Defense of the ansatz for dynamical hierarchies
Artificial Life
Improve the Learning of Subsequential Transducers by Using Alignments and Dictionaries
ICGI '00 Proceedings of the 5th International Colloquium on Grammatical Inference: Algorithms and Applications
Inference of Finite-State Transducers by Using Regular Grammars and Morphisms
ICGI '00 Proceedings of the 5th International Colloquium on Grammatical Inference: Algorithms and Applications
A New Approach to Speech-Input Statistical Translation
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
A finite-state approach to machine translation
NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
Stochastic finite-state models for spoken language machine translation
NAACL-ANLP-EMTS '00 Proceedings of the 2000 NAACL-ANLP Workshop on Embedded machine translation systems - Volume 5
Speech translation: coupling of recognition and translation
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Probabilistic Finite-State Machines-Part II
IEEE Transactions on Pattern Analysis and Machine Intelligence
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Two-Stage Hypotheses Generation for Spoken Language Translation
ACM Transactions on Asian Language Information Processing (TALIP)
Component-based discriminative classification for hidden Markov models
Pattern Recognition
Short communication: A SomAgent statistical machine translation
Applied Soft Computing
Data driven approaches to speech and language processing
Nonlinear Speech Modeling and Applications
Hi-index | 0.00 |
Speech-to-speech translation can be approached using finite state models and several ideas borrowed from automatic speech recognition. The models can be Hidden Markov Models for the accoustic part, language models for the source language and finite state transducers for the transfer between the source and target language. A "serial architecture" would use the Hidden Markov and the language models for recognizing input utterance and the transducer for finding the translation. An "integrated architecture", on the other hand, would integrate all the models in a single network where the search process takes place. The output of this search process is the target word sequence associated to the optimal path. In both architectures, HMMs can be trained from a source-language speech corpus, and the translation model can be learned automatically from a parallel text training corpus. The experiments presented here correspond to speech-input translations from Spanish to English and from Italian to English, in applications involving the interaction (by telephone) of a customer with the front-desk of a hotel.