Abstract:
Automatic language identification is an important problem in building multilingual speech recognition and understanding systems. We have developed a front-end LID module based on LVCSR to identify English, German, and Spanish language for use in spontaneous speech-to-speech translation. We studied the constitution of different levels of knowledge to identify a language, i.e. the phonetic, phonotactic, lexical, and syntactic-semantic knowledge. A comparison of LID systems using different levels of these knowledge sources is presented. We showed that the incorporation of lexical and linguistic knowledge leads to a reduction of the language identification error by up to 50%.
copied = false, 2000);
">
@conference{Schultz-1995-13908,
author = {Tanja Schultz And Ivica Rogina And Alex Waibel},
title = {Experiments with LVCSR Based Language Identification},
booktitle = {Proceedings of Speech Research Symposium (SRS '95)},
year = {1995},
month = {June},
pages = {89 - 94},
}
author = {Tanja Schultz And Ivica Rogina And Alex Waibel},
title = {Experiments with LVCSR Based Language Identification},
booktitle = {Proceedings of Speech Research Symposium (SRS '95)},
year = {1995},
month = {June},
pages = {89 - 94},
}