Abstract
The EuTransAll project aims at using example-based approaches for the automatic development of Machine Translation systems accepting text and speech input for limited-domain applications. During the first phase of the project, a speech-translation system that is based on the use of automatically learned subsequential transducers has been built. This paper contains a detailed and mostly self-contained overview of the transducer-learning algorithms and system architecture, along with a new approach for using categories representing words or short phrases in both input and output languages. Experimental results using this approach are reported for a task involving the recognition and translation of sentences in the hotel-receptioncommunication domain, with a vocabulary of 683 words in Spanish. Atranslation word-error rate of 1.97% is achieved in real-timefactor 2.7 on a Personal Computer.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amengual, J. C., J. M. Benedí, K. Beulen, F. Casacuberta, A. Castaño, A. Castellanos, V.M. Jiménez, D. Liorens, A. Marzal, H. Ney, F. Prat, E. Vidal and J. M. Vilar: 1997, ‘speech Translation Based on Automatically Trainable Finite-state Models’, '97: 5th European Conference on Speech Communication and Technology, Rhodes, Greece, pp. 1439–1442.
Amengual, J. C., J. M. Benedí, F. Casacuberta, A. Castaño, A. Castellanos, D. Llorens, A. Marzal, F. Prat, E. Vidal and J. M. Vilar: 1997, ‘Using Categories in the EUTRANS System’, Spoken Language Translation: Proceedings of a Workshop Sponsored by the Association for Computational Linguistics and by the European Network in Language and Speech (ELSNET), Madrid, Spain, pp. 44–53.
Baker, J. K.: 1975, ‘The Dragon System-An Overview’, IEEE Transactions on Acoustics, Speech, and Signal Processing 23, 24–29.
Block, Hans Ulrich: 1997, ‘The Language Components in Vermobil’, '97), Munich, Germany, pp. 79–82.
Brown, Peter F., John Cocke, Stephen A. Della Pietra, Vincent J. Della Pietra, Frederick Jelinek, John D. Lafferty, Robert L. Mercer and Paul S. Roossin: 1990, ‘A Statistical Approach to Machine Translation’, Computational Linguistics 16, 79–85.
Bub, Thomas, Wolfgang Wahlster and Alex Waibel: 1997, ‘Vermobil: The Combination of Deep and Shallow Processing for Spontaneous Speech Translation’, 97), Munich, Germany, pp. 71–74.
Casacuberta, F.: 1995, ‘Probabilistic Estimation of Stochastic Regular Syntax-directed Translation Schemes’, in A. Calvo and R. Medina (eds), Pattern Recognition and Image Analysis, Preprints of the VI Spanish Symposium on Pattern Recognition and Image Analysis, Córdoba, Spain, pp. 201–207.
Casacuberta, F.: 1996, ‘Maximum Mutual Information and ConditionalMaximum Likelihood Estimations of Stochastic Syntax-Directed Translation Schemes’, in Miclet and de la Higuera (1996), pp. 282–291.
Castellanos, A., I. Galiano and E. Vidal: 1994, ‘Application of OSTIA to Machine Translation Tasks’, in Rafael C. Carrasco and José Oncina (eds), Grammatical Inference and Applications, Berlin: Springer, pp. 93–105.
Forney, G. D.: 1973, ‘The Viterbi Algorithm’, Proceedings of the IEEE 61, 268–278.
García, P. and E. Vidal: 1990, ‘Inference of K-testable Languages in the Strict Sense and Applications to Syntactic Pattern Recognition’, IEEE Transactions on Pattern Analysis and Machine Intelligence 12, 920–925.
Gonzalez, Rafael C. and Michael G. Thomason: 1978, Syntactic Pattern Recognition: An Introduction, Reading, Massachusetts: Addison-Wesley.
Jelinek, F.: 1976, ‘Continuous Speech Recognition by Statistical Methods’, Proceedings of the IEEE 64, 532–556.
Jiménez, V. M., E. Vidal, J. Oncina, A. Castellanos, H. Rulot and J. A. Sánchez: 1994, ‘Spokenlanguage Machine Translation in Limited-domain Tasks’, in H. Niemann, R. de Mon and G. Hanrieder (eds), Progress and Prospects of Speech Research and Technology, Sankt Augustin: Infix, pp. 262–265.
Jiménez, V. M., A. Castellanos and E. Vidal: 1995, ‘some Results with a Trainable Speech Translation and Understanding System’, 1995 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 95), Detroit, Michigan, pp. 113–116.
Lavie, Alon, Alex Waibel, Lori Levin, Michael Finke, Donna Gates, Marsal Gavaldá, Torsten Zeppenfeld and Puming Zhan: 1997, ‘JANUS-III: Speech-to-speech Translation in Multiple Languages’, '97), Munich, Germany, pp. 99–102.
Lowerre, B. T.: 1976, The HARPY Speech Recognition System, PhD dissertation, Carnegie Mellon University, Pittsburgh, PA.
Miclet, Laurent and Colin de la Higuera (eds): 1996, Grammatical Inference: Learning Syntax from Sentences, Berlin: Springer.
Ney, H., D. Mergel, A. Noll and A. Paeseler: 1987, ‘A Data-driven Organization of the Dynamic Programming Beam Search for Continuous Speech Recognition’, 12th International Conference on Acoustics, Speech, and Signal Processing, ICASSP'87, Dallas, Texas, pp. 833–836.
Nirenburg, Sergei: 1995, The Pangloss Mark III Machine Translation System, Joint Technical Report CMU-CMT–95–145, Computing Research Laboratory (New Mexico State University, Las Cruces, NM), Center for Machine Translation (Carnegie Mellon University, Pittsburgh, PA), Information Sciences Institute (University of Southern California, Marina del Rey, CA).
Oncina, José: 1991, Aprendizaje de Lenguajes Regulares y Funciones Subsecuenciales [Learning Regular Languages and Subsequential Functions], PhD dissertation, Universidad Politécnica de Valencia, Spain.
Oncina, José, Pedro García and Enrique Vidal: 1993, ‘Learning Subsequential Transducers for Pattern Recognition Interpretation Tasks’, IEEE Transactions on Pattern Analysis and Machine Intelligence 15, 448–458.
Oncina, José and Miguel Ángel Varó: 1996, ‘Using Domain Information during the Learning of a Subsequential Transducer’, in Miclet and de la Higuera (1996), pp. 301–312.
Rayner, Manny and David Carter: 1997, ‘Hybrid Language Processing in the Spoken Language Translator’, '97), Munich, Germany, pp. 107–110.
Vidal, Enrique, Francisco Casacuberta and Pedro García: 1995, ‘Grammatical Inference and Automatic Speech Recognition’, in A. J. Rubio and J. M. López (eds), Speech Recognition and Coding: New Advances and Trends, Berlin: Springer, pp. 174–191.
Vidal, E.: 1997, ‘Finite-state Speech-to-speech Translation’, '97), Munich, Germany, pp. 111–114.
Vilar, J. M.: 1998, Aprendizaje de Traductores Subsecuenciales para su Empleo en Tareas de Dominio Restringido [Learning Subsequential Transducers for Limited Domain Tasks], PhD dissertation, Universidad Politécnica de Valencia, Spain.
Vilar, J. M., V. M. Jiménez, J. C. Amengual, A. Castellanos, D. Llorens and E. Vidal: 1996, ‘Text and Speech Translation by Means of Subsequential Transducers’, Natural Language Engineering 2, 351–354.
Vilar, J. M., A. Marzal and E. Vidal: 1995, ‘Learning Language Translation in Limited Domains Using Finite-stateModels: Some Extensions and Improvements’, EuroSpeech'95, Madrid, Spain, pp. 1231–1234.
Viterbi, A. J.: 1967, ‘Error Bounds for Convolutional Codes and an Asymptotically Optimal Decoding Algorithm’, IEEE Transactions on Information Theory 13, 260–269.
Young, S. J., P. C. Woodland and W. J. Byrne: 1993, HTK: Hidden Markov Model Toolkit V1.5, Cambridge University Engineering Department and Entropic Research Laboratories Inc.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Amengual, J.C., Castaño, A., Castellanos, A. et al. The EuTrans Spoken Language Translation System. Machine Translation 15, 75–103 (2000). https://doi.org/10.1023/A:1011116115948
Issue Date:
DOI: https://doi.org/10.1023/A:1011116115948