Change search
ReferencesLink to record
Permanent link

Direct link
Respiratory belts and whistles: A preliminary study of breathing acoustics for turn-taking
Stockholm University, Faculty of Humanities, Department of Linguistics, Phonetics.ORCID iD: 0000-0003-3824-2980
Stockholm University, Faculty of Humanities, Department of Linguistics, Phonetics.ORCID iD: 0000-0002-0034-0924
2016 (English)In: Proceedings Interspeech 2016, ISCA , 2016, 510-514 p.Chapter in book (Refereed)
Abstract [en]

This paper presents first results on using acoustic intensity of inhalations as a cue to speech initiation in spontaneous multiparty conversations. We demonstrate that inhalation intensity significantly differentiates between cycles coinciding with no speech activity, shorter (< 1 s) and longer stretches of speech. While the model fit is relatively weak, it is comparable to the fit of a model using kinematic features collected with Respiratory Inductance Plethysmography. We also show that incorpo- rating both kinematic and acoustic features further improves the model. Given the ease of capturing breath acoustics, we consider the results to be a promising first step towards studying communicative functions of respiratory sounds. We discuss possible extensions to the data collection procedure with a view to improving predictive power of the model. 

Place, publisher, year, edition, pages
ISCA , 2016. 510-514 p.
Keyword [en]
breathing, multiparty conversation, turn-taking cues, acoustics, loudness
National Category
General Language Studies and Linguistics
Research subject
URN: urn:nbn:se:su:diva-133773DOI: 10.21437/Interspeech.2016-344OAI: diva2:970909
Swedish Research Council, 2014-1072
Available from: 2016-09-15 Created: 2016-09-15 Last updated: 2016-09-19Bibliographically approved

Open Access in DiVA

fulltext(249 kB)17 downloads
File information
File name FULLTEXT01.pdfFile size 249 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Włodarczak, MarcinHeldner, Mattias
By organisation
General Language Studies and Linguistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 17 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: 15 hits
ReferencesLink to record
Permanent link

Direct link