Mobile Dictation Correction User Interface
AssigneeNuance Communications, Inc.
InventorWilliam Ganong
Life of this patent
Estimating the term…
Abstract
A method of speech recognition is described for use with mobile devices. A portion of an initial speech recognition result is presented on the mobile device including a set of general alternate recognition hypotheses associated with the portion of the speech recognition result. A key input representative of one or more associated letters is received from the user. The user is provided with a set of restricted alternate recognition hypotheses starting with the one or more letters associated with the key input. Then a user selection is accepted of one of the restricted alternate recognition hypotheses to represent a corrected speech recognition result.
Claims23
A method of speech recognition on a mobile device comprising:
- presenting with the mobile device a portion of an initial speech recognition result including presenting a set of general alternate recognition hypotheses associated with the portion of the speech recognition result;
- receiving from the user a key input representative of one or more associated letters;
- providing to the user a set of restricted alternate recognition hypotheses associated with the portion of the speech recognition result, the restricted alternate recognition hypotheses starting with the one or more letters associated with the key input;
- and
- accepting a user selection of one of the restricted alternate recognition hypotheses to represent a corrected speech recognition result.
A speech recognition user correction interface for a mobile device comprising:
- presenting means for presenting with the mobile device a portion of an initial speech recognition result including presenting a set of general alternate recognition hypotheses associated with the portion of the speech recognition result;
- key input means for receiving from the user a key input representative of one or more associated letters;
- alternative hypothesis means for providing to the user a set of restricted alternate recognition hypotheses associated with the portion of the speech recognition result, the restricted alternate recognition hypotheses starting with the one or more letters associated with the key input;
- and
- accepting means for accepting a user selection of one of the restricted alternate recognition hypotheses to represent a corrected speech recognition result.
A mobile user device comprising:
- a user correction interface including:
- presenting means for presenting with the mobile device a portion of an initial speech recognition result including presenting a set of general alternate recognition hypotheses associated with the portion of the speech recognition result;
- key input means for receiving from the user a key input representative of one or more associated letters;
- alternative hypothesis means for providing to the user a set of restricted alternate recognition hypotheses associated with the portion of the speech recognition result, the restricted alternate recognition hypotheses starting with the one or more letters associated with the key input;
- and
- accepting means for accepting a user selection of one of the restricted alternate recognition hypotheses to represent a corrected speech recognition result.
A method of speech recognition on a mobile device comprising:
- receiving an audio speech input from a user to a mobile device;
- processing the audio speech input with automatic speech recognition to produce speech recognition text representative of the audio speech input;
- and
- forwarding to a text application the speech recognition text and a link for retrieving the corresponding audio input.
A method of speech recognition on a mobile device comprising:
- receiving an audio speech input from a user of a mobile device;
- processing the audio speech input with automatic speech recognition having a recognition vocabulary to produce a set of speech recognition hypotheses corresponding to the audio speech input,
- wherein at least one of the recognition hypotheses includes a sequence of letters representing a word in the input which is not present in the recognition vocabulary.
Dependencies are inferred from the claim text.