Abstract
Our principal objective was to reduce the error rate of speech recognition systems used by professional translators. Our work concentrated on Spanish-to-English translation. In a baseline study we estimated the speech recognition error rate of an off-the-shelf recognizer to be 9.98% We describe two independent methods of improving speech recognition systems for translators: a word-for-word translation method and a topic-based method. The topic-based approach performed the best, reducing the error rate significantly, to 5.07%.
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
Hochberg, M, Renals, S., Robinson, A., Cook, G.: Recent Improvements to the Abbot Large Vocabulary CSR System. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (1995) 69–72.
Keizer, G.: The Gift of Gab: CNET Compares the Top Speech Recognition Apps. (1998) (http://204.162.80.182/Content/Reviews/Compare/Speech/).
Poor, R.: Speech Recognition: Watch What You Say. PC Magazine on-line (1998) (http://home.zdnet.com/pcmag/features/speech/index.html).
Renals, S., Hochberg, M.: Efficient Evaluation of the LVCSR Search Space Using the NOWAY Decoder. Proceedings of the International Conference on Speech and Language Processing (1996) 149–152.
Ringger, E.K.: A Robust Loose Coupling for Speech Recognition and Natural Language Understanding. Technical Report 592. University of Rochester Computer Science Department (1995).
Ringger, E.K., Allen, J.F.: A Fertility Channel Model for Post-correction of Continuous Speech Recognition. Proceedings of the Fourth International Conference on Speech and Language Processing (ICSLP’96) (1996).
Robinson, T.,, Christie, J.: Time-first Search for Large Vocabulary Speech Recognition. Proceedings of the International Conference on Acoustics, Speech and Signal Processing (1998).
Siegler, M.A., Stern. R.M.: On the Effects of Speech Rate in Large Vocabulary Speech Recognition Systems. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (1995).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ludovik, Y., Zacharski, R. (2000). Improving the Accuracy of Speech Recognition Systems for Professional Translators. In: Christodoulakis, D.N. (eds) Natural Language Processing — NLP 2000. NLP 2000. Lecture Notes in Computer Science(), vol 1835. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45154-4_28
Download citation
DOI: https://doi.org/10.1007/3-540-45154-4_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67605-8
Online ISBN: 978-3-540-45154-9
eBook Packages: Springer Book Archive