Speaking Status Detection from Body Movements Using Transductive Parameter Transfer

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

4 Citations (Scopus)

Abstract

We investigate the task of detecting speakers in crowded environments using a single triaxial accelerometer worn around the neck. Similar to the previous studies, by assuming that body movements are indicative of speech, we show experimentally that transductive transfer learning can better model individual differences in speaking behaviour compared to a traditional person independent setup. Such behaviour is very challenging to model as people’s body movements during speech vary greatly. To our knowledge, this is the first time that a transfer learning approach has been considered in the context of speaking status detection using a single body worn accelerometer. We show that by transferring knowledge across subjects, competitive performance scores compared to a person dependent training can be obtained.


Original languageEnglish
Title of host publicationUbiComp 2016
Subtitle of host publicationProceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct
EditorsPaul Lukowicz, Antonio Krüger
Place of PublicationNew York, NY
PublisherAssociation for Computing Machinery (ACM)
Pages69-72
Number of pages4
ISBN (Electronic)978-1-4503-4462-3
DOIs
Publication statusPublished - 2016
EventUbiComp 2016 : ACM International Joint Conference on Pervasive and Ubiquitous Computing, - Heidelberg, Germany
Duration: 12 Sep 201616 Sep 2016

Conference

ConferenceUbiComp 2016
CountryGermany
CityHeidelberg
Period12/09/1616/09/16

Keywords

  • social action recognition
  • wearable sensors
  • transfer learning

Fingerprint Dive into the research topics of 'Speaking Status Detection from Body Movements Using Transductive Parameter Transfer'. Together they form a unique fingerprint.

  • Cite this

    Gedik, E., & Hung, H. (2016). Speaking Status Detection from Body Movements Using Transductive Parameter Transfer. In P. Lukowicz, & A. Krüger (Eds.), UbiComp 2016: Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct (pp. 69-72). Association for Computing Machinery (ACM). https://doi.org/10.1145/2968219.2971444