DAVE: Detecting Agitated Vocal Events

Asif Salekin, Hongning Wang, Kristine Williams, John Stankovic

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

1 Scopus citations

Abstract

DAVE is a comprehensive set of event detection techniques to monitor and detect 5 important verbal agitations: Asking for help, verbal sexual advances, questions, cursing, and talking with repetitive sentences. The novelty of DAVE includes combining acoustic signal processing with three different text mining paradigms to detect verbal events (asking for help, verbal sexual advances, and questions) which need both lexical content and acoustic variations to produce accurate results. To detect cursing and talking with repetitive sentences we extend word sense disambiguation and sequential pattern mining algorithms. The solutions have applicability to monitoring dementia patients, for online video sharing applications, human computer interaction (HCI) systems, home safety, and other health care applications. A comprehensive performance evaluation across multiple domains includes audio clips collected from 34 real dementia patients, audio data from controlled environments, movies and Youtube clips, online data repositories, and healthy residents in real homes. The results show significant improvement over baselines and high accuracy for all 5 vocal events.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE 2nd International Conference on Connected Health
Subtitle of host publicationApplications, Systems and Engineering Technologies, CHASE 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages157-166
Number of pages10
ISBN (Electronic)9781509047215
DOIs
StatePublished - Aug 14 2017
Externally publishedYes
Event2nd IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2017 - Philadelphia, United States
Duration: Jul 17 2017Jul 19 2017

Publication series

NameProceedings - 2017 IEEE 2nd International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2017

Conference

Conference2nd IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies, CHASE 2017
CountryUnited States
CityPhiladelphia
Period7/17/177/19/17

Keywords

  • Acoustic signal processing
  • Asking for help
  • Cursing
  • Monitoring dementia patients
  • Verbal agitation
  • Verbal sexual advances

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Health(social science)
  • Communication
  • Computer Science Applications
  • Software
  • Biomedical Engineering
  • Health Informatics

Fingerprint Dive into the research topics of 'DAVE: Detecting Agitated Vocal Events'. Together they form a unique fingerprint.

Cite this