Method and apparatus for speech recognition
AssigneeFujitsu Limited
InventorKazuya Sako
Life of this patent
Estimating the term…
Abstract
A speech recognizing apparatus compares a speech command from a user with one of registration patterns stored in a storage unit in turn. Then if the speech command coincides with one of the registration patterns, the speech recognizing apparatus controls a predetermined electronic apparatus associated with an operation related to the registration pattern. If the speech command does not coincide with any one of the registration patterns, the speech recognizing apparatus stores into a memory the speech command as a new registration pattern in which the speech command is related to a manipulation of the electronic apparatus produced by the user immediately after speech command is produced.
Claims4
An apparatus for recognizing speech, that stores a registration pattern of a speech command and a corresponding operation, both the speech command and the corresponding operation being not prepared, and that controls an external apparatus connected thereto in accordance with the corresponding operation when the speech command is recognized by processing of speech input, comprising:
- input means for inputting speech;
- speech recognizing means for recognizing, in a command registration mode, an input speech pattern in the speech input by said input means;
- confirmation output means for providing a confirmation of a result from said speech recognizing means;
- storage means for storing a registration pattern containing a speech command included in the input speech pattern recognized by said speech recognizing means and a corresponding operation;
- and
- apparatus control means for controlling said external apparatus by outputting and inputting control data for the corresponding operation to and from the external apparatus and, in the command registration mode, registering into said storage means the corresponding operation consisting of manipulation data produced by the external apparatus either immediately before or after input of the speech containing the input speech pattern including the speech command.
A method for recognizing speech and controlling an external apparatus, comprising:
- inputting first speech signals in a command registration mode;
- recognizing an input speech pattern to be registered from the first speech signals;
- registering the speech pattern as a speech command after the input speech pattern is first recognized;
- and
- registering a new operation corresponding to the speech command and consisting of manipulation data produced by the external apparatus either immediately before or immediately after the speech command is produced.
Dependencies are inferred from the claim text.