Pitch detection algorithms modifications and implementations towards automated vocal analysis

Yuhong Zhang, Aaron C. Elkins, Jay F. Nunamaker

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

1 Scopus citations

Abstract

Discriminating between deceit and truth is a significant security challenge in a variety of situations, including border crossings, job interviews, flight passenger screenings, and police interviews. Previous research indicates that some features of vocal speech, e.g., fundamental frequency, are related to human emotion and stress levels making them applicable deception detection. This paper focuses on voice and speech feature extraction using advanced signal processing methodology. These generated speech features are used to submit data mining algorithms for classifying deception. The result of this paper is expected to be directly applied to the deception detection system.

Original languageEnglish (US)
Title of host publicationProceedings of the 11th IEEE International Conference on Networking, Sensing and Control, ICNSC 2014
PublisherIEEE Computer Society
Pages405-410
Number of pages6
ISBN (Print)9781479931064
DOIs
StatePublished - 2014
Externally publishedYes
Event11th IEEE International Conference on Networking, Sensing and Control, ICNSC 2014 - Miami, FL, United States
Duration: Apr 7 2014Apr 9 2014

Publication series

NameProceedings of the 11th IEEE International Conference on Networking, Sensing and Control, ICNSC 2014

Other

Other11th IEEE International Conference on Networking, Sensing and Control, ICNSC 2014
Country/TerritoryUnited States
CityMiami, FL
Period4/7/144/9/14

Keywords

  • deception detection
  • pitch
  • speech feature
  • speech processing

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Pitch detection algorithms modifications and implementations towards automated vocal analysis'. Together they form a unique fingerprint.

Cite this