A shallow model of backchannel continuers in spoken dialogue
Open accessAbstract
Spoken dialogue systems would be more acceptable if they were able to produce backchannel continuers such as mm-hmm in naturalistic locations during the user's utterances. Using the HCRC Map Task Corpus as our data source, we describe models for predicting these locations using only limited processing and features of the user's speech that are commonly available, and which therefore could be used as a low-cost improvement for current systems. The baseline model inserts continuers after a predetermined number of words. One further model correlates back-channel continuers with pause duration, while a second predicts their occurrence using trigram POS frequencies. Combining these two models gives the best results.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The hope is that conversational agents providing feedback result in more pleasant and more engaging user-experiences, and in an increase in acceptance.
“The hope is that conversational agents providing feedback result in more pleasant (Ward, 1996) and more engaging user-experiences, and in an increase in acceptance (Cathcart et al., 2003).”
From Modeling Feedback in Interaction With Conversational Agents—A Review (2022) · cites this paper as Cathcart et al., 2003
The Introduction (p. 1) describes feedback as a way to signal that communication is working, and the Evaluation section (p. 6) proposes testing whether adding the model improves a dialogue system’s acceptability. These passages support the hoped-for increase in acceptance, but they do not specifically address more engaging user experiences. The paper presents acceptability as a hoped-for outcome, not a measured result. (LLM, conf=0.84)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Designing SpeechActs: issues in speech user interfaces
Yankelovich, N., Levow, G.-A., & Marx, M. (1995) · Proceedings of the SIGCHI conference on Human factors in computing systems - CHI '95 · doi:10.1145/223904.223952 · Cited by 250 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [20]20. V.H. Yngve. 1970. On getting a word in edgewise. In Papers from the Sixth Regional Meeting, Chicago Linguistic Society, pages 567–577.
Cited by
Sorted by citations
Interpersonal synchrony: a survey of evaluation methods across disciplines.
Delaherche, E., Chetouani, M., Mahdhaoui, A., Saint-Georges, C., Viaux, S., & Cohen, D. (2012) · IEEE Transactions on Affective Computing · doi:10.1109/t-affc.2012.12 · Cited by 474 · see citing works
Lee, S., Lee, N., & Sah, Y. J. (2020) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2019.1699748 · Cited by 204 · see citing works
Modeling embodied feedback with virtual humans,
Kopp, S., Allwood, J., Grammer, K., Ahlsen, E., & Stocksmeier, T. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79037-2_2 · Cited by 71 · see citing works
Data-driven models for timing feedback responses in a Map Task dialogue system
Meena, R., Skantze, G., & Gustafson, J. (2014) · Computer Speech & Language · doi:10.1016/j.csl.2014.02.002 · Cited by 56 · see citing works
Predicting Speaker Head Nods and the Effects of Affective Information
Lee, J., & Marsella, S. C. (2010) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2010.2051874 · Cited by 37 · see citing works
A multimodal analysis of vocal and visual backchannels in spontaneous dialogs,
Truong, K. P., Poppe, R., Kok, I. D., & Heylen, D. (2011) · Interspeech 2011 · doi:10.21437/interspeech.2011-744 · Cited by 33 · see citing works
Modeling Feedback in Interaction With Conversational Agents—A Review
Axelsson, A., Buschmeier, H., & Skantze, G. (2022) · Frontiers in Computer Science · doi:10.3389/fcomp.2022.744574 · Cited by 33 · see citing works
Perceptual evaluation of backchannel strategies for artificial listeners
Poppe, R., Truong, K. P., & Heylen, D. (2013) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-013-9219-z · Cited by 14 · see citing works
- Authors
- Cathcart, N., Carletta, J., & Klein, E.
- Affiliations
- Canon (United Kingdom) (GB)
- University of Edinburgh (GB)
- ORCID
- Klein, Ewan
- Venue
- Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - EACL '03
- Published
- 2003
- Volume
- 1
- Pages
- 51
- OpenAlex
- W2034246592
- Cited by
- 88
- References
- 1
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 4 · 2023: 3 · 2022: 7 · 2021: 2 · 2019: 1 · 2018: 2 · 2017: 2 · 2016: 2 · 2015: 3 · 2014: 4 · 2013: 12 · 2012: 7
- Type
- conference abstract
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Conference of the European Chapter of the Association for Computational Linguistics (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- spoken dialogue systems, utterance segmentation, pause duration, conversational speech
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
