Comparative performance study of several pitch detection algorithms

By M. J. Cheng, Lawrence R. Rabiner, A. Rosenberg, C. McGonegal. 1975

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature (2022, methodology): “We also analyze the Gross Pitch Error (GPE) [37] which calculates the proportion of frames whose pitch discrepancy in the recording and synthetic speech is less than 20% among voiced frames.”
Yet Another Algorithm for Pitch Tracking (2002, background): “Although many pitch detection algorithms have been reported, using a variety of techniques and with varying degrees of accuracy (see [7], [8] for summary), robust, easy to integrate methods, are still problematic.”
Multiple fundamental frequency estimation based on harmonicity and spectral smoothness (2003, methodology): “Computational methods for multiple fundamental frequency (F0) estimation have received less attention, though many algorithms are available for estimating the F0 in single-voice speech signals [2]–[4].”
Reducing F0 Frame Error of F0 tracking algorithms under noisy conditions with an unvoiced/voiced classification frontend (2009, unknown): “Two types of error metrics are commonly used [2].”
A Probabilistic Interaction Model for Multipitch Tracking With Factorial Hidden Markov Models (2011, methodology): “For an early comparison of single pitch estimation methods, we refer the interested reader to [3].”