TSD 2010: Text, Speech and Dialogue pp 523-530 | Cite as
Using Knowledge about Misunderstandings to Increase the Robustness of Spoken Dialogue Systems
Abstract
This paper proposes a new technique to enhance the performance of spoken dialogue systems employing a method that automatically corrects semantic frames which are incorrectly generated by the semantic analyser of these systems. Experiments have been carried out using two spoken dialogue systems previously developed in our lab: Saplen and Viajero, which employ prompt-dependent and prompt-independent language models for speech recognition. The results obtained from 10,000 simulated dialogues show that the technique improves the performance of the two systems for both kinds of language modelling, especially for the prompt-independent language model. Using this type of model the Saplen system increased sentence understanding by 19.54%, task completion by 26.25%, word accuracy by 7.53%, and implicit recovery of speech recognition errors by 20.30%, whereas for the Viajero system these figures increased by 14.93%, 18.06%, 6.98% and 15.63%, respectively.
Keywords
Spoken dialogue systems speech recognition spoken language understanding user simulationPreview
Unable to display preview. Download preview PDF.
References
- 1.Higashinaka, R., Sudoh, K., Nakano, M.: Incorporating Discourse Features into Confidence Scoring of Intention Recognition Results in Spoken Dialogue Systems. Speech Communication 48, 417–436 (2006)CrossRefGoogle Scholar
- 2.Jiang, H.: Confidence Measures for Speech Recognition: A survey. Speech Communication 45, 455–470 (2005)CrossRefGoogle Scholar
- 3.Karsenty, K., Botherel, V.: Transparency Strategies to Help Users Handle System Errors. Speech Communication 45, 305–324 (2005)CrossRefGoogle Scholar
- 4.Lemon, O., Gruenstein, A.: Multithreaded Context for Robust Conversational Interfaces: Context-Sensitive Speech Recognition and Interpretation of Corrective Fragments. ACM Transactions on Computer-Human Interaction 11(3), 241–267 (2004)CrossRefGoogle Scholar
- 5.López-Cézar, R., García, R., Díaz, J., Rubio, A.: A Voice Activated Dialogue System for Fast-Food Restaurant Applications. In: Proc. of Eurospeech, pp. 1783–1786 (1997)Google Scholar
- 6.López-Cózar, R., Rubio, A.J., Garciá, P., Díaz Verdejo, J.E., López-Soler, J.M.: Telephone-Based Service for Bus Travellers Service. In: Proc. of 1st Spanish Meeting on Speech Technologies, Seville, Spain, pp. 181–184 (2000)Google Scholar
- 7.López-Cózar, R., De la Torre, A., Segura, J.C., Rubio, A.J., Sánchez, V.: Assessment of Spoken Dialogue Systems by means of a New Simulation Technique. Speech Communication 40(3), 387–407 (2003)CrossRefGoogle Scholar
- 8.López-Cózar, R., Callejas, Z.: Two-Level Speech Recognition to Enhance the Performance of Spoken Dialogue Systems. Computer Speech and Language 19, 153–163 (2006)Google Scholar
- 9.López-Cózar, R., Callejas, Z.: Combining Language Models in the Input Interface of a Spoken Dialogue System. Computer Speech and Language 20, 420–440 (2005)CrossRefGoogle Scholar