kth.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
"Am I listening?", Evaluating the Quality of Generated Data-driven Listening Motion
IDLab-AIRO -Ghent University Ghent, Belgium.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Tal, musik och hörsel, TMH.ORCID-id: 0000-0002-1643-1054
IDLab-AIRO -Ghent University Ghent, Belgium.
2023 (Engelska)Ingår i: ICMI 2023 Companion: Companion Publication of the 25th International Conference on Multimodal Interaction, Association for Computing Machinery (ACM) , 2023, s. 6-10Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper asks if recent models for generating co-speech gesticulation also may learn to exhibit listening behaviour as well. We consider two models from recent gesture-generation challenges and train them on a dataset of audio and 3D motion capture from dyadic conversations. One model is driven by information from both sides of the conversation, whereas the other only uses the character's own speech. Several user studies are performed to assess the motion generated when the character is speaking actively, versus when the character is the listener in the conversation. We find that participants are reliably able to discern motion associated with listening, whether from motion capture or generated by the models. Both models are thus able to produce distinctive listening behaviour, even though only one model is truly a listener, in the sense that it has access to information from the other party in the conversation. Additional experiments on both natural and model-generated motion finds motion associated with listening to be rated as less human-like than motion associated with active speaking.

Ort, förlag, år, upplaga, sidor
Association for Computing Machinery (ACM) , 2023. s. 6-10
Nyckelord [en]
embodied conversational agents, listening behaviour
Nationell ämneskategori
Språkteknologi (språkvetenskaplig databehandling)
Identifikatorer
URN: urn:nbn:se:kth:diva-339688DOI: 10.1145/3610661.3617160Scopus ID: 2-s2.0-85175853253OAI: oai:DiVA.org:kth-339688DiVA, id: diva2:1812471
Konferens
25th International Conference on Multimodal Interaction, ICMI 2023 Companion, Paris, France, Oct 9 2023 - Oct 13 2023
Anmärkning

Part of ISBN 9798400703218

QC 20231116

Tillgänglig från: 2023-11-16 Skapad: 2023-11-16 Senast uppdaterad: 2023-11-16Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Henter, Gustav Eje

Sök vidare i DiVA

Av författaren/redaktören
Henter, Gustav Eje
Av organisationen
Tal, musik och hörsel, TMH
Språkteknologi (språkvetenskaplig databehandling)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 42 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf