A robust real-time pitch detector based on neural networks

Horacio Martinez-Alfaro, Jose L. Contreras-Vidal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

A multilayer perceptron trained with the backpropagation procedure is used to detect the fundamental frequency (F0), or pitch, of a speech signal. The model does not require preprocessing of the signal and has good discriminatory capabilities. Preliminary results suggest that a multilayer perceptron can be trained to extract F0 as well as the formants. In the preliminary experiments, the detection rate of F0 was 100% for different numbers of hidden units. As the number of hidden units was increased, the generalization capabilities of the neural net decreased.

Original languageEnglish (US)
Title of host publicationProceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages521-523
Number of pages3
ISBN (Print)0780300033
DOIs
StatePublished - 1991
EventProceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91 - Toronto, Ont, Can
Duration: May 14 1991May 17 1991

Publication series

NameProceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Volume1
ISSN (Print)0736-7791

Other

OtherProceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91
CityToronto, Ont, Can
Period5/14/915/17/91

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A robust real-time pitch detector based on neural networks'. Together they form a unique fingerprint.

Cite this