Finite-State Transducers For Speech-Input Translation (2001)
| Venue: | IEEE Automatic Speech Recognition and Understanding Workhsop, ASRU’01 |
| Citations: | 9 - 3 self |
BibTeX
@INPROCEEDINGS{Casacuberta01finite-statetransducers,
author = {F. Casacuberta},
title = {Finite-State Transducers For Speech-Input Translation},
booktitle = {IEEE Automatic Speech Recognition and Understanding Workhsop, ASRU’01},
year = {2001}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Nowadays, hidden Markov models (HMMs) and n-grams are the basic components of the most successful speech recognition systems. In such systems, HMMs (the acoustic models) are integrated into a n-gram or a stochastic finite-state grammar (the language model). Similar models can be used for speech translation, and HMMs (the acoustic models) can be integrated into a finite-state transducer (the translation model). Moreover, the translation process can be performed by searching for an optimal path of states in the integrated network. The output of this search process is a target word sequence associated to the optimal path. In speech translation, HMMs can be trained from a source speech corpus, and the translation model can be learned automatically from a parallel training corpus.
