Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Improving Prediction of Speech Activity Using Multi-Participant Respiratory State
Stockholm University, Faculty of Humanities, Department of Linguistics, Phonetics.ORCID iD: 0000-0003-3824-2980
Carnegie Mellon University. (Speech group)
Stockholm University, Faculty of Humanities, Department of Linguistics, Phonetics.ORCID iD: 0000-0002-0034-0924
Stockholm University, Faculty of Humanities, Department of Linguistics, Phonetics.ORCID iD: 0000-0003-4432-2602
2017 (English)In: Proceedings of the 18th Annual Conference of the International Speech Communication Association (INTERSPEECH 2017) / [ed] Włodarczak, Marcin, Stockholm: The International Speech Communication Association (ISCA), 2017, 1666-1670 p.Conference paper, Published paper (Refereed)
Abstract [en]

One consequence of situated face-to-face conversation is the co- observability of participants’ respiratory movements and sounds. We explore whether this information can be exploited in pre- dicting incipient speech activity. Using a methodology called stochastic turn-taking modeling, we compare the performance of a model trained on speech activity alone to one additionally trained on static and dynamic lung volume features. The method- ology permits automatic discovery of temporal dependencies across participants and feature types. Our experiments show that respiratory information substantially lowers cross-entropy rates, and that this generalizes to unseen data. 

Place, publisher, year, edition, pages
Stockholm: The International Speech Communication Association (ISCA), 2017. 1666-1670 p.
Keyword [en]
respiratory kinematics, interaction chronograms, stochastic turn-taking models
National Category
General Language Studies and Linguistics
Research subject
Phonetics
Identifiers
URN: urn:nbn:se:su:diva-145398DOI: 10.21437/Interspeech.2017-1176OAI: oai:DiVA.org:su-145398DiVA: diva2:1128903
Conference
INTERSPEECH 2017
Projects
Swedish Research Council grant 2014-1072 Andning i samtal (Breathing in conversation)
Funder
Swedish Research Council, 2014-1072
Available from: 2017-07-31 Created: 2017-07-31 Last updated: 2017-07-31Bibliographically approved

Open Access in DiVA

fulltext(309 kB)12 downloads
File information
File name FULLTEXT01.pdfFile size 309 kBChecksum SHA-512
3d977ae8c3af65b600a2ccd4c0add23594dcb9e276c05d210813558861affb1381ccaccbd32ca4e31841bceb23ff434b4dd057e78d35f244a41b051446075394
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Włodarczak, MarcinHeldner, MattiasAare, Kätlin
By organisation
Phonetics
General Language Studies and Linguistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 12 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 82 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf