Abstract
Combining the output of several speech decoders is considered to be one of the most efficient approaches to reducing the Word Error Rate (WER) in automatic speech transcription. The Recognizer Output Voting Error Reduction (ROVER) is a well known procedure for systems’ combination. However, this technique’s performance has reached a plateau due to the limitation of the current voting schemes. The ROVER voting algorithms proposed originally rely on the frequency of occurrences and word level confidences, which leads to randomly broken ties and poor voting outcomes due to the unreliability of the decoder’s confidence scores. This paper presents a pattern-matching-based voting scheme which has shown to reduce even further the WER.
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.
Similar content being viewed by others
References
Abida, K., Karray, F.: Systems combination in large vocabulary continuous speech recognition. In: IEEE International Conference on Autonomous and Intelligent Systems, pp. 1–6 (2010)
Fiscus, J.: A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER). In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 347–352 (1997)
Jiang, H.: Confidence measures for speech recognition: a survey. J. Speech Communication 45(4), 455–470 (2005)
Huggins-Daines, D.: CMU Sphinx open source models (2008), http://www.speech.cs.cmu.edu/sphinx/models/
Fiscus, J., Garofolo, J., Przybocki, M., Fisher, W., Pallet, D.: 1997 English Broadcast News Speech, HUB4 (1998)
Graff, D., Cieri, C.: English Gigaword Corpus (2003)
Khoury, R.: The impact of Wikipedia on scientific research. In: 3rd International Conference on Internet Technologies and Applications, pp. 2–11 (2009)
Béchet, F., Charton, E.: Unsupervised knowledge acquisition for Extracting Named Entities from speech. In: ICASSP 2010, pp. 5338–5341 (2010)
Alemzadeh, M., Khoury, R., Karray, F.: Exploring Wikipedia’s Category Graph for Query Classification. In: Kamel, M., Karray, F., Gueaieb, W., Khamis, A. (eds.) AIS 2011. LNCS, vol. 6752, pp. 222–230. Springer, Heidelberg (2011)
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
AlemZadeh, M., Abida, K., Khoury, R., Karray, F. (2012). Enhancement of the ROVER’s Voting Scheme Using Pattern Matching. In: Kamel, M., Karray, F., Hagras, H. (eds) Autonomous and Intelligent Systems. AIS 2012. Lecture Notes in Computer Science(), vol 7326. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31368-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-31368-4_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31367-7
Online ISBN: 978-3-642-31368-4
eBook Packages: Computer ScienceComputer Science (R0)