Article published In:
Interpreting: Online-First Articles

Automatic subtitles increase accuracy and decrease cognitive load in simultaneous interpreting

ORCID logo | Shandong University
ORCID logo | Adam Mickiewicz University in Poznań
This study examines the effect of real-time subtitles generated by automatic speech recognition (ASR) technology on interpreting accuracy and interpreters’ cognitive load. Multiple measurements — including interpreting accuracy, the NASA-TLX for subjective ratings of cognitive load, eye-tracking and theta power as indicated by EEG recordings — were applied. Twenty-three professional simultaneous interpreters worked with a video recording of a speech presented in five conditions: a baseline without subtitles and then with subtitles of varying levels of precision (100%, 95%, 90% and 80%). The results reveal that the presence of subtitles significantly improved interpreting accuracy, with a suggested optimal precision rate of 90% or higher. The interpreters looked more at the subtitles, regardless of their level of precision, than the speaker. Contrary to our predictions, the presence of subtitles decreased, rather than increased, the cognitive load (although this outcome was shown by the EEG data only and not by the self-reported data). We conclude that the cognitive cost of processing subtitles as an additional information channel is offset by the cognitive gain achieved through visual prompting. The study highlights a complex effect of subtitles on interpreting, with such factors as subtitle presence and precision modulating the interpreters’ cognitive load in such a workflow.
Keywords: simultaneous interpreting, automatic speech recognition, ASR, live subtitling, cognitive load, electroencephalography, EEG
Article outline
  • 1.Introduction
  • 2.ASR subtitles in interpreting
  • 3.Measurement of cognitive load in interpreting with ASR subtitles
  • 4.The present study
    • 4.1Participants
    • 4.2Materials
    • 4.3Procedure
  • 5.Results
    • 5.1Accuracy
    • 5.2Self-reported cognitive load (NASA-TLX)
    • 5.3Eye-tracking
    • 5.4Theta power
  • 6.Discussion
    • 6.1Accuracy
    • 6.2Self-reported cognitive load (NASA-TLX)
    • 6.3Eye-tracking
    • 6.4Theta power
  • 7.Conclusions
  • Notes
  • References
Published online: 16 September 2024
DOI logo
https://doi.org/10.1075/intp.00111.li
References (74)
References
Abidi, O., Dženopoljac, V. & Safi, M. (2023). Online meeting tools, tacit knowledge sharing and entrepreneurial behaviours among knowledge workers during COVID-19. Knowledge Management Research & Practice 21 (6), 1137–1149. DOI logoGoogle Scholar
Albl-Mikasa, M. (2010). Global English and English as a lingua franca (ELF): Implications for the interpreting profession. Trans-Kom 3 (2), 126–148. DOI logoGoogle Scholar
Alexander, M. P., Benson, D. F. & Stuss, D. T. (1989). Frontal lobes and language. Brain and Language 37 (4), 656–691. DOI logoGoogle Scholar
Amankwah-Amoah, J., Khan, Z., Wood, G. & Knight, G. (2021). COVID-19 and digitalization: The great acceleration. Journal of Business Research 136 1, 602–611. DOI logoGoogle Scholar
Baranowska, K. (2020). Learning most with least effort: Subtitles and cognitive load. ELT Journal 74 (2), 105–115. DOI logoGoogle Scholar
Boos, M., Kobi, M., Elmer, S. & Jäncke, L. (2022). The influence of experience on cognitive load during simultaneous interpretation. Brain and Language 234 1, 105185. DOI logoGoogle Scholar
Castro-Meneses, L. J., Kruger, J.-L. & Doherty, S. (2020). Validating theta power as an objective measure of cognitive load in educational video. Educational Technology Research and Development 68 (1), 181–202. DOI logoGoogle Scholar
Chen, S. (2017). The construct of cognitive load in interpreting and its measurement. Perspectives 25 (4), 640–657. DOI logoGoogle Scholar
Cheung, A. K. F. (2008). Simultaneous interpreting of numbers: An experimental study. Forum 6 (2), 23–38. DOI logoGoogle Scholar
Cheung, A. K. F. & Li, T. (2022). Machine aided interpreting: An experiment of automatic speech recognition in simultaneous interpreting. Translation Quarterly 104 (2), 1–20.Google Scholar
Chiu, C.-C., Sainath, T. N., Wu, Y., Prabhavalkar, R., Nguyen, P., Chen, Z., Kannan, A., Weiss, R. J., Rao, K., Gonina, E., Jaitly, N., Li, B., Chorowski, J. & Bacchiani, M. (2018). State-of-the-art speech recognition with sequence-to-sequence models. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4774–4778. DOI logoGoogle Scholar
CSIS. (2017, 9 September). Raila Odinga on the Kenyan elections. [URL]
D’Ausilio, A., Craighero, L. & Fadiga, L. (2012). The contribution of the frontal lobe to the perception of speech. Journal of Neurolinguistics 25 (5), 328–335. DOI logoGoogle Scholar
Dehaene, S., Cohen, L., Sigman, M. & Vinckier, F. (2005). The neural code for written words: A proposal. Trends in Cognitive Sciences 9 (7), 335–341. DOI logoGoogle Scholar
Delorme, A. & Makeig, S. (2004). EEGLAB: An open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. Journal of Neuroscience Methods 134 (1), 9–21. DOI logoGoogle Scholar
Desmet, B., Vandierendonck, M. & Defrancq, B. (2018). Simultaneous interpretation of numbers and the impact of technological support. In C. Fantinuoli (Ed.), Interpreting and technology. Berlin: Language Science Press, 13–27. DOI logoGoogle Scholar
Díaz-Cintas, J. (2020). The name and nature of subtitling. In Ł. Bogucki & M. Deckert (Ed.), The Palgrave handbook of audiovisual translation and media accessibility. Cham: Palgrave Macmillan, 149–171. DOI logoGoogle Scholar
Díaz Cintas, J. & Remael, A. (2014). Audiovisual translation: Subtitling. Abingdon: Routledge. DOI logoGoogle Scholar
ritella, F. M. (2021). CAI tool-supported SI of numbers: A theoretical and methodological contribution. International Journal of Interpreter Education 14 (1), 32–56. DOI logoGoogle Scholar
Fujimoto, M. & Kawai, H. (2019). One-pass single-channel noisy speech recognition using a combination of noisy and enhanced features. Interspeech 2019, 486–490. DOI logoGoogle Scholar
Fuster, J. M. (2015). The prefrontal cortex (5th ed.). London: Academic Press. DOI logoGoogle Scholar
Gevins, A. & Smith, M. E. (2003). Neurophysiological measures of cognitive workload during human-computer interaction. Theoretical Issues in Ergonomics Science 4 (1–2), 113–131. DOI logoGoogle Scholar
Gile, D. (1999). Testing the Effort Model’s tightrope hypothesis in simultaneous interpreting — A contribution. Hermes 12 (23), 153–172. DOI logoGoogle Scholar
(2009). Basic concepts and models for interpreter and translator training (revised edition). Amsterdam: John Benjamins. DOI logoGoogle Scholar
Grabner, R. H., Brunner, C., Leeb, R., Neuper, C. & Pfurtscheller, G. (2007). Event-related EEG theta and alpha band oscillatory responses during language translation. Brain Research Bulletin 72 (1), 57–65. DOI logoGoogle Scholar
Hart, S. G. (2006). Nasa-Task Load Index (NASA-TLX); 20 years later. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 50 (9), 904–908. DOI logoGoogle Scholar
Johnson, E. B., Rees, E. M., Labuschagne, I., Durr, A., Leavitt, B. R., Roos, R. A. C., Reilmann, R., Johnson, H., Hobbs, N. Z., Langbehn, D. R., Stout, J. C., Tabrizi, S. J. & Scahill, R. I. (2015). The impact of occipital lobe cortical thickness on cognitive task performance: An investigation in Huntington’s Disease. Neuropsychologia 79 1, 138–146. DOI logoGoogle Scholar
Kafle, S. & Huenerfauth, M. (2016). Effect of speech recognition errors on text understandability for people who are deaf or hard of hearing. The 7th Workshop on Speech and Language Processing for Assistive Technologies (SLPAT 2016), 20–25. DOI logoGoogle Scholar
Kalina, S. (1992). Discourse processing and interpreting strategies — An approach to the teaching of interpreting. In C. Dollerup & A. Loddegaard (Ed.), Teaching translation and interpreting. Amsterdam: John Benjamins, 251–257. DOI logoGoogle Scholar
Klimesch, W., Schack, B. & Sauseng, P. (2005). The functional significance of theta and upper alpha oscillations. Experimental Psychology 52 (2), 99–108. DOI logoGoogle Scholar
Lee, S.-B. (2018). Exploring a relationship between students’ interpreting self-efficacy and performance: Triangulating data on interpreter performance assessment. The Interpreter and Translator Trainer 12 (2), 166–187. DOI logoGoogle Scholar
Lemhöfer, K. & Broersma, M. (2012). Introducing LexTALE: A quick and valid Lexical Test for Advanced Learners of English. Behavior Research Methods 44 (2), 325–343. DOI logoGoogle Scholar
Lenzo, K. (1993, 16 September). The CMU pronouncing dictionary. [URL]
Liao, S., Kruger, J.-L. & Doherty, S. (2020). The impact of monolingual and bilingual subtitles on visual attention, cognitive load, and comprehension. The Journal of Specialised Translation 33 (1), 70–98.Google Scholar
Lin, X. (2013). An empirical study on computer aided interpretation from English to Chinese Master’s thesis, Shandong Normal University. [URL]
Locke, E. A., Frederick, E., Lee, C. & Bobko, P. (1984). Effect of self-efficacy, goals, and task strategies on task performance. Journal of Applied Psychology 69 (2), 241–251. DOI logoGoogle Scholar
Ludersdorfer, P., Kronbichler, M. & Wimmer, H. (2015). Accessing orthographic representations from speech: The role of left ventral occipitotemporal cortex in spelling. Human Brain Mapping 36 (4), 1393–1406. DOI logoGoogle Scholar
Mackintosh, J. (2003). The AIIC workload study. Forum 1 (2), 189–214. DOI logoGoogle Scholar
Malakul, S. & Park, I. (2023). The effects of using an auto-subtitle system in educational videos to facilitate learning for secondary school students: Learning comprehension, cognitive load, and satisfaction. Smart Learning Environments 10 (1), 4. DOI logoGoogle Scholar
Mellinger, C. D. & Hanson, T. A. (2024, 15 June). Cognitive load scales in CTIS: A systematic review. The Third Meeting of the Bertinoro Translation Society (BTS3), Bertinoro, Italy.
Mognon, A., Jovicich, J., Bruzzone, L. & Buiatti, M. (2011). ADJUST: An automatic EEG artifact detector based on the joint use of spatial and temporal features. Psychophysiology 48 (2), 229–240. DOI logoGoogle Scholar
Nacimiento-García, E., González-González, C. S. & Gutiérrez-Vela, F. L. (2023). Automatic captions on video calls: A must for the older adults. Universal Access in the Information Society. DOI logoGoogle Scholar
Nomura, S., Mizuno, T., Nozawa, A., Asano, H. & Ide, H. (2009). Salivary cortisol as a new biomarker for a mild mental workload. 2009 International Conference on Biometrics and Kansei Engineering, 127–131. DOI logoGoogle Scholar
Orken, M., Dina, O., Keylan, A., Tolganay, T. & Mohamed, O. (2022). A study of transformer-based end-to-end speech recognition system for Kazakh language. Scientific Reports 12 (1), 8337. DOI logoGoogle Scholar
O’Sullivan, C. & Cornu, J.-F. (2018). History of audiovisual translation. In L. Pérez-González (Ed.), The Routledge handbook of audiovisual translation (pp. 15–30). Abingdon: Routledge. DOI logoGoogle Scholar
Paas, F. G. W. C. (1992). Training strategies for attaining transfer of problem-solving skill in statistics: A cognitive-load approach. Journal of Educational Psychology 84 (4), 429–434. DOI logoGoogle Scholar
Pisani, E. & Fantinuoli, C. (2021). Measuring the impact of automatic speech recognition on number rendition in simultaneous interpreting. In B. Zheng & C. Wang (Ed.), Empirical studies of translation and interpreting: The post-structuralist approach. Abingdon: Routledge, 181–197. DOI logoGoogle Scholar
Pöchhacker, F. (2004). Introducing interpreting studies. London/New York: Routledge. DOI logoGoogle Scholar
Prandi, B. (2018). An exploratory study on CAI tools in simultaneous interpreting: Theoretical framework and stimulus validation. In C. Fantinuoli (Ed.), Interpreting and technology. Berlin: Language Science Press, 29–59. DOI logoGoogle Scholar
Puma, S., Matton, N., Paubel, P.-V., Raufaste, É. & El-Yagoubi, R. (2018). Using theta and alpha band power to assess cognitive workload in multitasking environments. International Journal of Psychophysiology 123 1, 111–120. DOI logoGoogle Scholar
R Core Team. (2020). R: A language and environment for statistical computing. [URL]
Rinne, J. O., Tommola, J., Laine, M., Krause, B. J., Schmidt, D., Kaasinen, V., Teräs, M., Sipilä, H. & Sunnari, M. (2000). The translating brain: Cerebral activation patterns during simultaneous interpreting. Neuroscience Letters 294 (2), 85–88. DOI logoGoogle Scholar
Romero-Fresco, P. & Eugeni, C. (2020). Live subtitling through respeaking. In Ł. Bogucki & M. Deckert (Ed.), The Palgrave handbook of audiovisual translation and media accessibility. Cham: Palgrave Macmillan, 269–295. DOI logoGoogle Scholar
Scott, B. (2003). Automatic readability checker. Readability Formulas. [URL]
Seeber, K. G. (2011). Cognitive load in simultaneous interpreting: Existing theories — new models. Interpreting 13 (2), 176–204. DOI logoGoogle Scholar
(2017). Multimodal processing in simultaneous interpreting. In J. W. Schwieter & A. Ferreira (Ed.), The handbook of translation and cognition. Hoboken, NJ: Wiley, 461–475. DOI logoGoogle Scholar
Seeber, K. G., Keller, L. & Hervais-Adelman, A. (2020). When the ear leads the eye — the use of text during simultaneous interpretation. Language, Cognition and Neuroscience 35 (10), 1480–1494. DOI logoGoogle Scholar
Setton, R. (1999). Simultaneous interpretation: A cognitive-pragmatic analysis. Amsterdam: John Benjamins. DOI logoGoogle Scholar
Stone, J. V. (2002). Independent component analysis: An introduction. Trends in Cognitive Sciences 6 (2), 59–64. DOI logoGoogle Scholar
Sun, H., Li, K. & Lu, J. (2021). AI-assisted simultaneous interpreting: An experiment and its implications. Technology Enhanced Foreign Language Education 06 1, 75–80+86+12.Google Scholar
Szarkowska, A. & Gerber-Morón, O. (2019). Two or three lines: A mixed-methods study on subtitle processing and preferences. Perspectives 27 (1), 144–164. DOI logoGoogle Scholar
The BBC Academy. (2022, July). BBC subtitle guidelines. [URL]
Tran, Y., Craig, A., Craig, R., Chai, R. & Nguyen, H. (2020). The influence of mental fatigue on brain activity: Evidence from a systematic review with meta-analyses. Psychophysiology 57 (5). DOI logoGoogle Scholar
Van Rossum, G. & Drake, F. L. (2009). Python 3 reference manual. CreateSpace.Google Scholar
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. & Polosukhin, I. (2017). Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems, 6000–6010.Google Scholar
Wang, C., Wu, Y., Lu, L., Liu, S., Li, J., Ye, G. & Zhou, M. (2020). Low latency end-to-end streaming speech recognition with a scout network. Interspeech 2020, 2112–2116. DOI logoGoogle Scholar
Weiss, S. & Mueller, H. M. (2003). The contribution of EEG coherence to the investigation of language. Brain and Language 85 (2), 325–343. DOI logoGoogle Scholar
Williams, N. S., McArthur, G. M., de Wit, B., Ibrahim, G. & Badcock, N. A. (2020). A validation of Emotiv EPOC Flex saline for EEG and ERP research. PeerJ 8 1, e9713. DOI logoGoogle Scholar
Yuan, L. & Wang, B. (2023). Cognitive processing of the extra visual layer of live captioning in simultaneous interpreting: Triangulation of eye-tracked process and performance data. Ampersand 11 1, 100131. DOI logoGoogle Scholar
Zekveld, A. A., Kramer, S. E., Kessens, J. M., Vlaming, M. S. M. G. & Houtgast, T. (2009). The influence of age, hearing, and working memory on the speech comprehension benefit derived from an automatic speech recognition system. Ear & Hearing 30 (2), 262–272. DOI logoGoogle Scholar
Zhang, Y., Qin, J., Park, D. S., Han, W., Chiu, C.-C., Pang, R., Le, Q. V. & Wu, Y. (2020). Pushing the limits of semi-supervised learning for automatic speech recognition. DOI logoGoogle Scholar
Zhang, Z. (2019). Spectral and time-frequency analysis. In L. Hu & Z. Zhang (Ed.), EEG signal processing and feature extraction. Singapore: Springer, 89–116. DOI logoGoogle Scholar