Abstract

A fully integrated approach to Speech-Input Language Translation in limited-domain applications is presented. The mapping from the input to the output language is modeled in terms of a finite state translation model which is learned from examples of input-output sentences of the task considered. This model is tightly integrated with standard acoustic-phonetic models of the input language and the resulting global model directly supplies, through Viterbi search, an optimal output-language sentence for each input -language utterance. Several extensions to this framework, recently developed to cope with the increasing difficulty of translation tasks, are reviewed. Finally, results for a task in the framework of hotel front-desk communication, with a vocabulary of about 700 words, are reported.

Citations

502	A statistical approach to machine translation - Brown, Cocke, et al. - 1990
302	Self-organized language modeling for speech recognition - Jelinek - 1990
210	Adherences of languages - Boasson, Nivat
88	Learning subsequential transducers for pattern recognition interpretation tasks - ONCINA, GARCÍA, et al. - 1993
54	Miniature language acquisition: A touchstone for cognitive science - Feldman, Lakoff, et al. - 1990
51	Scalable backoff language models - Seymore, Rosenfeld - 1996
19	Application of OSTIA to Machine Translation Tasks - CASTELLANOS, GALIANO, et al. - 1994
9	Grammatical Inference and Automatic Speech Recognition - VIDAL, CASACUBERTA, et al. - 1994
9	Using knowledge to improve N-Gram Language Modeling through the MGGI methodology - VIDAL - 1996
8	Learning how to understanding language - Pieraccini, Levin, et al. - 1993
8	Language Learning, Understanding and Translation - Vidal - 1994
7	Corpus-Based Machine Translation through Subsequential Transducers - ONCINA, CASTELLANOS, et al. - 1994
6	Language Understanding and Subsequential Transducer Learning - Castellanos, Vidal, et al. - 1996
4	ExampleBased Understanding and Translation Systems (EuTrans): Final Report, Part I. Deliverable of ESPRIT project No - Amengual, Benedi, et al. - 1996
4	Some Results with a Trainable Speech Translation and Understanding System - enez, Castellanos, et al. - 1995
4	Vidal: "Learning Language Translation in Limited Domains using Finite-State Models: some Extensions and Improvements - VILAR, MARZAL, et al. - 1995
3	Ney: "Improvements in Timesynchronous Beam-Search for 10000-word continuous speech recognition - Haeb-Umbach, H - 1994
3	Amengual: "Learning Extended Finite State Models for Language Translation - Vilar, Vidal, et al. - 1996
1	M.Varo: "Using Domain Information During the Learning of a Subsequential Transducer - Oncina - 1996
1	Vidal: "Experiments with Finite-State Models for Speech-Input Language Translation - Vilar, Llorens, et al. - 1996