Human Voice Pitch Estimation: A Convolutional Network with Auto-Labeled and Synthetic Data

Jeremy Cochoy
8/14/2023
cs.SDcs.LGeess.AS

Official code: jeremycochoy/pitchnet (3 stars, last commit 2023-08-31).

Abstract

In the domain of music and sound processing, pitch extraction plays a pivotal role. Our research presents a specialized convolutional neural network designed for pitch extraction, particularly from the human singing voice in acapella performances. Notably, our approach combines synthetic data with auto-labeled acapella sung audio, creating a robust training environment. Evaluation across datasets comprising synthetic sounds, opera recordings, and time-stretched vowels demonstrates its efficacy. This work paves the way for enhanced pitch extraction in both music and voice settings.

View on arXivView PDF

Code Implementations(1)

jeremycochoy/pitchnetOfficial

Code for the paper PitchNet: A Fully Convolutional Neural Network for Pitch Estimation

30Shell, PythonAug 31, 20233 years ago

Similar Papers

PrimaDNN': A Characteristics-aware DNN Customization for Singing Technique Detection

82% match2023

FCPE: A Fast Context-based Pitch Estimation Model

80% match1 repo2132025

A Phoneme-Informed Neural Network Model for Note-Level Singing Transcription

80% match2 repos382023

Spectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation

80% match1 repo132024

Detection and classification of vocal productions in large scale audio recordings

80% match2023

Machine Learning Approaches to Vocal Register Classification in Contemporary Male Pop Music

80% match2025

Cite this paper

@article{cochoy2023human,
  title  = {Human Voice Pitch Estimation: A Convolutional Network with Auto-Labeled and Synthetic Data},
  author = {Jeremy Cochoy},
  year   = {2023},
  eprint = {2308.07170},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.07170v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.07170.svg)](https://codeofpaper.com/paper/2308.07170)

Discussion