Method and Apparatus for Training a Voice Recognition Model Database

摘要

An electronic device digitally combines a single voice input with each of a series of noise samples. Each noise sample is taken from a different audio environment (e.g., street noise, babble, interior car noise). The voice input/noise sample combinations are used to train a voice recognition model database without the user having to repeat the voice input in each of the different environments. In one variation, the electronic device transmits the user's voice input to a server that maintains and trains the voice recognition model database.

主权项

1. A method comprising:
recording an utterance; digitally combining the recorded utterance with one of a plurality of previously-recorded noise samples; training a voice recognition model database based on the digital combination; and for each of the rest of the plurality of previously-recorded noise samples, repeating the combining and training steps using the same recorded utterance.