The DOI matches its Crossref record; 74 of the 74 references it cites were found in a registry or an index; 28 of the 158 sources its claims cite were checked for support.
System and User Strategies to Repair Conversational Breakdowns of Spoken Dialogue Systems: A Scoping Review
Open accessAbstract
Spoken Dialogue Systems (SDSs) are critical in facilitating natural and efficient human-machine interaction through speech. SDSs frequently encounter challenges in managing complex dialogues, resulting in communication breakdowns, which include misunderstandings— where the system misunderstands user input— and non-understandings— where the system fails to interpret the input at all. Strategies to repair these breakdowns have been investigated across multiple disciplines; despite this interest, the findings from these studies are inconsistent and hinder comparative analysis due to the use of diverse methodologies and terminologies. To address this gap, this scoping review systematically examines SDS and user repair strategies within a broad spectrum of literature. Based on 36 papers out of 818 found, we provide two comprehensive frameworks: one categorising SDS system-repair strategies into six distinct categories and the other user-repair strategies into five categories. Our analysis reveals a disparity in the literature’s focus on repair strategies, highlighting, in particular, the lack of research on less explored strategies, such as Information and Disclosure repair strategies, providing potential avenues for future research directions in this area.
Overview
CoChat Summary
TL;DR
This scoping review synthesizes 36 papers, selected from 818 found, on repair strategies for conversational breakdowns in spoken dialogue systems (SDSs). It proposes frameworks categorizing system-repair strategies into six categories and user-repair strategies into five categories, while highlighting uneven research coverage and terminology inconsistencies.
Key findings
- From 36 included papers, system-repair strategies are categorized into six types: confirmation, information, social, solve, ask, and disclosure; user-repair strategies into five: clarification, information adjustment, modulation, system-centric, and user adaptation.
- Most system-repair studies focused on confirmation, asking, and social strategies; only N=3 studies focused on information repair strategies, and there was a complete absence of studies investigating disclosure as a repair strategy.
- For user-repair, clarification and information strategies were more common, while modulation, system-centric, and user adaptation strategies were notably under-explored; clarification strategies such as repetition and reformulation were the most widely employed, but repetition and modulation were often least successful and could negatively impact SDS recognition.
- Methodologically, the majority of studies were mixed-method (N=16), followed by qualitative (N=10) and quantitative (N=10); field-collected corpora (N=11) and lab-collected corpora (N=10) were common, as were between-subject (N=10) and within-subject (N=10) experiments. Sample sizes ranged from 5 to 850 participants; English was the most prevalent language (N=16) and the United States the most common location (N=16).
Methods
- Scoping review following PRISMA-ScR and Arksey & O’Malley’s framework; searched ACM Digital Library, IEEE Xplore, Scopus, and Web of Science up to August 2023, yielding 818 papers, reduced to 505 after duplicate removal, then 128 after title/abstract screening, 17 eligible from database search, plus 19 from backward/forward chaining, for 36 included papers.
- Inclusion criteria: user studies examining strategies to repair or mitigate breakdowns in SDSs; voice-based interactions primarily; at least one user and one SDS; original peer-reviewed journal or full-length conference papers. Exclusion criteria included non-English publications, multimodal interactions where voice was not primary, purely technical error-handling studies, and dissertations/review articles/conference abstracts.
- Data were charted and strategies categorized by function and objective, adapting existing frameworks where applicable; studies were classified as qualitative, quantitative, or mixed-method.
Limitations
- The authors state that reliance on predefined frameworks may not fully account for the multifaceted nature of repair strategies; categorization was subjective and compounded by terminology inconsistencies; combined repair strategies blurred category distinctions; and the review was limited to four databases, predefined search terms, and inclusion criteria.
- The authors also state that the review aimed to map strategies rather than evaluate their effectiveness on user experience or SDS performance.
- Evident from the text: many field-collected corpora were pre-2009 and telephone-based; studies were predominantly Western and English-language; most examined single-session, single-language, disembodied SDS interactions, limiting generalizability to current and culturally diverse SDS contexts.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
22 Valid · 6 Not valid · 54 Not checked · 73 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Centred on the main dialogue actor in the breakdown-repairing process, research in repair strategies has been broadly divided into two areas: investigations into system-repair strategies and studies on user-repair strategies [10, 16].”
What the sources say
- Not checked — no full text of the sourcecites [10] [10] Marie-Luce Bourguet. 2006. Towards a taxonomy of error-handling strategies in recognition-based multi-modal human-computer interfaces. Signal Processing 86, 12 (2006), 3625-3643. - source
- Could not verifycites [16] [16] Leigh Clark, Philip Doyle, Diego Garaialde, Emer Gilmartin, Stephan Schlögl, Jens Edlund, Matthew Aylett, João Cabral, Cosmin Munteanu, Justin Edwards, et al. 2019. The state of speech in HCI: Trends, themes and challenges. Interacting with computers 31, 4 (2019), 349-371. Essam Alghamdi, Martin Halvey, and Emma Nicol - sourceExperimental — accuracy not yet measured
Section 5.1 (pp. 9–10) divides the speech-HCI papers reviewed into usability/theory-based research and system-experience research, not categories of repair strategies. Searches for repair strategies and breakdown repair found no passage in our copy addressing the claimed system-repair versus user-repair division. (LLM, conf=0.72)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Research shows the effectiveness of system-repair strategies is stronger when combined with other strategies as a multiple-repair strategy [37, 77].”
What the sources say
- Partly supportedcites [37] [37] Esther S Kox, José H Kerstholt, Tom F Hueting, and Peter W de Vries. 2021. Trust repair in human-agent teams: the effectiveness of explanations and expressing regret. Autonomous agents and multi-agent systems 35, 2 (2021), 30. - sourceExperimental — accuracy not yet measured
The Results (§3.2 Trust) and Discussion (§4) report stronger trust recovery when the agent combined an explanation with an expression of regret than when it expressed regret alone. The paper tested those specific apology components in a human–agent team; it does not establish that system-repair strategies generally become more effective whenever they are combined with other strategies. (LLM, conf=0.81)
- Not checked — no full text of the sourcecites [77] [77] Sihan Yuan, Birgit Brüggemeier, Stefan Hillmann, and Thilo Michael. 2020. User preference and categories for error responses in conversational user interfaces. In Proceedings of the 2nd Conference on Conversational User Interfaces . 1-8. - source
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Four studies we reviewed investigated user-repair strategies specifically focused on lexical adjustments (when users modify vocabulary), semantic adjustments (when users alter the meaning of the original statement) and syntactic adjustments (when users restructure sentences; e.g. [30, 46]).”
What the sources say
- Not checked — no full text of the sourcecites [30] [30] Mohit Jain, Ramachandra Kota, Pratyush Kumar, and Shwetak N Patel. 2018. Convey: Exploring the use of a context view for chatbots. In Proceedings of the 2018 chi conference on human factors in computing systems . 1-6. - source
- Supportedcites [46] [46] Lina Mavrina, Jessica Szczuka, Clara Strathmann, Lisa Michelle Bohnenkamp, Nicole Krämer, and Stefan Kopp. 2022. 'Alexa, You're Really Stupid': A Longitudinal Field Study on Communication Breakdowns Between Family Members and a Voice Assistant. Frontiers in Computer Science 4 (2022), 791704. - source
Section 3.3.2 says the study investigated users’ repair strategies, and the Discussion (section 5; page unavailable) describes users varying the semantic, syntactical, and lexical content of their utterances. This supports citing the paper as an example of a study of those adjustments; the count of four reviewed studies belongs to the citing authors’ review, not to this source. (LLM, conf=0.91)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Recent studies, particularly those produced in the past five years, have shown increased interest in exploring modulation strategies across various domains and settings, primarily through the analysis of lab-collected corpora (e.g. [35, 46, 53]).”
What the sources say
- Not checked — no full text of the sourcecites [35] [35] Sujeong Kim, David Salter, Luke DeLuccia, and Amir Tamrakar. 2020. Study on text-based and voice-based dialogue interfaces for human-computer interactions in a blocks world. In Proceedings of the 8th International Conference on HumanAgent Interaction . 227-229. - source
- Partly supportedcites [46] [46] Lina Mavrina, Jessica Szczuka, Clara Strathmann, Lisa Michelle Bohnenkamp, Nicole Krämer, and Stefan Kopp. 2022. 'Alexa, You're Really Stupid': A Longitudinal Field Study on Communication Breakdowns Between Family Members and a Voice Assistant. Frontiers in Computer Science 4 (2022), 791704. - sourceExperimental — accuracy not yet measured
Section 3.3.2 studies users’ repair strategies, so this 2022 paper is an example of recent research on how people modify their speech after communication breakdowns. But the Introduction and section 3.1 describe a five-week study of families using Alexa at home, with conversations retrieved from Alexa logs—not a lab-collected corpus. The paper does not establish the claimed broader increase in research interest across domains. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [53] [53] Chelsea Myers, Anushay Furqan, Jessica Nebolsky, Karina Caro, and Jichen Zhu. 2018. Patterns for how users overcome obstacles in voice user interfaces. In Proceedings of the 2018 CHI conference on human factors in computing systems . 1-7. - source
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“These studies found that in correction and non-correction dialogue acts, the prosodic elements of user utterances typically shift towards hyper-articulated speech patterns.”
What the sources say
- Not checked — no full text of the sourcecites [35] [35] Sujeong Kim, David Salter, Luke DeLuccia, and Amir Tamrakar. 2020. Study on text-based and voice-based dialogue interfaces for human-computer interactions in a blocks world. In Proceedings of the 8th International Conference on HumanAgent Interaction . 227-229. - source
- Partly supportedcites [46] [46] Lina Mavrina, Jessica Szczuka, Clara Strathmann, Lisa Michelle Bohnenkamp, Nicole Krämer, and Stefan Kopp. 2022. 'Alexa, You're Really Stupid': A Longitudinal Field Study on Communication Breakdowns Between Family Members and a Voice Assistant. Frontiers in Computer Science 4 (2022), 791704. - sourceExperimental — accuracy not yet measured
Section 2.2 reports that earlier studies observed hyperarticulation or prosodic changes as common user strategies, especially after speech-recognition errors. It does not establish that utterances typically shift toward hyper-articulated speech in both correction and non-correction dialogue acts. In this paper’s own data, changes in articulation were the least-used repair-strategy group (Section 3.3.2). Page numbers are unavailable in our copy. (LLM, conf=0.88)
- Not checked — no full text of the sourcecites [53] [53] Chelsea Myers, Anushay Furqan, Jessica Nebolsky, Karina Caro, and Jichen Zhu. 2018. Patterns for how users overcome obstacles in voice user interfaces. In Proceedings of the 2018 CHI conference on human factors in computing systems . 1-7. - source
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
65 more claims · 1 with their cited sources checked
Create a free account to see all 155 claims and every source verdict.
- It may state two separate claims as one. 48
- The quote only partly states this claim. 2
- Probably not a substantial claim. 53
- Borderline: one of the tests for a substantial claim is unclear. 2
Citations
Cites
Scoping studies: towards a methodological framework
Arksey, H., & O'Malley, L. (2005) · International Journal of Social Research Methodology · doi:10.1080/1364557032000119616 · Cited by 36,742
Munn, Z., Peters, M. D. J., Stern, C., Tufanaru, C., McArthur, A., & Aromataris, E. (2018) · BMC Medical Research Methodology · doi:10.1186/s12874-018-0611-x · Cited by 11,385
Nass, C., Steuer, J., & Tauber, E. R. (1994) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/191666.191703 · Cited by 2,148 · cited 1×
“Grounded in the Computers Are Social Actors (CASA) paradigm, these strategies embody a range of human-like qualities through various responses, including apologies and compensatory strategies [55].”
Daudt, H. M., van Mossel, C., & Scott, S. J. (2013) · BMC Medical Research Methodology · doi:10.1186/1471-2288-13-48 · Cited by 1,891
Luger, E., & Sellen, A. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858288 · Cited by 1,176
Understanding scoping reviews: Definition, purpose, and process
Peterson, J., Pearce, P. F., Ferguson, L. A., & Langford, C. A. (2017) · Journal of the American Association of Nurse Practitioners · doi:10.1002/2327-6924.12380 · Cited by 740
Voice Interfaces in Everyday Life
Porcheron, M., Fischer, J. E., Reeves, S., & Sharples, S. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174214 · Cited by 717 · cited 7×
“Importantly, the selection of user-repair strategies is not random but is significantly influenced by the system’s repair strategies [43, 50, 60, 61].”
BackgroundInfluentialHarnessing the power of llms in practice: a survey on chatGPT and beyond
Yang, J., Jin, H., Tang, R., Han, X., Feng, Q., Jiang, H., Zhong, S., Yin, B., & Hu, X. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3649506 · Cited by 644
Nass, C., Steuer, J., & Tauber, E. R. (1994) · Conference companion on Human factors in computing systems - CHI '94 · doi:10.1145/259963.260288 · Cited by 579
Relational agents: a model and implementation of building user trust
Bickmore, T., & Cassell, J. (2001) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/365024.365304 · Cited by 479
The impact of chatbot conversational skill on engagement and perceived humanness
Schuetzler, R. M., Grimes, G. M., & Scott Giboney, J. (2020) · Journal of Management Information Systems · doi:10.1080/07421222.2020.1790204 · Cited by 357 · cited 1×
“Evidence suggests that a conversational agent’s self-disclosure as a computer artefact can efficiently set user expectations by acknowledging its non-human intelligence [64].”
Background"What can i help you with?": infrequent users' experiences of intelligent personal assistants
Cowan, B. R., Pantidi, N., Coyle, D., Morrissey, K., Clarke, P., Al-Shehri, S., Earley, D., & Bandeira, N. (2017) · Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services · doi:10.1145/3098279.3098539 · Cited by 351
Communication Breakdowns Between Families and Alexa
Beneteau, E., Richards, O. K., Zhang, M., Kientz, J. A., Yip, J., & Hiniker, A. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300473 · Cited by 313 · cited 7×
“A number of studies (N=7) favoured semi-structured interviews [19, 34, 42, 50, 53, 77, 78] while others chose structured interviews [2] or did not specify interview format [6, 67].”
BackgroundMethodInfluentialResilient Chatbots: Repair Strategy Preferences for Conversational Breakdowns
Ashktorab, Z., Jain, M., Liao, Q. V., & Weisz, J. D. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300484 · Cited by 224
Effects of communication style and culture on ability to accept recommendations from robots
Rau, P. L. P., Li, Y., & Li, D. (2009) · Computers in Human Behavior · doi:10.1016/j.chb.2008.12.025 · Cited by 221
Patterns for How Users Overcome Obstacles in Voice User Interfaces
Myers, C., Furqan, A., Nebolsky, J., Caro, K., & Zhu, J. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173580 · Cited by 213 · cited 10×
“Recent studies, particularly those produced in the past five years, have shown increased interest in exploring modulation strategies across various domains and settings, primarily through the analysis of lab-collected corpora (e.g. [35, 46, 53]).”
BackgroundMethodInfluentialThe State of Speech in HCI: Trends, Themes and Challenges
Clark, L., Doyle, P., Garaialde, D., Gilmartin, E., Schlögl, S., Edlund, J., Aylett, M., Cabral, J., Munteanu, C., Edwards, J., et al. (2019) · Interacting with Computers · doi:10.1093/iwc/iwz016 · Cited by 193 · cited 3×
“For the current review, the list of terms was derived directly from similar papers that performed systematic reviews on speech-based and conversational interfaces [7, 16, 52].”
BackgroundMethodSong, M., Zhang, H., Xing, X., & Duan, Y. (2023) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2023.103323 · Cited by 153
Doing research on a deployed spoken dialogue system: one year of let's go! experience
Raux, A., Bohus, D., Langner, B., Black, A. W., & Eskénazi, M. (2006) · Interspeech (USB) · doi:10.21437/interspeech.2006-17 · Cited by 153
Krämer, N. C., von der Pütten, A., & Eimler, S. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-25691-2_9 · Cited by 135 · cited 1×
“These interactions often mirror human face-to-face interactions, as demonstrated by models based on Human-Human Interaction (HHI) theories [39].”
Method(2017) · doi:10.1145/2998181.2998298 · Cited by 131
Virtual Assistance in Any Context: A Taxonomy of Design Elements for Domain-Specific Chatbots
Janssen, A., Passlick, J., Cardona, D. R., & Breitner, M. H. (2020) · Business & Information Systems Engineering · doi:10.1007/s12599-020-00644-1 · Cited by 117
Trust in Human-AI Interaction: Scoping Out Models, Measures, and Methods
Ueno, T., Sawa, Y., Kim, Y., Urakami, J., Oura, H., & Seaborn, K. (2022) · Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491101.3519772 · Cited by 91
Jokinen, K., & McTear, M. (2009) · Synthesis lectures on human language technologies · doi:10.2200/s00204ed1v01y200910hlt005 · Cited by 84
Trust repair in human-agent teams: the effectiveness of explanations and expressing regret
Kox, E. S., Kerstholt, J. H., Hueting, T. F., & de Vries, P. W. (2021) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-021-09515-9 · Cited by 83 · cited 2×
“Research shows the effectiveness of system-repair strategies is stronger when combined with other strategies as a multiple-repair strategy [37, 77].”
BackgroundJanssen, C. P., & Netherlands, A. '. 1. I. C. O. A. U. I. A. I. V. A. 2. U. (2019) · doi:10.1145/3349263 · Cited by 81
Convey: Exploring the Use of a Context View for Chatbots
Jain, M., Kota, R., Kumar, P., & Patel, S. N. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174042 · Cited by 74
Why doesn't it work?: voice-driven interfaces and young children's communication repair strategies
Cheng, Y., Yen, K., Chen, Y., Chen, S., & Hiniker, A. (2018) · Proceedings of the 17th ACM Conference on Interaction Design and Children · doi:10.1145/3202185.3202749 · Cited by 69
When Robot (Vs. Human) Employees Say “Sorry” Following Service Failure
Wang, X., Hwang, Y., & Guchait, P. (2023) · International Journal of Hospitality & Tourism Administration · doi:10.1080/15256480.2021.2017812 · Cited by 60
Arnold, A., Kolody, S., Comeau, A., & Miguel Cruz, A. (2024) · Disability and Rehabilitation: Assistive Technology · doi:10.1080/17483107.2022.2065369 · Cited by 59
Pérez-Marín, D. (2021) · Digital · doi:10.3390/digital1010002 · Cited by 57
Characterizing and Predicting Corrections in Spoken Dialogue Systems
Litman, D., Hirschberg, J., & Swerts, M. (2006) · Computational Linguistics · doi:10.1162/coli.2006.32.3.417 · Cited by 56
Analysis of user behavior under error conditions in spoken dialogs
Shin, J., Narayanan, S. S., Gerber, L., Kazemzadeh, A., & Byrd, D. (2002) · 7th International Conference on Spoken Language Processing (ICSLP 2002) · doi:10.21437/icslp.2002-567 · Cited by 54 · cited 9×
“For example, around 75% (8 out of 11) of the studies published before 2011 primarily focused on analysing audio corpora from real-world environments in order to explore system-repair and user-repair strategies in communication breakdowns in SDSs (e.g. [66]).”
BackgroundMethodResultInfluentialOwning Mistakes Sincerely: Strategies for Mitigating AI Errors
Mahmood, A., Fung, J. W., Won, I., & Huang, C.-M. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517565 · Cited by 52
My Bad! Repairing Intelligent Voice Assistant Errors Improves Interaction
Cuadra, A., Li, S., Lee, H., Cho, J., & Ju, W. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3449101 · Cited by 52 · cited 3×
“A number of studies (N=7) favoured semi-structured interviews [19, 34, 42, 50, 53, 77, 78] while others chose structured interviews [2] or did not specify interview format [6, 67].”
BackgroundMethodMavrina, L., Szczuka, J., Strathmann, C., Bohnenkamp, L. M., Krämer, N., & Kopp, S. (2022) · Frontiers in Computer Science · doi:10.3389/fcomp.2022.791704 · Cited by 43
Essentials of Qualitatively-Driven Mixed-Method Designs
(2016) · doi:10.4324/9781315543406 · Cited by 43
Identifying user corrections automatically in spoken dialogue systems
Hirschberg, J., Litman, D., & Swerts, M. (2001) · Second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies 2001 - NAACL '01 · doi:10.3115/1073336.1073363 · Cited by 40
Dippold, D. (2023) · Journal of Pragmatics · doi:10.1016/j.pragma.2022.12.004 · Cited by 37
Error-correction detection and response generation in a spoken dialogue system
Bulyko, I., Kirchhoff, K., Ostendorf, M., & Goldberg, J. (2005) · Speech Communication · doi:10.1016/j.specom.2004.09.009 · Cited by 36
What's The Talk on VUI Guidelines? A Meta-Analysis of Guidelines for Voice User Interface Design
Murad, C., Candello, H., & Munteanu, C. (2023) · Proceedings of the 5th International Conference on Conversational User Interfaces · doi:10.1145/3571884.3597129 · Cited by 36
(2008) · doi:10.1007/978-1-4020-6821-8_6 · Cited by 36
Bourguet, M.-L. (2006) · Signal Processing · doi:10.1016/j.sigpro.2006.02.047 · Cited by 30
Kim, J., Jeong, M., & Lee, S. C. (2019) · Proceedings of the 11th International Conference on Automotive User Interfaces and Interactive Vehicular Applications: Adjunct Proceedings · doi:10.1145/3349263.3351513 · Cited by 29
Huang, B., & Sénécal, S. (2023) · The Service Industries Journal · doi:10.1080/02642069.2023.2208522 · Cited by 27 · cited 6×
“By contrast, studies within the customer service domain utilised telephones [9, 11, 15, 27, 32, 66] or computer speakers [29, 38].”
BackgroundMethodResultInfluentialChen, C., Lifset, E. T., Han, Y., Roy, A., Hogarth, M., Moore, A. A., Farcas, E., & Weibel, N. (2023) · The 25th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3597638.3608378 · Cited by 25
Lin, W., Chen, H.-C., & Yueh, H.-P. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.785815 · Cited by 21 · cited 9×
“A number of studies (N=7) favoured semi-structured interviews [19, 34, 42, 50, 53, 77, 78] while others chose structured interviews [2] or did not specify interview format [6, 67].”
BackgroundMethodInfluential“I Didn’t Catch That, But I’ll Try My Best”: Anticipatory Error Handling in a Voice Controlled Game
Zargham, N., Pfau, J., Schnackenberg, T., & Malaka, R. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502115 · Cited by 20
Making it easier for older people to talk to smart homes: the effect of early help prompts
Wolters, K. M., Engelbrecht, K.-P., Gödde, F., Möller, S., Naumann, A., & Schleicher, R. (2010) · Universal Access in the Information Society · doi:10.1007/s10209-009-0184-x · Cited by 18 · cited 2×
“Certain domains are aligned with particular platform types, indicating specialised applications e.g. the smart home assistance domain was associated with devices such as Amazon Alexa [6, 17, 19, 33, 46, 60], the INSPIRE system [74], and devices not specified [38].”
BackgroundUser Preference and Categories for Error Responses in Conversational User Interfaces
Yuan, S., Brüggemeier, B., Hillmann, S., & Michael, T. (2020) · Proceedings of the 2nd Conference on Conversational User Interfaces · doi:10.1145/3405755.3406126 · Cited by 16
Do Smart Speakers Respond to Their Errors Properly? A Study on Human-Computer Dialogue Strategy
Ge, X., Li, D., Guan, D., Xu, S., Sun, Y., & Zhou, M. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-23541-3_32 · Cited by 15
Xu, Z., Wang, G., Zhai, S., & Liu, P. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2023.2176986 · Cited by 12
Exploring Humor as a Repair Strategy During Communication Breakdowns with Voice Assistants
Clausen, M., Kyhn, M. P., Papachristos, E., & Merritt, T. (2023) · Proceedings of the 5th International Conference on Conversational User Interfaces · doi:10.1145/3571884.3597127 · Cited by 12
Opfermann, C., & Pitsch, K. (2017) · 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN) · doi:10.1109/roman.2017.8172319 · Cited by 12 · cited 4×
“Finally, participants’ ages varied considerably, from as young as three years old [14] to as old as 92 years old [57].”
BackgroundInfluentialAlloatti, F., Grasso, F., Ferrod, R., Siragusa, G., Di, L., & Cena, F. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2023.101603 · Cited by 12
Task Automation Intelligent Agents: A Review
Wali, A., Mahamad, S., & Sulaiman, S. (2023) · Future Internet · doi:10.3390/fi15060196 · Cited by 11
“Try, Try, Try Again:” Sequence Analysis of User Interaction Data with a Voice User Interface
Myers, C. M., Laris Pardo, L. F., Acosta-Ruiz, A., Canossa, A., & Zhu, J. (2021) · CUI 2021 - 3rd Conference on Conversational User Interfaces · doi:10.1145/3469595.3469613 · Cited by 10
Acoustic correlates of user response to error in human-computer dialogues
Kazemzadeh, A., Lee, S., & Narayanan, S. (2004) · 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721) · doi:10.1109/asru.2003.1318443 · Cited by 10 · cited 5×
“By contrast, studies within the customer service domain utilised telephones [9, 11, 15, 27, 32, 66] or computer speakers [29, 38].”
BackgroundMethodResultInfluentialWhen to Say What and How: Adapting the Elaborateness and Indirectness of Spoken Dialogue Systems
Miehle, J., Minker, W., & Ultes, S. (2022) · Dialogue & Discourse · doi:10.5210/dad.2022.101 · Cited by 10
Repair strategies on trial: which error recovery do users like best?
Zgorzelski, A., Schmitt, A., Heinroth, T., & Minker, W. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-557 · Cited by 9
Clarifying False Memories in Voice-based Search
Kiesel, J., Bahrami, A., Stein, B., Anand, A., & Hagen, M. (2019) · Proceedings of the 2019 Conference on Human Information Interaction and Retrieval · doi:10.1145/3295750.3298961 · Cited by 9
Lee, D., Sah, Y. J., & Lee, S. (2019) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2018.1561069 · Cited by 9 · cited 6×
“A few studies were carried out in other languages and regions, including China [29, 75], Sweden [22, 67], UK [60], Brazil [50], Denmark [17], South Korea [40] and Taiwan [42].”
BackgroundMethodInfluentialUsing dialogue acts to learn better repair strategies for spoken dialogue systems
Frampton, M., & Lemon, O. (2008) · 2008 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2008.4518792 · Cited by 9
Zue, V. W., & Seneff, S. (2007) · Springer handbooks · doi:10.1007/978-3-540-49127-9_35 · Cited by 7
Lee, M., & Lee, S. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451812 · Cited by 5 · cited 1×
“Furthermore, they often prevent users from completing tasks, leading to task aban-donment [5], negatively impacting user experience and damaging the overall effectiveness of SDS performance [5, 18, 41, 44].”
BackgroundKim, S., Salter, D., DeLuccia, L., & Tamrakar, A. (2020) · Proceedings of the 8th International Conference on Human-Agent Interaction · doi:10.1145/3406499.3418754 · Cited by 4
Users' error recovery strategies in the interaction with voice assistants (VAs)
Motta, I., & Quaresma, M. (2022) · Lecture Notes in Networks and Systems · doi:10.1007/978-3-030-74614-8_82 · Cited by 4 · cited 10×
“This dynamic interaction has been explored in only a few studies (N=8) within our review (e.g., [50]).”
BackgroundMethodInfluentialHyperarticulation of Corrections in Multilingual Dialogue Systems
Kraljevski, I., & Hirschfeld, D. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-753 · Cited by 3 · cited 7×
“Almost all studies included in the review were conducted in a single language, except one [38], which was a multi-language study encompassing nine languages.”
BackgroundResultInfluentialMeck, A.-M., Draxler, C., & Vogt, T. (2024) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2023.2266791 · Cited by 3
Cackett, M., Fulton, L., & Pearl, D. (2023) · Lecture Notes in Networks and Systems · doi:10.1007/978-3-031-18458-1_9 · Cited by 3 · cited 1×
“In SDSs, voice is the preferred mode of communication with machines because it offers intuitive and hands-free interactions [12, 13, 42].”
BackgroundAn Analysis of Dialogue Repair in Voice Assistants
Galbraith, M. (2023) · arXiv · doi:10.48550/arxiv.2311.03952
Large Language User Interfaces: Voice Interactive User Interfaces powered by LLMsPreprint
Wasti, S. M., Pu, K. Q., & Neshati, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.07938
Research works printed but not linked: 6
- Dennis Benner, Edona Elshan, Sofia Schöbel, and Andreas Janson. 2021. What do you mean? A review on recovery strategies to overcome conversational breakdowns of conversational agents. In International Conference on Information Systems (ICIS). 1–17.
- Stephen Choularton and Robert Dale. 2004. User responses to speech recognition errors: consistency of behaviour across domains. In Proceedings of SST, Vol. 4.
- Lea Kisser and Ingo Siegert. 2022. Erroneous reactions of voice assistants" in the wild"–first analyses. Elektronische Sprachsignalverarbeitung (2022), 113–120.
- 10.1080/10447318.2023.2266791 · DOI · Paper page
- Gabriel Skantze. 2003. Exploring human error handling strategies: Implications for spoken dialogue systems. In ISCA Tutorial and Research Workshop on Error Handling in Spoken Dialogue Systems.
- Lionel Sujay Vailshery. 2021. Number of digital voice assistants in use worldwide 2019-2024. Statista Research Departement.[Online]. Available: https://www. statista. com/statistics/973815/worldwide-digital-voice-assistant-in-use (2021).
Cited by
The Art of Talking Machines: A Comprehensive Literature Review of Conversational User Interfaces
Namvarpour, M. (., & Razi, A. (2025) · Proceedings of the 7th ACM Conference on Conversational User Interfaces · doi:10.1145/3719160.3736621 · Cited by 19
Gnewuch, U., & Reinkemeier, F. (2026) · MIS Quarterly · doi:10.25300/misq/2025/18742 · Cited by 5
Lan, L., Cai, Y., Chu, Y., Tang, W., Chen, Y., & Liu, P. (2025) · International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI) · doi:10.1145/3744333.3747832 · Cited by 2
To Apologize or Not to Apologize? Trust Repair After Automated Vehicles’ Mistakes
Cai, Y., Chu, Y., Xu, Z., & Liu, P. (2025) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981251355535 · Cited by 6
Kim, E.-J., & Koo, Y. (2026) · Behaviour and Information Technology · doi:10.1080/0144929x.2026.2630372 · Cited by 1
Metadata
- Authors
- Alghamdi, E., Halvey, M., & Nicol, E.
- Affiliations
- University of Strathclyde (GB)
- Venue
- ACM Conversational User Interfaces 2024
- Publisher
- ACM
- Published
- 2024-07-08
- Pages
- 1-13
- OpenAlex
- W4400396839
- Semantic Scholar
- 432682853a953b862ba3cefde8a854e145e611f7
- Cited by
- 36
- References
- 59
- Citations by year
- 2026: 27 · 2025: 8 · 2024: 1
- FWCI
- 10.61
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Conference on Conversational User Interfaces (CUI) (publishedVersion, cc-by)
- Strathprints: The University of Strathclyde institutional repository (University of Strathclyde) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Social Sciences › Arts and Humanities › Language and Linguistics › Language, Discourse, Communication Strategies
- Keywords
- spoken dialogue systems, conversational breakdown, repair strategies, misunderstanding, non-understanding, human-machine interaction, dialogue management
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.