Abstract
In this paper we discuss the problem that in a dialogue system, speech recognizers should be able to guess whether the speech recognition failed, even if no correct transcription of the actual user utterance is available. Only with such a diagnosis available, the dialogue system can choose an adequate repair strategy and try to recover from the interaction problem with the user and avoid negative consequences for the successful completion of the dialogue. We present a data collection for a controlled out-of-vocabulary scenario and discuss an approach to estimate the success of a speech recognizer’s results by exploring differences between the N-gram distribution in the best word chain and in the language model. We present the results of our experiments that indicate that differences can be found to be significant if the speech recognition failed severely. From these results, we derive a quick test for failed recognition that is based on a negative language model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chang, J.C., Lien, A., Lathrop, B., Hees, H.: Usability evaluation of a volkswagen group in-vehicle speech system. In: Schmidt, A., Dey, A.K., Seder, T., Juhlin, O. (eds.) Automotive UI, pp. 137–144. ACM (2009)
Chelba, C., Jelinek, F.: Structured language modeling. Computer Speeech & Language 14, 283–332 (2000)
Bocchieri, E., Dimitriadis, D.C.D.: Speech recognition modeling advances for mobile voice search. In: Proceedings of Acoustics, Speech and Signal Processing (ICASSP 2011), Prague, pp. 4888–4891 (2011)
Chen, L., Chin, K.K., Knill, K.: Improved language modelling using bag of word pairs. In: Proceedings of Interspeech 2009, Brighton, pp. 2671–2674 (2009)
Jurafsky, D., Martin, J.H.: Speech and Language Processing. Prentice Hall (2009)
Hacker, M.: Context-aware speech recognition in a robot navigation scenario. In: Proceedings of the 2nd Workshop on Context Aware Intelligent Assistance, pp. 4–15 (2012)
Katz, S.M.: Estimation of probabilities from sparse data for the language model component of a speech recogniser. IEEE Transactions on Acoustics, Speech, and Signal Processing 35, 400–401 (1987)
Chelba, C., Brants, T., Neveitt, W., Xu, P.: Study on interaction between entropy pruning and kneser-ney smoothing. In: Proceedings of Interspeech 2010, pp. 2242–2245 (2010)
Uhrik, C., Ward, W.: Confidence Metrics Based on N-Gram Language Model Backoff Behaviors. In: Fifth European Conference on Speech Communication and Technology. ISCA (1997)
Jiang, H.: Confidence measures for speech recognition: A survey. Speech Communication 45, 455–470 (2005)
Katz, S.: Estimation of probabilities from sparse data for the language model component of a speech recogniser. IEEE Transactions on Acoustics, Speech, and Signal Processing 35, 400–401 (1987)
Spiegl, W., Riedhammer, K., Steidl, S., Nöth, E.: FAU IISAH Corpus – A German Speech Database Consisting of Human-Machine and Human-Human Interaction Acquired by Close-Talking and Far-Distance Microphones. In: Proceedings of the Seventh Conference on International Language Resources and Evaluation (LREC 2010), pp. 2420–2423. ELRA (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ludwig, B., Hitzenberger, L. (2012). Did You Say What I Think You Said?. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2012. Lecture Notes in Computer Science(), vol 7499. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32790-2_52
Download citation
DOI: https://doi.org/10.1007/978-3-642-32790-2_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32789-6
Online ISBN: 978-3-642-32790-2
eBook Packages: Computer ScienceComputer Science (R0)