Abstract
A speech input machine translation system based on weighted finite state transducers is presented. This system allows for a tight integration of the speech recognition with the machine translation modules. Transducer inference algorithms to automatically learn the translation module are also presented. Good experimental results confirmed the adequacy of these techniques to limited-domain tasks. In particular, the reordering algorithm proposed showed impressive improvements by reducing the error rate in excess of 50%.
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
Mohri, M., Pereira, F., Riley, M.: Weighted finite-state transducers in speech recognition. In: ASR 2000 Workshop, Paris, France (2000)
Hetherington, I.: An efficient implementation of phonological rules using finitestate transducers. In: Proc. Eurospeech 2001, Aalborg, Denmark (2001)
Knight, K., Al-Onaizan, Y.: Translation with finite-state devices. In: Farwell, D., Gerber, L., Hovy, E. (eds.) AMTA 1998. LNCS (LNAI), vol. 1529, pp. 421–437. Springer, Heidelberg (1998)
Gale, W., Church, K.: A program for aligning sentences in bilingual corpora. Computational Linguistics 102, 19–75 (1993)
Bangalore, S., Riccardia, G.: Stochastic finite-state models for spoken language machine translation. In: Workshop on Embedded Machine Translation Systems, Seattle, EUA (2000)
Oncina, J., Castellanos, A., Vidal, E., Jimenez, V.: Corpus–based machine translation through subsequential transducers. In: Third International Conference on the Cognitive Science of Natural Language Processing, Dublin, Ireland (1994)
GarcÃa-Varea, I., Sanchis, A., Casacuberta, F.: A new approach to speech-input statistical translation. In: 15th International Conference on Pattern Recognition, Barcelona, Spain, vol. 3, pp. 94–97. IEEE Computer Society, Los Alamitos (2000)
Casacuberta, F., Vidal, E., Picó, D.: Inference of finite-state transducers from regular languages. Pattern Recognition 38, 1431–1442 (2005)
Meinedo, H., Caseiro, D., Neto, J., Trancoso, I.: Audimus. media: a broadcast news speech recognition system for the european portuguese language. In: Mamede, N.J., Baptista, J., Trancoso, I., Nunes, M.d.G.V. (eds.) PROPOR 2003. LNCS, vol. 2721, pp. 9–17. Springer, Heidelberg (2003)
Caseiro, D.: Finite-State Methods in Automatic Speech Recognition. PhD thesis, Instituto Superior Técnico, Universidade Técnica de Lisboa (2003)
Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Computational Linguistics 29, 19–51 (2003)
Casacuberta, F.: Inference of finite-state transducers by using regular grammars and morphisms. In: Oliveira, A.L. (ed.) ICGI 2000. LNCS (LNAI), vol. 1891, pp. 1–14. Springer, Heidelberg (2000)
Riccardi, G., Bocchieri, E., Pieraccini, R.: Non deterministic stochastic language models for speech recognition. In: Proc. ICASSP 1995, Detroit, USA, pp. 237–240 (1995)
Stolcke, A.: Srilm - an extensible language modeling toolkit. In: Proc. ICSLP 2002, Denver, Colorado, USA (2002)
Amengual, J., BenedÃ, J., Casacuberta, F., Castaño, A., Castellanos, A., Jiménez, V., Llorens, D., Marzal, A., Pastor, M., Prat, F., Vidal, E., Vilar, J.: The eutrans-i speech translation system. Machine Translation 15, 75–103 (2000)
Meinedo, H., Souto, N., Neto, J.: Speech recognition of broadcast news for the European portuguese language. In: Automatic Speech Recognition and Understanding ASRU 2001, Madona de Campilho, Trento, Italy (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Caseiro, D., Trancoso, I. (2006). Weighted Finite-State Transducer Inference for Limited-Domain Speech-to-Speech Translation. In: Vieira, R., Quaresma, P., Nunes, M.d.G.V., Mamede, N.J., Oliveira, C., Dias, M.C. (eds) Computational Processing of the Portuguese Language. PROPOR 2006. Lecture Notes in Computer Science(), vol 3960. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11751984_7
Download citation
DOI: https://doi.org/10.1007/11751984_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34045-4
Online ISBN: 978-3-540-34046-1
eBook Packages: Computer ScienceComputer Science (R0)