Expanding The Domain Of A Multi-Lingual Speech-To-Speech Translation System
نویسندگان
چکیده
JANUS is a multi-lingual speech-to-speech translation system, which has been designed to translate spontaneous spoken language in a limited domain. In this paper, we describe our recent preliminary e orts to expand the domain of coverage of the system from the rather limited Appointment Scheduling domain, to the much richer Travel Planning domain. We compare the two domains in terms of out-of-vocabulary rates and linguistic complexity. We discuss the challenges that these di erences impose on our translation system and some planned changes in the design of the system. Initial evaluations on Travel Planning data are also presented.
منابع مشابه
Testing Generality in Janus: a Multi-lingual Speech Translation System
For speech translation to be practical and useful, speech translation systems should be portable to multiple languages without substantial modi cation. We present the results of expanding the English-based JANUS speech translation system [1] to translate from spoken German sentences to English and Japanese utterances. We also report the results of implementing part of the LPNN speech recognitio...
متن کاملJANUS: a Multi-lingual Speech-to-speech Translation System for Spontaneously Spoken Language in a Limited Domain
Janus is a multilingual speech translation system currently operating in the domain of meeting scheduling. Translating spontaneous speech requires a high degree of robustness to overcome the dissuencies of spoken language as well as errors in speech recognition. In this system description, we focus on the robust speech translation components in Janus|the skipping GLR* parser, the segmentation o...
متن کاملSpeech{language Integration in a Multi{lingual Speech Translation System
In this paper we report on our e orts to combine speech and language processing toward multi-lingual spontaneous speech translation. The ongoing work extends our JANUS system e ort toward handling spontaneous spoken discourse and multiple languages. A major objective of this project is to maximize the number of modules, methods and data structures that are language-independent and extensible to...
متن کاملA Trainable Approach for Multi-Lingual Speech-To-Speech Translation System
This paper presents a statistical speech-to-speech machine translation (MT) system for limited domain applications using a cascaded approach. This architecture allows for die creation of multilingual applications. In this paper, the system architecture and its components, including the speech recognition, parsing, information extraction, translation, natural language generation (NLG) and textto...
متن کاملMulti-lingual Spoken Dialog Translation System Using Transfer-driven Machine Translation
This paper describes a Transfer-Driven Machine Translation (TDMT) system as a prototype for efficient multi-lingual spoken-dialog translation. Currently, the TDMT system deals with dialogues in the travel domain, such as travel scheduling, hotel reservation, and trouble-shooting, and covers almost all expressions presented in commercially-available travel conversation guides. In addition, to pu...
متن کامل