An Analysis of the Errors in the Auto-Generated Captions of University Commencement Speeches on YouTube
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Auto-generated captions on YouTube have proven useful in helping viewers better understand the words being spoken. However, at times they fail to contain accurate captions. In these cases, they lead to confusion. The aim of this paper is to identify and analyze errors in the auto-generated captions of 20 commencement speeches on YouTube. These speeches were presented over a period of 12 years by speakers from different walks of life. The researchers selected ten male and ten female icons. Only the first 10 minutes of the speeches were utilized for this investigation. All the captioned errors were collected and analyzed. Upon completion of the analysis, it was discovered that the frequency of errors in each speech ranged between 10 and 46 cases, with an average of one error occurring about every 26 seconds. Among the different error categories, nouns record the highest number with 144 cases (31.3%). The second is verbs with 93 cases (20.2%), then prepositions with 37 cases (8.1%). Among the four subcategories, namely omission, addition, substitution, and word order, substitution recorded the highest amount of errors with 357 cases (77.6%). Furthermore, the errors were classified into two major groups. The first, involving function words, appeared in 169 cases (36.7%). The second, involving content words, appeared in 291 cases (63.3%). The results of this research suggest that a continuous development of the voice recognition software that automatically generates captions is necessary for more efficient and accurate data that will help viewers and listeners better comprehend the video contents.
Abstract
Auto-generated captions on YouTube have proven useful in helping viewers better understand the words being spoken. However, at times they fail to contain accurate captions. In these cases, they lead to confusion. The aim of this paper is to identify and analyze errors in the auto-generated captions of 20 commencement speeches on YouTube. These speeches were presented over a period of 12 years by speakers from different walks of life. The researchers selected ten male and ten female icons. Only the first 10 minutes of the speeches were utilized for this investigation. All the captioned errors were collected and analyzed. Upon completion of the analysis, it was discovered that the frequency of errors in each speech ranged between 10 and 46 cases, with an average of one error occurring about every 26 seconds. Among the different error categories, nouns record the highest number with 144 cases (31.3%). The second is verbs with 93 cases (20.2%), then prepositions with 37 cases (8.1%). Among the four subcategories, namely omission, addition, substitution, and word order, substitution recorded the highest amount of errors with 357 cases (77.6%). Furthermore, the errors were classified into two major groups. The first, involving function words, appeared in 169 cases (36.7%). The second, involving content words, appeared in 291 cases (63.3%). The results of this research suggest that a continuous development of the voice recognition software that automatically generates captions is necessary for more efficient and accurate data that will help viewers and listeners better comprehend the video contents.
참고문헌 (47)
- 안미리, "The Impact of Subtitled Online Video Clips on Incidental Vocabulary Learning", 영상영어교육, 14(2), pp.135~151 (2013), 영상영어교육학회[DOI]
- Afshin, H., "A contrastive analysis of machine translation (Google Translate) and human translation: Efficacy in translating verb tense from English to Persian", Mediterranean Journal of Social Sciences, 7(4), pp.40~48 (2016)
- Aslerasouli, P., "Comparison of Google online translation and human translation with regard to soft vs. hard science texts", Journal of Applied Linguistics and Language Research, 2(3), pp.169~184 (2015)
- Bahri, H., "Google Translate as a supplementary tool for learning Malay : A case study at Universiti Sains Malay", Advances in Language and Literary Studies, 7(3), pp.161~167 (2016)
- Baker, M., "Routledge encyclopedia of translation studies" (2001), Routledge
- Brasel S. A., "Enhancing television advertising: Same-language subtitles can improve brand recall, verbal memory, and behavioral intent", Journal of the Academy of Marketing Science, 42(3), pp.322~336 (2014)
- Briggs, N., "Neural machine translation tools in the language learning classroom: Students’ use, perceptions, and analyses", The JALT CALL Journal, 14(1), pp.23~24 (2018)
- Caimi, A., "Audiovisual translation and language learning: The promotion of intralingual subtitles", The Journal of Specialized Translation, 6, pp.85~97 (2006)
- "Smartphone speech recognition can write text messages there times faster than human typing" (2016)[URL]
- Cha, K. W., "A study of impediments in listening to English news broadcasts", English Teaching, 55(1), pp.101~225 (2000)
- Chen, A. H., "EFL listeners’ strategy development and listening problems : A process-based study", The Journal of Asia TEFL, 10(3), pp.81~101 (2013)
- Chen, H. C., "Judgments of intelligibility and foreign accent by listeners of different language backgrounds", The Journal of Asia TEFL, 8(4), pp.61~83 (2011)
- Choi, Y. H., "A commencement address from the American college of honorary" (2016), Jonghap Books
- Clossen, A., "Beyond the letter of the law: Accessibility, universal design, and human centered design in video tutorials", Pennsylvania Libraries : Research & Practice, 2(1), pp.27~37 (2014)
- Danan, M., "Captioning and subtitling : Undervalued language learning strategies", Erudite, 49(1), pp.67~77 (2004)
- Doherty, S., "Translation quality assessment", pp.179~197 (2018), Springer
- "What is the difference between open and closed captioning?" (2019)[URL]
- "Captions and subtitles: Do you know the difference?" (2016)[URL]
- Gemsbacher, M. A., "Video captions benefit everyone", Policy Insights Behave Science, 2(1), pp.195~202 (2017)
- Ghasemi, H., "A comparative study of Google translate translations : An error analysis of English-to-Persian and Persian-to-English translations", English Language Teaching, 9(3), pp.13~17 (2016)
- Guan, C., "Did we overlook the visual context in bilingually subtitled movies?", Paper presented at the 16th Asia TEFL 1st MAAL & 6th HAAL 2018 International Conference: English Language Teaching in the Changing Glocalised World: Research and Praxis (2018), University of Macau
- 한정림, "인공지능 음성인식 기반 스피킹 서비스 제공 방안 연구", 초등영어교육, 25(2), pp.109~125 (2019), 한국초등영어교육학회[DOI]
- Hardmeier, C., "Pronoun translation in English-French machine translation: An analysis of error types", Computer Science (2018)
- Hinkin, M. P., "Verbal redundancy aids memory for filmed entertainment dialogue", The Journal of Psychology, 148(2), pp.161~176 (2014)
- Igareda, P., "Developing a learning platform for AVT : Challenges and solutions", JoSTrans, 16, pp.145~162 (2011)
- Johnson, A, "Video captioning policy and compliance at the University of Minnesota at Duluth", master, pp.2014
- Koskinen, P. S., "Closed-captioned television : A new technology for enhancing reading skills of learning disabled students", Spectrum, 4(2), pp.9~13 (1986)
- "Caption it yourself" (2019)[URL]
- Lee, G. S., "Speech recognition" (2001), Hanyang University Press
- 이정화, "A Study on the Effectiveness of Machine Translators for University Freshmen in Translating Korean Writing into English", 학습자중심교과교육연구, 19(8), pp.155~180 (2019), 학습자중심교과교육학회[DOI]
- 이정화, "An Analysis of Korean-English Translation Errors in Google Translate", 언어과학연구, (89), pp.221~257 (2019), 언어과학회[DOI]
- 이제영, "Effects of Using Subtitles of Video Contents on L2 Learners’ Listening and Vocabulary Development: A Meta-Analysis", 응용언어학, 33(2), pp.137~158 (2017), 한국응용언어학회
- Li, H., "Comparison of Google translation with human translation", FLAIRS Conference (2014)
- Markham, P. L., "The effects of captioned television videotapes on the listening comprehension of beginning, intermediate, and advanced ESL students", Educational Technology, 29(10), pp.38~41 (1989)
- "Foreign subtitles help but native-language subtitles harm foreign speech perception" (2009)[URL]
- Elisabet Titik Murtisari, "Google T ranslate in Language Learning : I ndonesian EFL Students’ Attitudes", Journal of Asia TEFL, 16(3), pp.978~986 (2019), 아시아테플
- 박옥수, "한영 기계 번역에서 ST의 유형적 특징에 따른 번역 오류 분석", 동아인문학, (41), pp.155~183 (2017), 동아인문학회
- Parton, B., "Video captions for online courses: Do you tube’s auto-generated captions meet deaf students’ needs?", Journal of Open, Flexible, and Distance Learning, 20(1), pp.8~18 (2016)
- Ranchal, R., "Using speech recognition for real-time captioning and lecture transcription in the classroom", IEEE Transactions on Learning Technologies, 6(4), pp.299~311 (2013)
- Shin, D. L., "Using videotaped lectures for testing academic listening proficiency", International Journal of Listening, 12(1), pp.57~80 (1998)
- 서정예, "유튜브 K-뷰티 콘텐츠 자막 번역 연구", 번역학연구, 20(1), pp.127~155 (2019), 한국번역학회[DOI]
- Tatman, R., "Speaker dialect is a necessary feature to model perceptual accent adaptation in humans", 4th Pacific Northwest Regional NLP Workshop: NW-NLP 2016 (2016)
- Teng, F., "Maximizing the potential of captions for primary school ESL students’ comprehension of English-language videos", Computer Assisted Language Learning, 32(7), pp.665~691 (2019)
- 윤상돈, "자막의 종류에 대한 학습자의 선험 학습 경험이영어 읽기 및 듣기 능력에 미치는 영향: 뉴스룸 시즌 1 자막을 중심으로", 영상영어교육, 19(3), pp.65~82 (2018), 영상영어교육학회[DOI]
- 유도형, "선출력(output-first) 활동 실행을 위한 영화자막의 실효성: 영화 유 어게인을 이용하여", 영상영어교육, 14(1), pp.119~136 (2013), 영상영어교육학회[DOI]
- Vidhaysasai, T., "Investigating the use of Google Translate in "terms and conditions" in an airline's official website: Errors and implications", Journal of Language Teaching and Learning in Thailand, 49, pp.137~169 (2015)
- Vilar, D., "Error analysis of statistical machine translation output", Proceedings of the Fifth International Conference on Language Resources and Evaluation, pp.697~702 (2006)