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
Automatic Turn Segmentation for Movie & TV Subtitles
KTH, School of Computer Science and Communication (CSC), Speech, Music and Hearing, TMH, Speech Communication and Technology.ORCID iD: 0000-0002-7412-0967
2016 (English)In: 2016 IEEE Workshop on Spoken Language Technology (SLT 2016), IEEE conference proceedings, 2016, 245-252 p.Conference paper, Published paper (Refereed)
Abstract [en]

Movie and TV subtitles contain large amounts of conversational material, but lack an explicit turn structure. This paper present a data-driven approach to the segmentation of subtitles into dialogue turns. Training data is first extracted by aligning subtitles with transcripts in order to obtain speaker labels. This data is then used to build a classifier whose task is to determine whether two consecutive sentences are part of the same dialogue turn. The approach relies on linguistic, visual and timing features extracted from the subtitles themselves and does not require access to the audiovisual material -- although speaker diarization can be exploited when audio data is available. The approach also exploits alignments with related subtitles in other languages to further improve the classification performance. The classifier achieves an accuracy of 78% on a held-out test set. A follow-up annotation experiment demonstrates that this task is also difficult for human annotators.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2016. 245-252 p.
National Category
Computer Science Language Technology (Computational Linguistics)
Identifiers
URN: urn:nbn:se:kth:diva-193938DOI: 10.1109/SLT.2016.7846272ISI: 000399128000036Scopus ID: 2-s2.0-85016021595OAI: oai:DiVA.org:kth-193938DiVA: diva2:1034694
Conference
2016 IEEE Workshop on Spoken Language Technology
Note

QC 20161014

Available from: 2016-10-12 Created: 2016-10-12 Last updated: 2017-05-08Bibliographically approved

Open Access in DiVA

fulltext(363 kB)119 downloads
File information
File name FULLTEXT01.pdfFile size 363 kBChecksum SHA-512
75a937714db3b72d98ab26ca2ce55772d942b08d26120c1b8ee66c57ea6d41d48332b8a8e5b73284b2b806791dd6f7c54ca4aaf96e20b8385a306a1bb230b579
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Meena, Raveesh
By organisation
Speech Communication and Technology
Computer ScienceLanguage Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
Total: 119 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

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 465 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