Patent attributes
A method of performing speech recognition, comprises, at a first device: receiving an audio signal representing speech; performing a first data integrity check operation on the received audio signal; performing a speaker recognition process on the received audio signal; forwarding the received audio signal to a second device, wherein the second device comprises a speech recognition function; and forwarding an output of the first data integrity check operation to the second device. The method further comprises, at the second device: receiving the audio signal forwarded from the first device; receiving the output of the first data integrity check operation forwarded from the first device; performing a second data integrity check operation on the audio signal forwarded from the first device; and using a result of performing the speech recognition function on the audio signal forwarded from the first device only if an output of the second data integrity check operation matches the output of the first data integrity check operation forwarded from the first device.
