Analysis and recognition of esophageal speech

Alfredo Mantilla, Héctor Pérez-Meana, Jorge Treviño, Patricia Ortal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

This paper presents a system for analysis and recognition of voiced segments in Spanish esophageal speech. This algorithm involves voiced speech segments analysis methods based in energy criterion and zero crossing, as well as, feature extraction using a wavelet function based on the inner ear model and the recognition stage through the artificial neural networks. Simulation results are presented for normal and esophageal speech.

Original languageEnglish
Title of host publicationSixth IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2006
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages101-106
Number of pages6
ISBN (Print)0780397541, 9780780397545
DOIs
StatePublished - 2006
Event6th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2006 - Vancouver, BC, Canada
Duration: 27 Aug 200630 Aug 2006

Publication series

NameSixth IEEE International Symposium on Signal Processing and Information Technology, ISSPIT

Conference

Conference6th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2006
Country/TerritoryCanada
CityVancouver, BC
Period27/08/0630/08/06

Keywords

  • Esophageal speech
  • Feature extraction
  • Neural networks
  • Voiced and unvoiced classification
  • Wavelet transform

Fingerprint

Dive into the research topics of 'Analysis and recognition of esophageal speech'. Together they form a unique fingerprint.

Cite this