Skip to Main content Skip to Navigation
Conference papers

Toward Genre Adapted Closed Captioning

François Buet 1 François yvon 1 
1 TLP - Traitement du Langage Parlé
LISN - Laboratoire Interdisciplinaire des Sciences du Numérique, STL - Sciences et Technologies des Langues
Abstract : This paper studies the generation of intralingual closed captions from automatic speech transcripts, with the aim to assess techniques for multi-genre captioning. Captions and subtitles greatly vary in form and content depending on the programs genres and subtitling styles, resulting for instance in significantly different compression rates and lexical content. Borrowing ideas from the multi-domain machine translation literature, we implement and contrast several adaptation methods on a diverse set of programs broadcast on the French public TV. Our results show that such multi-domain adaption techniques are effective and help to improve our automatic subtitling system.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03329488
Contributor : François Yvon Connect in order to contact the contributor
Submitted on : Tuesday, August 31, 2021 - 8:56:58 AM
Last modification on : Sunday, June 26, 2022 - 3:12:43 AM
Long-term archiving on: : Wednesday, December 1, 2021 - 6:58:34 PM

File

buet21_interspeech.pdf
Publisher files allowed on an open archive

Identifiers

Citation

François Buet, François yvon. Toward Genre Adapted Closed Captioning. Interspeech 2021, Aug 2021, Brno (virtual), Czech Republic. pp.4403-4407, ⟨10.21437/interspeech.2021-1762⟩. ⟨hal-03329488⟩

Share

Metrics

Record views

77

Files downloads

119