supervised Detection of Fundamental Frequency and Accurate Probability of Voicing in Monophonic Music
Bitra, Venkat Suprabath
Beigi, Homayoon
Audio and Speech Processing
Artificial Intelligence
Machine Learning
Sound
Signal Processing
Reliable fundamental frequency (F 0) and voicing estimation is essential for neural synthesis, yet many pitch extractors depend on large labeled corpora and degrade under realistic recording artifacts. We propose a lightweight, fully self-supervised framework for joint F 0 estimation and voicing inference, designed for rapid single-instrument training from limited audio. Using transposition-equivariant learning on CQT features, we introduce an EM-style iterative reweighting scheme that uses Shift Cross-Entropy (SCE) consistency as a reliability signal to suppress uninformative noisy/unvoiced frames. The resulting weights provide confidence scores that enable pseudo-labeling for a separate lightweight voicing classifier without manual annotations. Trained on MedleyDB and evaluated on MDB-stem-synth ground truth, our method achieves competitive cross-corpus performance (RPA 95.84, RCA 96.24) and demonstrates cross-instrument generalization.
title Lightweight Self-Supervised Detection of Fundamental Frequency and Accurate Probability of Voicing in Monophonic Music
topic Audio and Speech Processing
Artificial Intelligence
Machine Learning
Sound
Signal Processing
url https://arxiv.org/abs/2601.11768