Deaf and Hard-of-Hearing Perspectives on Imperfect Automatic Speech Recognition for Captioning One-on-One Meetings
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Recent advances in Automatic Speech Recognition (ASR) have made this technology a potential solution for transcribing audio input in real-time for people who are Deaf or Hard of Hearing (DHH). However, ASR is imperfect; users must cope with errors in the output. While some prior research has studied ASR-generated transcriptions to provide captions for DHH people, there has not been a systematic study of how to best present captions that may include errors from ASR software nor how to make use of the ASR system's word-level confidence. We conducted two studies, with 21 and 107 DHH participants, to compare various methods of visually presenting the ASR output with certainty values. Participants answered subjective preference questions and provided feedback on how ASR captioning could be used with confidence display markup. Users preferred captioning styles with which they were already most familiar (that did not display confidence information), and they were concerned about the accuracy of ASR systems. While they expressed interest in systems that display word confidence during captions, they were concerned that text appearance changes may be distracting. The findings of this study should be useful for researchers and companies developing automated captioning systems for DHH users.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Flesch, R. (1948) · Journal of Applied Psychology · doi:10.1037/h0057532 · Cited by 5,391 · cited 1×
“To analyze the reading complexity of our stimuli, we analyzed them using the Flesch-Kincaid [14] formula: the Flesch Reading-Ease Score was (FRES: mean=69.76, median=69.21 with SD=9.69) and the Flesch-Kincaid Grade Level was (FKGL: mean=8.6, median=8.73 with SD=2.28).”
MethodInfluentialThe microsoft 2016 conversational speech recognition system
Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M., Stolcke, A., Yu, D., & Zweig, G. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7953159 · Cited by 326
Toward Human Parity in Conversational Speech Recognition
Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M. L., Stolcke, A., Yu, D., & Zweig, G. (2017) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2756440 · Cited by 245
Ranking vs. Preference: A Comparative Study of Self-reporting
Yannakakis, G. N., & Hallam, J. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-24600-5_47 · Cited by 90
Improving Real-Time Captioning Experiences for Deaf and Hard of Hearing Students
Kawas, S., Karalis, G., Wen, T., & Ladner, R. E. (2016) · Proceedings of the 18th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/2982142.2982164 · Cited by 82
Cited by
Accessibility in Action: Co-Located Collaboration among Deaf and Hearing Professionals
Wang, E. Q., & Piper, A. M. (2018) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3274449 · Cited by 64
McDonnell, E. J., Liu, P., Goodman, S. M., Kushalnagar, R., Froehlich, J. E., & Findlater, L. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3479578 · Cited by 54
“, [7,28]) or in terms of a narrowly defined outcome (e.”
BackgroundWorking at the Intersection of Race, Disability and Accessibility
Harrington, C. N., Desai, A., Lewis, A., Moharana, S., Ross, A. S., & Mankoff, J. (2023) · The 25th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3597638.3608389 · Cited by 53
“As an example, an accessibility focused research project may focus on automated speech recognition and captioning technologies potential to support d/Deaf and hard-of-hearing individuals (e.g., [13, 83, 89, 106]).”
BackgroundSeita, M., Lee, S., Andrew, S., Shinohara, K., & Huenerfauth, M. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501843 · Cited by 52
“Motivated by work in ASR-captioning [7, 43, 44], we explore two design dimensions: • How errors in ASR output should be indicated and how to correct them: Prior work has revealed DHH participants are frustrated when there are errors in output [22], and are interested in error correction features…”
BackgroundMethodSelf-citationBerke, L., Albusays, K., Seita, M., & Huenerfauth, M. (2019) · Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290607.3312921 · Cited by 48
Self-citation
Metadata
- Authors
- Berke, L., Caulfield, C., & Huenerfauth, M.
- Venue
- Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility
- Publisher
- ACM
- Published
- 2017-10-19
- Pages
- 155-164
- OpenAlex
- W2765828580
- Cited by
- 62
- References
- 5
- FWCI
- 55.34
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.