Abstract
Despite the recent improvements in performance and reliably of the different components of dialog systems, it is still crucial to devise strategies to avoid error propagation from one another. In this paper, we contribute a framework for improved error detection and correction in spoken conversational interfaces. The framework combines user behavior and error modeling to estimate the probability of the presence of errors in the user utterance. This estimation is forwarded to the dialog manager and used to compute whether it is necessary to correct possible errors. We have designed an strategy differentiating between the main misunderstanding and non-understanding scenarios, so that the dialog manager can provide an acceptable tailored response when entering the error correction state. As a proof of concept, we have applied our proposal to a customer support dialog system. Our results show the appropriateness of our technique to correctly detect and react to errors, enhancing the system performance and user satisfaction.
Similar content being viewed by others
Notes
The degrees of freedom that SPSS employs for t tests are \(N-1\) in case the compared groups have the same number of samples (N), and \(N1+N2-1\) when they differ in the number of samples (N1 and N2).
References
Aberdeen J, Ferro L (2003) Dialogue patterns and misunderstandings. In: Proceedings of ISCA Workshop on error handling in SDSs, pp 17–23
Ai H, Litman D, Forbes-Riley K, Rotaru M, Tetreault J, Purandare A (2006) Using systems and user performance features to improve emotion detection in spoken tutoring dialogs. In: Proceedings of Interspeech’06-ICSLP, pp 797–800
Ai H, Raux A, Bohus D, Eskenazi M, Litman D (2007) Comparing spoken dialog corpora collected with recruited subjects versus real users. In: Proceedings of SIGdial, pp 124–131
Batliner A, Burkhardt F, van Ballegooy M, Noth E (2006) IA taxonomy of applications that utilize emotional awareness. In: Proceedings of IS-LTC’06, pp 246–250
Bickmore T, Giorgino T (2004) Some novel aspects of health communication from a dialogue systems perspective. In: Proceedings of AAAI Fall symposium on dialogue systems for health communication, pp 275–291
Black A, Burger S, Langner B, Parent G, Eskenazi M (2010) Spoken dialog challenge 2010. In: Proceedings of SLT’10, pp 448–453
Bulyko I, Kirchhoff K, Ostendorf M, Goldberg J (2005) Error-correction detection and response generation in a spoken dialogue system. Speech Commun 45(3):271–288
Calvo R, D’Mello S, Gratch J, Kappas A (2014) The Oxford handbook of affective computing. Oxford University Press, Oxford
Dethlefs N, Cuayáhuitl H (2015) Hierarchical reinforcement learning for situated natural language generation. Nat Lang Eng 21(3):391–435
Eckert W, Levin E, Pieraccini R (1997) User modeling for spoken dialogue system evaluation. In: Proceedings of ASRU, pp 80–87
Engelbrecht KP, Moller S (2010) Sequential classifiers for the prediction of user judgments about spoken dialog systems. Speech Commun 52(10):816–833
Erdogan H, Sarikaya R, Chen S, Gao Y, Picheny M (2005) Using semantic analysis to improve speech recognition performance. Comput Speech Lang 19:321–343
Fonfara J, Hellbacha S, Bohme H (2014) Imitating dialog strategies under uncertainty. In: Proceedings of IHCI, pp 131–138
Fukubayashi Y, Komatani K, Ogata T, Okuno H (2006) Dynamic help generation by estimating user’s mental model in spoken dialogue systems. In: Proceedings of ICSLP, pp 1946–1949
Gemello R, Mana F, Albesano D, Mori RD (2006) Multiple resolution analysis for robust automatic speech recognition. Comput Speech Lang 20:2–21
Griol D, Carbo J, Molina JM (2013a) An automatic dialog simulation technique to develop and evaluate interactive conversational agents. Appl Artif Intell 27(9):759–780
Griol D, Carbo J, Molina J (2013b) A statistical simulation technique to develop and evaluate conversational agents. AI Commun 26(4):355–371
Griol D, Callejas Z, López-Cózar R, Riccardi G (2014) A domain-independent statistical methodology for dialog management in spoken dialog systems. Comput Speech Lang 28(3):743–768
Hakkani-Tur D, Bechet F, Riccardi G, Tur G (2006) Beyond ASR 1-best: using word confusion networks in spoken language understanding. Comput Speech Lang 20(4):495–514
Hirst G, McRoy S, Heeman P, Edmonds P, Horton D (1993) Repairing conversational misunderstandings and non-understandings. Speech Commun 15(3–4):825–840
Karsenty L, Botherel V (2005) Transparency strategies to help users handle system errors. Speech Commun 45:305–324
Kitaoka N, Kakutani N, Nakagawa S (2003) Detection and recognition of correction utterance in spontaneously spoken dialog. In: Proceedings of Eurospeech, pp 625–628
Lee C, Jung S, Kim K, Lee GG (2010) Hybrid approach to robust dialog management using agenda and dialog examples. Comput Speech Lang 24(4):609–631
Levin E, Pieraccini R, Eckert W (2000) A stochastic model of human–machine interaction for learning dialog strategies. IEEE Trans Speech Audio Process 8(1):11–23
López-Cózar R, Callejas Z, Griol D (2010) Using knowledge of misunderstandings to increase the robustness of spoken dialogue systems. Knowl Based Syst 23:471–485
Lutfi SL, Fernández-Martínez F, Lucas-Cuesta JM, López-Lebón L, Montero JM (2013) A satisfaction-based model for affect recognition from conversational features in spoken dialog systems. Speech Commun 55(7–8):825–840
Martinovsky B, Traum D (2003) The error is the clue: breakdown in human–machine interaction. In: Proceedings of ISCA Workshop on error handling in SDSs, 99 11–17
McCrae R, John O (1992) An introduction to the five-factor model and its applications. J Pers 60(2):175–215
McTear MF, Callejas Z, Griol D (2016) The conversational interface. Springer, Berlin
Paek T, Pieraccini R (2008) Automating spoken dialogue management design using machine learning: an industry perspective. Speech Commun 50(8–9):716–729
Schatzmann J, Georgila K, Young S (2005) Quantitative evaluation of user simulation techniques for spoken dialogue systems. In: Proceedings of SIGdial, pp 45–54
Schatzmann J, Weilhammer K, Stuttle M, Young S (2006) A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies. Knowl Eng Rev 21(2):97–126
Schatzmann J, Thomson B, Weilhammer K, Ye H, Young S (2007a) Agenda-based user simulation for bootstrapping a POMDP dialogue system. In: Proceedings of HLT/NAACL, pp 149–152
Schatzmann J, Thomson B, Young S (2007b) Statistical user simulation with a hidden agenda. In: Proceedings of SIGdial, pp 273–282
Schmitt A, Ultes S (2015) Interaction quality: assessing the quality of ongoing spoken dialog interaction by experts and how it relates to user satisfaction. Speech Commun 74:12–36
Schuller B, Batliner A (2013) Computational paralinguistics: emotion, affect and personality in speech and language processing. Wiley, New York
Shin J, Narayanan S, Gerber L, Kazemzadeh A, Byrd D (2002) Analysis of user behavior under error conditions in spoken dialogs. In: Proceedings of ICSLP, pp 2069–2072
Skantze G (2009) Exploring human error recovery strategies: implications for spoken dialogue systems. Speech Commun 45(3):325–341
Stepanov E, Riccardi G, Bayer A (2014) The development of the multilingual LUNA corpus for spoken language system porting. In: Proceedings of LREC, pp 2675–2678
Wang F, Swegles K (2013) Modeling user behavior online for disambiguating user input in a spoken dialogue system. Speech Commun 55:84–98
Wang Y, Acero A, Chelba C (2003) Is word error rate a good indicator for spoken language understanding accuracy? In: Proceedings of ASRU, pp 577–582
Williams J (2009) The best of both worlds: Unifying conventional dialog systems and pomdps. In: Proceedings of Interspeech, pp 1173–1176
Young SJ, Gasic M, Thomson B, Williams JD (2013) Pomdp-based statistical spoken dialog systems: a review. Proc IEEE 101(5):1160–1179
Acknowledgments
This work was supported in part by Projects MINECO TEC2012-37832-C02-01, CICYT TEC2011-28626-C02-02, CAM CONTEXTS (S2009/TIC-1485).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Additional information
Communicated by A. Herrero.
Rights and permissions
About this article
Cite this article
Griol, D., Molina, J.M. A framework for improving error detection and correction in spoken dialog systems. Soft Comput 20, 4229–4241 (2016). https://doi.org/10.1007/s00500-016-2290-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-016-2290-z