SPEECH RECOGNITION SYSTEM

摘要

The invention is directed to a method for automatically generating a vocabulary for a speech recognizer, comprising the steps of receiving digital word data, in particular, name data, automatically searching for a word entry in a predetermined dictionary matching at least part of the received word data, wherein the dictionary comprises a phonetic transcription for each word entry and automatically phonetically transcribing each part of the received word data for which no matching word entry was determined.