USING CHARACTER DESCRIBER TO EFFICIENTLY INPUT AMBIGUOUS CHARACTERS FOR SMART CHINESE SPEECH DICTATION CORRECTION

摘要

A computer-implemented method is described for user disambiguation of Chinese speech recognition inputs. A speech input in Chinese is received from a user for automatic speech recognition. An unprompted character description cue is also received from the user that describes one or more of the characters in the speech input. Then automatic speech recognition of the speech input is performed based on the character description cue to determine one or more Chinese language characters that correspond to the speech input.