Speech recognition system and method

摘要

A speech input stream is fed to a first speech recogniser. A confidence measure is formed for each recognition hypothesis produced in output by the first speech recogniser and this confidence measure is compared against an acceptability threshold. Where the confidence measure of a recognition hypothesis is below the threshold, the corresponding portion of the speech input is passed to a second speech recogniser and the recognition hypothesis produced is used instead of, or as a supplement to, that output by the first speech recogniser. In a preferred embodiment, the first speech recogniser is a recogniser trained to a particular user whilst the second recogniser is one associated with a particular speech application currently being accessed by the user.