Efficient handling of multilingual language models

Abstract

We introduce techniques for building a multilingual speech recognizer. More specifically, we present a new language model method that allows for the combination of several monolingual into one multilingual language model. Furthermore, we extend our techniques to the concept of grammars. All linguistic knowledge sources share one common interface to the search engine. As a consequence, new language model types can be easily integrated into our Ibis decoder. Based on a multilingual acoustic model, we compare multilingual statistical n-gram language models with multilingual grammars. Results are given in terms of recognition performance as well as resource requirements. They show that: (a) n-gram LMs can be easily combined at the meta level without major loss in performance; (b) grammars are very suitable to model multilinguality; (c) language switches can be significantly reduced by using the introduced techniques; (d) the resource overhead for handling multiple languages in one language model is acceptable; (e) language identification can be done implicitly during decoding.