On the benefits of confidence visualization in speech recognition
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
In a typical speech dictation interface, the recognizer's best-guess is displayed as normal, unannotated text. This ignores potentially useful information about the recognizer's confidence in its recognition hypothesis. Using a confidence measure (which itself may sometimes be inaccurate), we investigated providing visual feedback about low-confidence portions of the recognition using shaded, red underlining. An evaluation showed, compared to a baseline without underlining, underlining low-confidence areas did not increase user's speed or accuracy in detecting errors. However, we found that when recognition errors were correctly underlined, they were discovered significantly more often than baseline. Conversely, when errors failed to be underlined, they were discovered less often. Our results indicate confidence visualization can be effective --- but only if the confidence measure has high accuracy. Further, since our results show that users tend to trust confidence visualization, designers should be careful in its application if a high accuracy confidence measure is not available.
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
The information capacity of the human motor system in controlling the amplitude of movement.
Fitts, P. M. (1954) · Journal of Experimental Psychology · doi:10.1037/h0055392 · Cited by 6,466 · cited 1×
“Fitts’ law [3] tells us that larger targets are faster to click than smaller (assuming same amplitude).”
BackgroundMultimodal error correction for speech user interfaces
Suhm, B., Myers, B., & Waibel, A. (2001) · ACM Transactions on Computer-Human Interaction · doi:10.1145/371127.371166 · Cited by 198 · cited 2×
“[8], they found no difference in the corrected words-per-minute achieved using an interface with confidence visualization and one without.”
BackgroundMethodError correction of voicemail transcripts in SCANMail
Burke, M., Amento, B., & Isenhour, P. (2006) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1124772.1124823 · Cited by 21
Cited by
A Review of User Interface Design for Interactive Machine Learning
Dudley, J. J., & Kristensson, P. O. (2018) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3185517 · Cited by 343
Self-citationFive Challenges for Intelligent Text Entry Methods
Kristensson, P. O., & Jameson, A. (2009) · AI Magazine · doi:10.1609/aimag.v30i4.2269 · Cited by 75
Self-citationKafle, S., Yeung, P., & Huenerfauth, M. (2019) · Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3308561.3353781 · Cited by 39
“Font Color ( color_r ) Ponce and Mayer [36]; Bold Face ( bold ) Rello et al. [39]; Background ( color_bg ) Chi et al. [12]; UPPERCASE ( uc ) Berger et al. [5] Underlining ( ul ) Vertanen et al. [44] Italicized ( it ) Berger et al. [5] Font Size ( size ) Wang et al. [46] Table 1.”
Background
Metadata
- Authors
- Vertanen, K., & Kristensson, P. O.
- Venue
- Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2008-04-06
- Pages
- 1497-1500
- OpenAlex
- W2118632343
- Cited by
- 73
- References
- 3
- FWCI
- 0.77
- 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.