Speaker trait characterization in web videos: Uniting speech, language, and facial features

Abstract: We present a multi-modal approach to speaker characterization using acoustic, visual and linguistic features. Full realism is provided by evaluation on a database of real-life web videos and automatic feature extraction including face and eye detection, and automatic speech recognition. Different segmentations are evaluated for the audio and video streams, and the statistical relevance of Linguistic Inquiry and Word Count (LIWC) features is confirmed. In the result, late multimodal fusion delivers 73, 92 and 73% average recall in binary age, gender and race classification on unseen test subjects, outperforming the best single modalities for age and race

Location
Deutsche Nationalbibliothek Frankfurt am Main
Extent
Online-Ressource, 3647-3651 S.
Language
Englisch
Notes
Veröffentlichungsversion
begutachtet (peer reviewed)
In: Proceedings of the 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013). 2013. S. 3647-3651. ISBN 978-1-4799-0356-6

Event
Veröffentlichung
(where)
New York
(who)
IEEE
(when)
2013
Event
Veröffentlichung
(where)
Mannheim
(who)
SSOAR - Social Science Open Access Repository
(when)
2013
Creator
Weninger, Felix
Wagner, Claudia
Wöllmer, Martin
Schuller, Björn
Morency, Louis-Philipp

DOI
10.1109/ICASSP.2013.6638338
URN
urn:nbn:de:0168-ssoar-66084-2
Rights
Open Access unbekannt; Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Last update
25.03.2025, 1:45 PM CET

Data provider

This object is provided by:
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.

Associated

  • Weninger, Felix
  • Wagner, Claudia
  • Wöllmer, Martin
  • Schuller, Björn
  • Morency, Louis-Philipp
  • IEEE
  • SSOAR - Social Science Open Access Repository

Time of origin

  • 2013

Other Objects (12)