Voice and speech recognition with speech-independent vocabulary expansion e.g. for mobile (cell) phones etc, requires generating phonetic transcription from acoustic voice /speech signals

摘要

A method for expanding the vocabulary of a voice/speech recognition system, in which new, acceptable words are input several times as acoustic voice or speech signals from which corresponding phonetic transcriptions are generated. These transcriptions are evaluated as word hypotheses and according to specified criteria are combined into a single phonetic representation of the new word.