Quality analysis. YouTube interlingual real time captioning onan American news broadcast accessible for Peruvian user
DOI:
https://doi.org/10.24310/Entreculturasertci.vi13.15352Keywords:
quality, live subtitling, NTR model, automatic speech recognition, machine translationAbstract
This research aims to analyze the quality of interlingual live subtitling using automatic speech recognition and machine translation provided by YouTube. It is a qualitative descriptive study. In this case study, the instruments applied were an analysis sheet and a questionnaire. The corpus analyzed was an interview in English on mental health due to the COVID-19 pandemic and the population questioned was nine Peruvian users. It was possible to know the accuracy rate and the criteria to establish the quality of interlingual live subtitling by applying the NTR model. The study identified that machine translation generated significantly more errors than automatic speech recognition; these were mostly minor errors. Although the workflow used fell short of quality, participants understood more than half of the information presented.
Downloads
Metrics
References
Abadou, Fadila y Khadich, Saleh (2019). Coherence in machine translation output. Traduction et Langues, 18(2), 138-153.
Alsan, Merve (12 de junio de 2022). The best machine translation software you can try in 2022. Weglot. https://weglot.com/blog/machine-translation-software/
Asociación Española de Normalización. (2012). Subtitulado para personas sordas y personas con discapacidad auditivas (UNE 153010:2012). www.une.org.
Canadian Association of Broadcasters (2012). Closed Captioning Standards and Protocol for Canadian English Language Television Programming Services. www.cab-acr.ca
Canadian Radio-television and Telecommunications Commission. (2016). English-language closed captioning quality standard related to the accuracy rate for live programming.
Castells, Manuel (2014). El impacto de internet en la sociedad: una perspectiva global. En BBVA (ed.), C@mbio 19
ensayos fundamentales sobre cómo internet está cambiando nuestras vidas. OpenMind/BBVA.
CBS News, & Paramount+. (9 de marzo 2021). The mental health impacts of the pandemic one year later. YouTube. https://www.youtube.com/watch?v=p2gzCJhcuT8
Chan, Wing Shan, Kruger, Jan-Louis y Doherty, Stephen (2019). Comparing the impact of automatically generated
and corrected subtitles on cognitive load and learning in a firstand second-language educational context. Linguistica Antverpiensia, New Series: Themes in Translation Studies, 18, 237–272.
Cooper, David (1999). Cómo mejorar la comprensión lectora. Editorial Visor.
Dawson, Hayley y Romero-Fresco, Pablo (2021). Towards research-informed training in interlingual respeaking: an empirical approach. The Interpreter and Translator Trainer, 15(1), 66–84.
Described and Captioned Media Program. (s.f.). Captioning Key. https://www.captioningkey.org/about_c.html#1
Do, Thi Ngoc Diep (2012). Extraction de corpus parallèle pour la traduction automatique [Tesis doctoral no publicada]. Université de Grenoble.
Doherty, Stephen y Kruger, Jan-Louis (2018). Assessing Quality in Human- and Machine-Generated Subtitles and Captions. En J. Moorkens, S. Castilho, F. Gaspari, S. Doherty (eds.), Translation Quality Assessment. Machine Translation: Technologies and Applications (pp. 179–197). Springer, Cham.
Eugeni, Carlo (2020). Respeaking: aspects techniques, professionnels et linguistiques du sous-titrage en direct.
ESSACHESS-Journal for Communication Studies, 13(25), 21–35.
Fresno, Nazaret, Sepielak, Katarzyna y Krawczyk, Maciej (2020). Football for all: the quality of the live closed captioning in the Super Bowl LII. Universal Access in the Information Society, 1–12.
Galarza Loayza, Katteryn (12 de diciembre de 2018). La televisión peruana ya no es útil para la educación. Chiqaq
News. https://medialab.unmsm.edu.pe/chiqaqnews/latelevision-peruana-ya-no-es-util-para-la-educacion/
Harrenstien, Ken (2009). Automatic captions in YouTube. Google blog. https://googleblog.blogspot.com/2009/11/automatic-captions-in-youtube.html
Jurafsky, Daniel y Martin, James H. (2020). Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition. Standford University. https://web.stanford.edu/~jurafsky/slp3/ed3book.pdf
Karakanta, A., Papi, S., Negri, M., y Turchi, M. (2021). Simultaneous speech translation for live subtitling: from delay to display. MTSUMMIT. https://arxiv.org/pdf/2107.08807.pdf
Korybski, T., Davitti, E., Or?san, C. y Braun, S. (2022). A Semi-Automated Live Interlingual Communication Workflow Featuring Intralingual Respeaking: Evaluation and Benchmarking. Proceedings of the 13th Conference on Language Resources and Evaluation (pp. 4405–4413). European Language Resources Association. http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.468.pdf
Lambourne, A. (2007). Real-time Subtitling: Extreme Audio-visual Translation. Presentado en conferencia Multidimensional Translation: LSP Translation Scenarios. Vienna, mayo 2007.
Levis, Jhon M. y Suvorov, Ruslan (2012). Automatic Speech Recognition. En Carol Chapelle (ed.), Encyclopedia of
Applied Linguistics (pp. 1-8). Blackwell.
Lockrey, Michael (2015). YouTube automatic craptions score an incredible 95% accuracy rate! Medium. https://medium.com/@mlockrey/youtube-s-incredible-95-accuracy-rateon-auto-generated-captions-b059924765d5
Lu, Xugang, Li, Sheng y Fujimoto, Masakiyo (2020). Automatic Speech Recognition. En Yutaka Kidiwara, Eiichiro
Sumita y Hisashi Kawai (eds.), Speech-to-speech translation (pp. 21–38). SpringerBriefs in Computer Science.
Mikul, Chris (2014). Caption Quality: Approaches to standards and measurement. Media Access Australia. https://mediaaccess.org.au/research-policy/white-papers/captionquality-international-approaches-to-standards-and-measurement
Moores, Zoe (2020). Fostering access for all through respeaking at live events. The Journal of Specialised Translation, 33, 207–226.
National Institute on Aging. (2018). ¿Es confiable la información sobre la salud que se encuentra en el Internet? National Institute on Aging. https://www.nia.nih.gov/espanol/confiable-informacion-sobre-salud-se-encuentra-internet
Navimedia. (s.f.). ¿Por qué el cerebro prefiere vídeo vs. texto? Navimedia https://navimedia.es/por-que-el-cerebro-prefiere-el-video-vs-texto/
Ofcom. (2005). Subtitling - An Issue of Speed?
Puente, Alejandra (2020). El rol de los medios de comunicación en el Perú durante la pandemia. Konrad Adenauer Stiftung. https://www.kas.de/documents/269552/0/El+rol+de+los+medios+de+comunicaci%C3%B3n+en+el+Per%C3%BA+durante+la+Pandemia.pdf/d457a599-7f4a-99ca3230-b8f4ec620bdd?version=1.0&t=1595436508362
Rao, Durgesh D. (1998). Machine translation. A gentle introduction. Resonance, 3(7), 61–70.
Ríos Valero, Laura (2022). Análisis de la calidad. El subtitulado para sordos de YouTube en un programa de televisión peruano. En Miguel Ibáñez Rodríguez, Carmen Cuéllar Lázaro y Paola Masseau (eds.), De la hipótesis a la tesis: Traductología y lingüística aplicada. Comares.
Robert, Isabelle R. y Remael, Aline (2017). Assessing quality in live interlingual subtitling: A new challenge. Linguistica Antverpiensia, New Series–Themes in Translation Studies, 16, 168–195.
Romero-Fresco, Pablo (2010). Standing on quicksand: hearing viewers’ comprehension and reading patterns of respoken subtitles for the news. En Jorge Díaz Cintas, Anna Matamala y Josélia Neves (eds.), New insights into audiovisual translation and media accessibility (pp. 175–1994). Brill.
Romero-Fresco, Pablo (2011). Subtitling through speech recognition: Respeaking. St Jerome.
Romero-Fresco, Pablo (2016). Accessing communication: The quality of live subtitles in the UK. Language and Communication, 49, 56–69.
Romero-Fresco, Pablo (2020, February 13). The State of Live Captioning Today - An Expert’s Perspective. AppTek.
Romero-Fresco, Pablo y Alonso-Bacigalupe, Luis (2022). An empirical analysis on the efficiency of five interlingual
live subtitling workflows. XLinguae, 15(2), 3–16.
Romero-Fresco, Pablo y Martínez, Juan (2015). Accuracy Rate in Live Subtitling-the NER Model. Audiovisual Translation in a Global Context: Mapping an Ever-Changing Landscape, 28–50.
Romero-Fresco, Pablo y Pöchhacker, Franz (2017). Quality assessment in interlingual live subtitling: The NTR model. Linguistica Antverpiensia, 16, 149–167.
Rubio, Isabel (29 de mayo de 2020). ¿Cuál es el mejor traductor?: probamos DeepL, Google Translate y Bing. El País. https://elpais.com/tecnologia/2020-05-29/cual-es-el-mejor-traductor-probamos-deepl-google-translate-y-bing.html
Sandrelli, Annalisa (2020). Interlingual respeaking and simultaneous interpreting in a conference setting: a comparison. En Nicoletta Spinolo y Amalia Amato (eds.), inTRAlinea Special Issue: Technology in Interpreter Education and Practice. Università degli Studi Internazionali di Roma.
Sandrelli, Annalisa (2021). Eventi dal vivo e accessibilità: Uno studio di caso sul respeaking interlinguistico. Lingue
e Linguaggi, 43, 145–168.
Tarakini, G., Mwedzi, T., Manyuchi, T. y Tarakini, T. (2021). The Role of Media During COVID-19 Global Outbreak: A
Conservation Perspective. Tropical Conservation Science, 14, 1–13.
Trajectory Partnership. (2010). The Information Dividend: Why IT makes you “happier.” Trajectory. https://trajectorypartnership.com/wp-content/uploads/2013/09/BCS_InformationDividend_UK.pdf
Ulatus. (20 de junio de 2022). How Automatic Speech Recognition & Machine Translation are Revolutionizing Subtitling. Ulatus. https://www.ulatus.com/translation-blog/how-automatic-speech-recognition-machine-translation-are-revolutionizing-subtitling/
University of Minessota Duluth (Media Hub) (s.f.). Correcting YouTube Auto-Captions. https://itss.d.umn.edu/centers-locations/media-hub/media-accessibility-services/captioning-and-captioning-services/correct
Youtube. (s.f.). Ayuda de YouTube. https://support.google.com/youtube/?hl=es-419#topic=925749
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Laura Ríos Valero
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
All contents published in Entre culturas. Revista de traducción y comunicación intercultural are protected under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license. All about this license is available in the following link: <http://creativecommons.org/licenses/by-nc-sa/4.0>
Users can copy, use, redistribute, share and exhibit publicly as long as:
- The original source and authorship of the material are cited (Journal, Publisher and URL of the work).
- It is not used for comercial purposes.
- The existence of the license and its especifications are mentioned.
There are two sets of authors’ rights: moral and property rights. Moral rights are perpetual prerogatives, unrenounceable, not-transferable, unalienable, imprescriptible and inembargable. According to authors’ rights legislation, Entreculturas. Revista de traducción y comunicación intercultural recognizes and respects authors moral rights, as well as the ownership of property rights, which will be transferred to University of Malaga in open access. The property rights are referred to the benefits that are gained by the use or the dissemination of works. Entreculturas. Revista de traducción y comunicación intercultural is published in an open access form and it is exclusively licenced by any means for doing or authorising distribution, dissemination, reproduction, , adaptation, translation or arrangement of works.
Authors are responsable for obtaining the necessary permission to use copyrighted images.
7.png)
