An autocorrelation pitch detector and voicing decision with confidence measures developed for noise-corrupted speech

The authors describe an integrated speech feature extraction method consisting of: (1) a pitch detector; (2) a voicing decision to correctly partition speech into voiced and unvoiced intervals; (3) a confidence measure which reflects the probabilistic accuracy of the voicing decision; (4) a confiden...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on signal processing 1991-02, Vol.39 (2), p.319-329
Main Authors: Krubsack, D.A., Niederjohn, R.J.
Format: Article
Language:English
Subjects:
Algorithm design and analysis
Autocorrelation
Curve fitting
Detectors
Feature extraction
Signal analysis
Smoothing methods
Speech analysis
Speech enhancement
White noise
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The authors describe an integrated speech feature extraction method consisting of: (1) a pitch detector; (2) a voicing decision to correctly partition speech into voiced and unvoiced intervals; (3) a confidence measure which reflects the probabilistic accuracy of the voicing decision; (4) a confidence measure which reflects the expected deviation of the pitch estimate from the true pitch and the probabilistic accuracy of this deviation; and (5) smoothing techniques for the pitch detector, the voicing decision, and the two confidence measures. The focus of their research is on voiced and unvoiced speech corrupted by high levels of white noise. The voicing decision and the confidence measures are developed by observing the behavior of three features derived from the autocorrelation function and experimentally fitting curves to the data. This integrated set of algorithms is statistically analyzed for speech at seven signal-to-noise ratios.< >
ISSN:1053-587X
1941-0476
DOI:10.1109/78.80814