EUROSPEECH 2003 - INTERSPEECH 2003 8th European Conference on Speech Communication and Technology Geneva, Switzerland September 1-4, 2003

The Dynamic, Multi-lingual Lexicon in SmartKom

Silke Goronzy, Zica Valsan, Martin Emele, Juergen Schimanowski

Sony International (Europe) GmbH, Germany

This paper describes the dynamic, multi-lingual lexicon that was developed in the SmartKom project. SmartKom is a multimodal dialogue system that is supposed to assist the user in many applications which are characterised by their highly dynamic contents. Because of this dynamic nature various modules of the dialogue ranging from speech recognition over analysis to synthesis need to have one common knowledge source that takes care of the dynamic vocabularies that need to be processed. This central knowledge source is the lexicon. It is able to dynamically add and remove new words and generate the pronunciations for these words. We also describe the class-based language model (LM) that is used in SmartKom and that is closely coupled with the lexicon. Also evaluation results for this LM are given. Furthermore we describe our approach to dynamically generate pronunciations and give experimental results for the different classifiers we trained for this task.

Full Paper

Bibliographic reference.  Goronzy, Silke / Valsan, Zica / Emele, Martin / Schimanowski, Juergen (2003): "The dynamic, multi-lingual lexicon in smartkom", In EUROSPEECH-2003, 1937-1940.