The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Error correction of voicemail transcripts in SCANMail
Abstract
Despite its widespread use, voicemail presents numerous usability challenges: People must listen to messages in their entirety, they cannot search by keywords, and audio files do not naturally support visual skimming. SCANMail overcomes these flaws by automatically generating text transcripts of voicemail messages and presenting them in an email-like interface. Transcripts facilitate quick browsing and permanent archive. However, errors from the automatic speech recognition (ASR) hinder the usefulness of the transcripts. The work presented here specifically addresses these problems by evaluating user-initiated error correction of transcripts. User studies of two editor interfaces-a grammar-assisted menu and simple replacement by typing-reveal reduced audio playback times and an emphasis on editing important words with the menu, suggesting its value in mobile environments where limited input capabilities are the norm and user privacy is essential. The study also adds to the scarce body of work on ASR confidence shading, suggesting that shading may be more helpful than previously reported.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Transparency may erode confidence in a system, with users trusting it less, because transparency leads them to question the system even when it is correct [1,13,50].”
From Progressive Disclosure: When, Why, and How Do Users Want Algorithmic Transparency Information? (2020) · cites this paper as [13]
In the citing paper
“Furthermore, making accurate system predictions about emotions is also difficult, allowing us to examine a key challenge for intelligent systems: how to deal with system error [13,50,51,60].”
From Progressive Disclosure: When, Why, and How Do Users Want Algorithmic Transparency Information? (2020) · cites this paper as [13]
Citations
Cites
Moore, R. K. (1986) · Cited by 628
Taming recognition errors with a multimodal interface
Oviatt, S. (2000) · Communications of the ACM · doi:10.1145/348941.348979 · Cited by 299
Patterns of entry and correction in large vocabulary continuous speech recognition systems
Karat, C.-M., Halverson, C., Horn, D., & Karat, J. (1999) · Proceedings of the SIGCHI conference on Human factors in computing systems the CHI is the limit - CHI '99 · doi:10.1145/302979.303160 · Cited by 275
Multimodal 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 6×
“Multimodal input generally outperforms simple respeaking [12, 17].”
BackgroundMethodResultInfluentialSpeechSkimmer: a system for interactively skimming recorded speech
Arons, B. (1997) · ACM Transactions on Computer-Human Interaction · doi:10.1145/244754.244758 · Cited by 182
FILOCHAT: handwritten notes provide access to recorded conversations
Whittaker, S., Hyland, P., & Wiley, M. (1994) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/191666.191763 · Cited by 172
The audio notebook: paper and pen interaction with structured speech
Stifelman, L., Arons, B., & Schmandt, C. (2001) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/365024.365096 · Cited by 167
Moran, T. P., Palen, L. A., Harrison, S., Chiu, P., Kimber, D., Minneman, S., van Melle, W., & Zellweger, P. T. (1997) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/258549.258704 · Cited by 151
Recognition confidence scoring and its use in speech understanding systems
Hazen, T. J., Seneff, S., & Polifroni, J. H. (2002) · Computer Speech & Language · doi:10.1006/csla.2001.0183 · Cited by 149
Informedia: news-on-demand multimedia information acquisition and retrieval
Hauptmann, A. G., & Witbrock, M. (1997) · Cited by 143
Research works printed but not linked: 1
- 10.5555/1241889.1241901 · doi:10.5555/1241889.1241901
Cited by
Progressive Disclosure: When, Why, and How Do Users Want Algorithmic Transparency Information?
Springer, A., & Whittaker, S. (2020) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3374218 · Cited by 84
“Transparency may erode confidence in a system, with users trusting it less, because transparency leads them to question the system even when it is correct [1, 13, 50].”
BackgroundInfluentialOn the benefits of confidence visualization in speech recognition
Vertanen, K., & Kristensson, P. O. (2008) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/1357054.1357288 · Cited by 73
Kalnikaitė, V., Ehlen, P., & Whittaker, S. (2012) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/2145204.2145260 · Cited by 41
Zhou, Z., Li, Z., Zhang, Y., & Sun, L. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2093773 · Cited by 22
“Compared with an explanation that addresses transparency from a technical perspective (Burke et al., 2006; Choi, 2020; Lou et al., 2012), a human-centric explanation, which could foster the use of agents (Eslami et al., 2019), is preferred by users with low technical expertise (Cheng et al., 2019)…”
BackgroundPiquard-Kipffer, A., Mella, O., Miranda, J., Jouvet, D., & Orosanu, L. (2015) · Workshop on Speech and Language Processing for Assistive Technologies · doi:10.18653/v1/w15-5107 · Cited by 14
“Along this line, it is always words with low confidence scores tha are differentiated, either in a lighter shade for error correction in voicemail transcripts [11], or highlighted for computer assisted speech transcription [12], or displayed with an underlining dependent on the confidence measure [13].”
Simple gesture-based error correction interface for smartphone speech recognition
Yuan, L., Iwano, K., & Shinoda, K. (2014) · Interspeech (USB) · doi:10.21437/interspeech.2014-302 · Cited by 9
“Researches for speech recognition error correction can be divided into two categories: automatic error correction [16, 17, 18, 19] and semi-automatic error correction [5, 6, 7, 8].”
BackgroundMethodThird-party error detection support mechanisms for dictation speech recognition
Zhou, L., Shi, Y., & Sears, A. (2010) · Interacting with Computers · doi:10.1016/j.intcom.2010.02.002 · Cited by 8
A Contextual Study of Semantic Speech Editing in Radio Production
Baume, C., Plumbley, M. D., Ćalić, J., & Frohlich, D. M. (2018) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2018.03.006 · Cited by 8
Beyond errors: measuring reliability for error-prone interaction devices
Feng, J. H., & Sears, A. (2009) · Behaviour and Information Technology · doi:10.1080/01449290802196596 · Cited by 10
“These factors suggest that recognition errors are unlikely to be eliminated (Oviatt 2000) and recent studies confirm that recognition errors continue to pose significant problems in the context of dictation-oriented applications (Burke et al .”
BackgroundImproving Query Reformulation in Voice Search System
Sa, N. (2016) · Conference on Human Information Interaction and Retrieval · doi:10.1145/2854946.2854951 · Cited by 6
Investigating Critical Speech Recognition Errors in Spoken Short Messages
Pappu, A., Misu, T., & Gupta, R. K. (2016) · Signals and communication technology · doi:10.1007/978-3-319-21834-2_7 · Cited by 5
“[5, 8] proposed menubased error correction technique to resolve errors in transcriptions.”
MethodSun, L., Li, Z., Zhang, Y., Liu, Y., Lou, S., & Zhou, Z. (2021) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3411763.3451819 · Cited by 12
“However, compared with the prior works that address trans-parency from a technical perspective [15, 22, 57], the user-centric explanation, which could bring personal gains and foster the use of agents [35], is preferable by users with low technical expertise when faced with low-risk applications…”
BackgroundAn efficient error correction interface for speech recognition on mobile touchscreen devices
Liang, Y., Iwano, K., & Shinoda, K. (2014) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2014.7078617 · Cited by 5
“First, he/she marks one error word and then either selects its corresponding correct word from a candidate list provided by the interface [3, 4, 5, 6], or inputs the correct word by speech, handwriting, or virtual keyboard [7, 8, 9, 10].”
BackgroundDeconstructing Human-assisted Video Transcription and Annotation for Legislative Proceedings
Ruprechter, T., Khosmood, F., & Gütl, C. (2020) · Digital Government Research and Practice · doi:10.1145/3395316 · Cited by 4
“Even though audio tracks are a different media type than video, many audio transcription systems are similar to those handling video in that the initial text presented to the user is also created by automatic speech recognition [3, 6, 32, 60, 76].”
BackgroundWyant, K., Sant'Ana, S. J. K., Punturieri, C., Yu, J., Fronk, G. E., Maggard, C. M., Janssen, C., Wanta, S. E., Kornfield, R., Swol, L. M. V., et al. (2025) · JMIR Research Protocols · doi:10.2196/81697 · Cited by 2
“…in some instances, overly complex or otherwise detailed explanations of how a system works may erode confidence in that system because incremental feedback provides more information than necessary, reveals errors, or leads users to question the system even when it was correct [45,48,51,52,55-57].”
Kuhn, K., Kersken, V., & Zimmermann, G. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720038 · Cited by 5
“Previous studies have highlighted the limitations of then-current HMM-based confidence score implementations [57], called for further research [4, 55, 62], and hypothesised that improved confidence accuracy could enable practical applications [5].”
Error Correction Using Long Context Match for Smartphone Speech Recognition
Liang, Y., Iwano, K., & Shinoda, K. (2015) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2015edp7179 · Cited by 1
“In the system-initiated method, those words for which the system is less confident are highlighted [8] or appear in a shade [7].”
BackgroundMethodUseful transcriptions of webcast lectures
Munteanu, C. (2009) · TSpace (University of Toronto) · Cited by 2
Using Confidence Scores to Improve Eyes-free Detection of Speech Recognition Errors
Nowrin, S., & Vertanen, K. (2025) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3733155.3734896
“Speech error correction involves a two-step process: 1) detecting errors, and 2) correcting errors [28].”
Phan, T. (2014) · doi:10.70675/eb8a95b2zd929z489fza0a5zff06210685e5
“Based on space efficiency, our filters can be applied to deal with a wide range of common problems such as join operation in databases [4][5][6][27]; reconciliation and deduplication in networking and distributed systems [28][29][30][31], bioinformatics [32][33], as well as databases [34][35][36]; error-correction in…”
Method
Metadata
- Authors
- Burke, M., Amento, B., & Isenhour, P.
- Affiliations
- Carnegie Mellon University (US)
- AT&T (United States) (US)
- ORCID
- Burke, Moira
- Venue
- Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2006-04-22
- Pages
- 339-348
- OpenAlex
- W2004912959
- Cited by
- 21
- References
- 25
- Citations by year
- 2025: 3 · 2022: 1 · 2021: 1 · 2020: 2 · 2018: 1 · 2016: 2 · 2015: 3 · 2014: 3 · 2012: 1
- FWCI
- 0.79
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- voice mail, error correction, speech recognition errors, mobile usability, user privacy
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.