Speech translation: coupling of recognition and translation
نویسنده
چکیده
In speech translation, we are faced with the problem of how to couple the speech recognition process and the translation process. Starting from the Bayes decision rule for speech translation, we analyze how the interaction between the recognition process and the translation process can be modelled. In the light of this decision rule, we discuss the already existing approaches to speech translation. None of the existing approaches seems to have addressed this direct interaction. We suggest two new methods, the local averaging approximation and the monotone alignments.
منابع مشابه
The Effect of Private Speech and Self-Regulation on Translation Quality among Iranian Translation Students: A Mixed-Methods Study
The current study presents findings from a mixed-methods study of investigating the self-regulatory role of private speech (self-talk) on students’ translation quality. The aim of the study was to validate the adapted version of a self-verbalization questionnaire. The construct validity and reliability of the scale were supported by the CFA which revealed that all items reached the acceptable f...
متن کاملA Coarse-Grained Model for Optimal Coupling of ASR and SMT Systems for Speech Translation
Speech translation is conventionally carried out by cascading an automatic speech recognition (ASR) and a statistical machine translation (SMT) system. The hypotheses chosen for translation are based on the ASR system’s acoustic and language model scores, and typically optimized for word error rate, ignoring the intended downstream use: automatic translation. In this paper, we present a coarset...
متن کاملUsing Word Lattice Information for a Tighter Coupling in Speech Translation Systems
In this paper we present first experiments towards a tighter coupling between Automatic Speech Recognition (ASR) and Statistical Machine Translation (SMT) to improve the overall performance of our speech translation system. In coventional speech translation systems, the recognizer outputs a single hypothesis which is then translated by the SMT system. This approach has the limitation of being l...
متن کاملThe Effects of Collaborative Translation Task on the Apology Speech Act Production of Iranian EFL Learners
The present study aims to investigate the relative effectiveness of different types of pragmatic instruction including two collaborative translation tasks and two structured input tasks with and without explicit pragmatic instruction on the production of apologetic utterances by low-intermediate EFL learners. One hundred and fifty university students in four experimental groups and one control ...
متن کاملUsing word latice information for a tighter coupling in speech translation systems
In this paper we present first experiments towards a tighter coupling between Automatic Speech Recognition (ASR) and Statistical Machine Translation (SMT) to improve the overall performance of our speech translation system. In coventional speech translation systems, the recognizer outputs a single hypothesis which is then translated by the SMT system. This approach has the limitation of being l...
متن کامل