# Traditional Machine Learning for Pitch Detection

## TL;DR

This paper explores traditional machine learning methods for pitch detection, demonstrating significant improvements in voicing error reduction and perceptual quality over baseline methods, with a focus on feature analysis and comparison of approaches.

## Contribution

It introduces a comprehensive analysis of traditional machine learning techniques for pitch detection, highlighting their effectiveness compared to deep learning approaches.

## Key findings

- 20% reduction in voicing errors with K-means clustering
- 45% reduction in voicing errors with Multi-Layer Perceptron
- Perceptual preference for proposed methods over RAPT and DIO

## Abstract

Pitch detection is a fundamental problem in speech processing as F0 is used in a large number of applications. Recent articles have proposed deep learning for robust pitch tracking. In this paper, we consider voicing detection as a classification problem and F0 contour estimation as a regression problem. For both tasks, acoustic features from multiple domains and traditional machine learning methods are used. The discrimination power of existing and proposed features is assessed through mutual information. Multiple supervised and unsupervised approaches are compared. A significant relative reduction of voicing errors over the best baseline is obtained: 20% with the best clustering method (K-means) and 45% with a Multi-Layer Perceptron. For F0 contour estimation, the benefits of regression techniques are limited though. We investigate whether those objective gains translate in a parametric synthesis task. Clear perceptual preferences are observed for the proposed approach over two widely-used baselines (RAPT and DIO).