Demo abstract: Online detection of speaking from respiratory measurements collected in the natural environment

Md Mahbubur Rahman, Amin Ahsan Ali, Andrew Raij, Mustafa Al'Absi, Emre Ertin, Santosh Kumar

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

2 Scopus citations

Abstract

We present a novel method to detect when a person is speaking using respiratory measurements collected in the natural environment. A speaker's respiration pattern is sampled from a respiratory inductive plethysmograph (RIP) band worn around the speaker's chest. Ratio of inhalation duration to exhalation duration (IE ratio) has traditionally been used to detect speaking in controlled lab environment [7]. However, we find that IE ratio is inadequate in the natural environment. We propose several new features to be used along with IE ratio. Using various statistics over these features, we obtain >95% accuracy in classifying respiration measurements into "speaking" or "silence" states with 10-fold cross validation. Our demonstration will show realtime capture of the respiration signal, computation of features, and detection of speaking and silence, all on a mobile smartphone.

Original languageEnglish (US)
Title of host publicationProceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN'11
Pages137-138
Number of pages2
StatePublished - 2011
Externally publishedYes
Event10th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN'11 - Chicago, IL, United States
Duration: Apr 12 2011Apr 14 2011

Publication series

NameProceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN'11

Other

Other10th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN'11
CountryUnited States
CityChicago, IL
Period4/12/114/14/11

Keywords

  • Respiration signal
  • speaking detection

Fingerprint Dive into the research topics of 'Demo abstract: Online detection of speaking from respiratory measurements collected in the natural environment'. Together they form a unique fingerprint.

Cite this