LANGUAGE MODEL MODIFICATION FOR LOCAL SPEECH RECOGNITION SYSTEMS USING REMOTE SOURCES

摘要

A language model is modified for a local speech recognition system using remote speech recognition sources. In one example, a speech utterance is received. The speech utterance is sent to at least one remote speech recognition system. Text results corresponding to the utterance are received from the remote speech recognition system. A local text result is generated using local vocabulary. The received text results and the generated text result are compared to determine words that are out of the local vocabulary and the local vocabulary is updated using the out of vocabulary words.

主权项

1. A method comprising:
receiving a speech utterance at a local device; sending the speech utterance to at least one remote speech recognition system; receiving a text result corresponding to the utterance from the remote speech recognition system; generating a text result corresponding to the utterance at the local device using a local language model including a local vocabulary in a local lexicon; comparing the received text result and the generated text result to determine words that are out of the local vocabulary; and updating the local language model using the out of vocabulary words.