Confirmation detection in human-agent interaction using non-lexical speech cues

Brandt M, Wrede B, Kummert F, Schillingmann L (2017)
Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA.

Konferenzbeitrag | Englisch
 
Download
OA 2.58 MB
Abstract / Bemerkung
Even if only the acoustic channel is considered, human communication is highly multi-modal. Non-lexical cues provide a variety of information such as emotion or agreement. The ability to process such cues is highly relevant for spoken dialog systems, especially in assistance systems. In this paper we focus on the recognition of non-lexical confirmations such as "mhm", as they enhance the system's ability to accurately interpret human intent in natural communication. The architecture uses a Support Vector Machine to detect confirmations based on acoustic features. In a systematic comparison, several feature sets were evaluated for their performance on a corpus of human-agent interaction in a setting with naive users including elderly and cognitively impaired people. Our results show that using stacked formants as features yield an accuracy of 84% outperforming regular formants and MFCC or pitch based features for online classification.
Erscheinungsjahr
2017
Konferenz
AAAI Symposium on Natural Communication for Human-Robot Collaboration
Konferenzort
Arlington, VA
Konferenzdatum
2017-11-09 – 2017-11-11
Page URI
https://pub.uni-bielefeld.de/record/2915391

Zitieren

Brandt M, Wrede B, Kummert F, Schillingmann L. Confirmation detection in human-agent interaction using non-lexical speech cues. Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA.
Brandt, M., Wrede, B., Kummert, F., & Schillingmann, L. (2017). Confirmation detection in human-agent interaction using non-lexical speech cues. Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA.
Brandt, Mara, Wrede, Britta, Kummert, Franz, and Schillingmann, Lars. 2017. “Confirmation detection in human-agent interaction using non-lexical speech cues”. Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA .
Brandt, M., Wrede, B., Kummert, F., and Schillingmann, L. (2017).“Confirmation detection in human-agent interaction using non-lexical speech cues”. Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA.
Brandt, M., et al., 2017. Confirmation detection in human-agent interaction using non-lexical speech cues. Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA.
M. Brandt, et al., “Confirmation detection in human-agent interaction using non-lexical speech cues”, Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA, 2017.
Brandt, M., Wrede, B., Kummert, F., Schillingmann, L.: Confirmation detection in human-agent interaction using non-lexical speech cues. Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA (2017).
Brandt, Mara, Wrede, Britta, Kummert, Franz, and Schillingmann, Lars. “Confirmation detection in human-agent interaction using non-lexical speech cues”. Presented at the AAAI Symposium on Natural Communication for Human-Robot Collaboration, Arlington, VA, 2017.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:54Z
MD5 Prüfsumme
fac0ea911fc7ba181d84a303c7ee10ff


Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Quellen

arXiv: 1710.00171

Suchen in

Google Scholar