Volltext herunterladen
(194.2 KB)
Zitationshinweis
Bitte beziehen Sie sich beim Zitieren dieses Dokumentes immer auf folgenden Persistent Identifier (PID):
https://nbn-resolving.org/urn:nbn:de:0168-ssoar-66084-2
Export für Ihre Literaturverwaltung
Speaker trait characterization in web videos: Uniting speech, language, and facial features
[Konferenzbeitrag]
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. Differen... mehr
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.... weniger
Thesaurusschlagwörter
Video; Video-Clip; Aufzeichnung; Computerlinguistik; Internet; Evaluation; Soziale Medien; Experiment; audiovisuelle Medien
Klassifikation
Naturwissenschaften, Technik(wissenschaften), angewandte Wissenschaften
Freie Schlagwörter
speaker classification; computational paralinguistics; multi-modal fusion; Linguistic Inquiry and Word Count; LIWC
Titel Sammelwerk, Herausgeber- oder Konferenzband
Proceedings of the 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)
Konferenz
38. International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013). Vancouver, 2013
Sprache Dokument
Englisch
Publikationsjahr
2013
Verlag
IEEE
Seitenangabe
S. 3647-3651
DOI
https://doi.org/10.1109/ICASSP.2013.6638338
ISSN
2379-190X
ISBN
978-1-4799-0356-6
Status
Veröffentlichungsversion; begutachtet (peer reviewed)
Lizenz
Deposit Licence - Keine Weiterverbreitung, keine Bearbeitung