kth.sePublications KTH
Operational message
There are currently operational disruptions. Troubleshooting is in progress.
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
"Well", what can you do with messy data? Exploring the prosody and pragmatic function of the discourse marker "well" with found data and speech synthesis
University of Edinburgh, UK.
University of Edinburgh, UK.
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.ORCID iD: 0000-0003-1175-840X
2024 (English)In: Interspeech 2024, International Speech Communication Association , 2024, p. 4084-4088Conference paper, Published paper (Refereed)
Abstract [en]

Recently, there has been growing interest in the synthesis of conversational speech prosody. Conversational prosody is variable and carries many pragmatic functions. As speech synthesis research moves to using large amounts of untranscribed data, it is crucial that we understand the subtle pragmatic differences prosody can make. This study focuses on discourse markers, which are linguistic elements that perform various communicative functions, with their specific roles often linked to their prosodic realisation. In this paper, we explore the prosodic realisation of well using an unlabelled corpus of conversational speech. We use clustering to explore the variation in its prosodic realisation and identify common patterns in a data-driven manner. We synthesise the cluster centroids using controllable speech synthesis. Finally, we evaluate how the prosodic realisation of well affects the meaning of an utterance.

Place, publisher, year, edition, pages
International Speech Communication Association , 2024. p. 4084-4088
Keywords [en]
conversational speech synthesis, pragmatics, prosody
National Category
General Language Studies and Linguistics Natural Language Processing Computer Sciences Specific Languages
Identifiers
URN: urn:nbn:se:kth:diva-358879DOI: 10.21437/Interspeech.2024-2122ISI: 001331850104038Scopus ID: 2-s2.0-85214836302OAI: oai:DiVA.org:kth-358879DiVA, id: diva2:1930532
Conference
25th Interspeech Conferece 2024, Kos Island, Greece, Sep 1 2024 - Sep 5 2024
Note

QC 20250127

Available from: 2025-01-23 Created: 2025-01-23 Last updated: 2025-12-05Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Székely, Éva

Search in DiVA

By author/editor
Székely, Éva
By organisation
Speech, Music and Hearing, TMH
General Language Studies and LinguisticsNatural Language ProcessingComputer SciencesSpecific Languages

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 64 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