Forensic Speaker Verification Using Ordinary Least Squares

In Brazil, the recognition of speakers for forensic purposes still relies on a subjectivity-based decision-making process through a results analysis of untrustworthy techniques. Owing to the lack of a voice database, speaker verification is currently applied to samples specifically collected for con...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2019-10, Vol.19 (20), p.4385
Main Authors: Machado, Thyago J., Vieira Filho, Jozue, de Oliveira, Mario A.
Format: Article
Language:English
Subjects:
Accuracy
Brazilian Portuguese
Clinical decision making
Decision making
Discourse analysis
forensic phonetics
Forensic sciences
forensic speaker comparison
Formants
linear predictive coding (lpc)
Neural networks
Noise
ordinary least squares (ols)
Phonetics
Recognition
Software
Speaker identification
Speech
Statistical methods
Subjectivity
Verification
voice processing
Voice recognition
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:In Brazil, the recognition of speakers for forensic purposes still relies on a subjectivity-based decision-making process through a results analysis of untrustworthy techniques. Owing to the lack of a voice database, speaker verification is currently applied to samples specifically collected for confrontation. However, speaker comparative analysis via contested discourse requires the collection of an excessive amount of voice samples for a series of individuals. Further, the recognition system must inform who is the most compatible with the contested voice from pre-selected individuals. Accordingly, this paper proposes using a combination of linear predictive coding (LPC) and ordinary least squares (OLS) as a speaker verification tool for forensic analysis. The proposed recognition technique establishes confidence and similarity upon which to base forensic reports, indicating verification of the speaker of the contested discourse. Therefore, in this paper, an accurate, quick, alternative method to help verify the speaker is contributed. After running seven different tests, this study preliminarily achieved a hit rate of 100% considering a limited dataset (Brazilian Portuguese). Furthermore, the developed method extracts a larger number of formants, which are indispensable for statistical comparisons via OLS. The proposed framework is robust at certain levels of noise, for sentences with the suppression of word changes, and with different quality or even meaningful audio time differences.
ISSN:1424-8220
1424-8220
DOI:10.3390/s19204385