Smoothed cepstrum calculation using stressed vowels in connected speech to objectively measure dysphonia

K. M. Murray, R. T. Sataloff, Y. Heman-Ackah

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

Abstract

Voice disorders are rather common: the NIDCD reports that at least 7.5 million people in the United States have vocal problems [1]. To address this problem, voice scientists have developed various objective vocal health measurements [3-6]. To further study those measurements, vocal health practitioners have collected and organized speech databases [3,4,6]. One standard for evaluation of these measurements is the GRBAS Scale [7]. This scale achieves strong perceptual agreement among medical professionals with respect to a speaker's vocal health. In broad terms, dysphonia represents a marked difficulty in producing voiced phonation. As such, traditional voicing detection algorithms can fail on dysphonic voices [5].

Original languageEnglish (US)
Title of host publication2015 IEEE Signal Processing in Medicine and Biology Symposium - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509013500
DOIs
StatePublished - Feb 11 2016
Externally publishedYes
EventIEEE Signal Processing in Medicine and Biology Symposium - Philadelphia, United States
Duration: Dec 12 2015 → …

Publication series

Name2015 IEEE Signal Processing in Medicine and Biology Symposium - Proceedings

Conference

ConferenceIEEE Signal Processing in Medicine and Biology Symposium
Country/TerritoryUnited States
CityPhiladelphia
Period12/12/15 → …

ASJC Scopus subject areas

  • Biomedical Engineering
  • Signal Processing
  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Fingerprint

Dive into the research topics of 'Smoothed cepstrum calculation using stressed vowels in connected speech to objectively measure dysphonia'. Together they form a unique fingerprint.

Cite this