Abstract
Previous research has shown that speech disfluencies - speech errors that occur in spoken language - affect NLP systems and hence need to be repaired or at least marked. This study presents a hybrid approach that uses different detection techniques for this task where each of these techniques is specialized within its own disfluency domain. A thorough investigation of the used disfluency scheme, which was developed by [1], led us to a detection design where basic rule-matching techniques are combined with machine learning approaches. The aim was both to reduce computational overhead and processing time and also to increase the detection performance. In fact, our system works with an accuracy of 92.9% and an F-Score of 90.6% while working faster than real-time.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Besser, J.: A Corpus-Based Approach to the Classification and Correction of Disfluencies in Spontaneous Speech. Master’s thesis, Saarbrücken (2006)
Ferreira, F., Lau, E., Bailey, K.: Disfluencies, Language Comprehension and Tree Adjoining Grammars. Cognitive Science, 28, 721–749 (2004)
Jorgensen, F.: The Effects of Disfluency Detection in Parsing Spoken Language. In: NODALIDA-2007, pp. 240–244 (2007)
Stolcke, A., Shriberg, E.: Statistical Language Modeling for Speech Disfluencies. In: Proc. ICASSP 1996, pp. 405–408 (1996)
Carletta, Jean, Ashby, S., Bourban, S., Flynn, M., et al.: The AMI Meeting Corpus. In: Proceedings of the Measuring Behavior 2005 symposium on “Annotating and measuring Meeting Behaviour” (2005)
Charniak, E., Johnson, M.: A TAG-based noisy channel model of speech repairs. In: Annual Meeting of the Association for Computational Linguistics (2004)
Lease, M., Johnson, M., Charniak, E.: Recognizing disfluencies in conversational speech. In: IEEE Transactions on Audio, Speech and Language Processing, pp. 1566–1573 (September 2006)
Snover, M., Dorr, B., Schwartz, R.: A lexically-driven algorithm for disfluency detection. In: Human Language Technology Conference (2004)
Moreno, I., Pineda, L.: Speech Repairs in the DIME Corpus (2006)
Shriberg, E., Bates, R., Stolcke, A.: A Prosody-Only Decision-Tree Model for Disfluency Detection. In: Proc. Eurospeech 1997, pp. 2383–2386 (1997)
Finkler, W.: Automatische Selbstkorrektur bei der inkrementellen Generierung gesprochener Sprache unter Realzeitbedinungen, Dissertation, Universität des Saarlandes, 165, DISKI (1997)
Eklund, R.: Disfluency in Swedish human-human and human-machine travel booking dialogues (2004)
Witten, I., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques, vol. 2. Morgan Kaufmann, San Francisco (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Germesin, S., Becker, T., Poller, P. (2008). Hybrid Multi-step Disfluency Detection. In: Popescu-Belis, A., Stiefelhagen, R. (eds) Machine Learning for Multimodal Interaction. MLMI 2008. Lecture Notes in Computer Science, vol 5237. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85853-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-85853-9_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85852-2
Online ISBN: 978-3-540-85853-9
eBook Packages: Computer ScienceComputer Science (R0)