摘要 |
A speech recognition device that is capable of presenting, to a user in an easy-to-understand manner, whether or not the user's utterance is a word unregistered in a speech recognition dictionary and whether or not the utterance should be repeated due to a recognition error includes: a speech recognition vocabulary storage unit ( 102 ) which defines vocabulary for speech recognition; a speech recognition unit ( 101 ) which checks the uttered speech against the registered words; a reference similarity calculation unit ( 103 ) which calculates a similarity between the uttered speech and a combination of acoustic units, which are subwords; an unregistered word judgment unit ( 104 ) which judges, based on the result of the check by the speech recognition unit ( 101 ) and a result of the calculation performed by the reference similarity calculation unit ( 103 ), whether the uttered speech is a registered word or an unregistered word; an unregistered word storage ( 106 ) which stores unregistered words; an unregistered word candidate search unit ( 105 ) which searches the unregistered word storage unit ( 106 ) for unregistered word candidates that are likely to correspond to the uttered speech, in the case where the unregistered word judgment unit ( 104 ) judges the uttered speech to be an unregistered word; and a result display unit ( 107 ) which displays the result of the search.
|