Speech-input multi-target machine translation

Authors:
Alicia Pérez;M. Inés Torres;M. Teresa González;Francisco Casacuberta
Affiliations:
University of the Basque Country;University of the Basque Country;University of Valencia;University of Valencia
Venue:
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
Year:
2007

Citing 7
Cited 0

Inference of k-Testable Languages in the Strict Sense and Application to Syntactic Pattern Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Finite-State Speech-to-Speech Translation

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Machine Translation with Inferred Stochastic Finite-State Transducers

Computational Linguistics
Representation and treatment of multiword expressions in Basque

MWE '04 Proceedings of the Workshop on Multiword Expressions: Integrating Processing
Augmenting a small parallel text with morpho-syntactic language resources for Serbian-English statistical machine translation

ParaText '05 Proceedings of the ACL Workshop on Building and Using Parallel Texts
Novel reordering approaches in phrase-based statistical machine translation

ParaText '05 Proceedings of the ACL Workshop on Building and Using Parallel Texts

Quantified Score

Hi-index	0.00

Visualization

Abstract

In order to simultaneously translate speech into multiple languages an extension of stochastic finite-state transducers is proposed. In this approach the speech translation model consists of a single network where acoustic models (in the input) and the multilingual model (in the output) are embedded. The multi-target model has been evaluated in a practical situation, and the results have been compared with those obtained using several mono-target models. Experimental results show that the multi-target one requires less amount of memory. In addition, a single decoding is enough to get the speech translated into multiple languages.