Abstract
This paper demonstrates the usefulness of syntactic trigrams in improving the performance of a speech recognizer for the Spanish language. This technique is applied as a post-processing stage that uses syntactic information to rescore the N-best hypothesis list in order to increase the score of the most syntactically correct hypothesis. The basic idea is to build a syntactic model from training data, capturing syntactic dependencies between adjoint words in a probabilistic way, rather than resorting to the use of a rule-based system. Syntactic trigrams are used because of their power to express relevant statistics about the short-distance syntactic relationships between the words of a whole sentence. For this work we used a standarized tagging scheme known as the EAGLES tag definition, due of its ease of use and its broad coverage of all grammatical classes for Spanish. Relative improvement for the speech recognizer is 5.16%, which is statistically significant at the level of 10%, for a task of 22,398 words (HUB-4 Spanish Broadcast News).
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
Rosenfeld, R., Chen, S.F., Zhu, X.: Whole-Sentence Exponential Language Models: A Vehicle for Linguistic-Statistical Integration. Computer Speech and Language 15(1) (2001)
Manning, C., Schütze, H.: Fundations of Statistical Natural Language Processing, pp. 191–255. MIT Press, Cambridge (2001)
Jelinek, F.: Statistical Methods for Speech Recognition, pp. 57–78. MIT Press, Cambridge (1994)
Bellegarda, J., Junqua, J., van Noord, G.: Robustness in Language and Speech Technology, pp. 101–121. ELSNET/Kluwer Academic Publishers (2001)
Huang, X., Acero, A., Hon, H.: Spoken Language Processing, pp. 602–610. Prentice-Hall, Englewood Cliffs (2001)
Huerta, J.M., Chen, S., Stern, R.M.: The 1998 CMU SPHINX-3 Broadcast News Transcription System. In: Darpa Broadcast News Workshop (1999)
Gillick, L., Cox, S.J.: Some statistical issues in the comparisson of speech recognition algorithms. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 1992, pp. 532–535 (1992)
Padró, L.: A Hybrid Environment for Syntax-Semantic Tagging (Ph.D. Thesis), Departament de Llenguatges i Sistemes Informàtics, Universitat Politècnica de Cataluyna, Barcelona (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Salgado-Garza, L.R., Stern, R.M., Nolazco F., J.A. (2004). N-Best List Rescoring Using Syntactic Trigrams. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds) MICAI 2004: Advances in Artificial Intelligence. MICAI 2004. Lecture Notes in Computer Science(), vol 2972. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24694-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-24694-7_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21459-5
Online ISBN: 978-3-540-24694-7
eBook Packages: Springer Book Archive