Message recognition using shared language model
6 Assignments
0 Petitions
Accused Products
Abstract
A system is disclosed for generating text responsive to both voice and handwriting input, including a microphone, stylus, and a tablet having an flat-panel display integrated into its surface. The system performs speech and handwriting recognition using a shared language model, which in one embodiment is trainable responsive to user correction of errors in either speech or handwriting recognition. Various other systems and methods are also disclosed.
120 Citations
83 Claims
-
1-80. -80. (canceled)
-
81. A system for generating text responsive to both voice and handwriting input, comprising:
-
(a) a microphone;
(b) a stylus; and
(c) a tablet including (1) a tablet surface, (2) a flat-panel display integrated into the tablet surface and responsive to freehand input conveyed via manipulation of the stylus on or near the tablet surface to render ink-like indicia of the freehand input, and (3) a message recognizer including a speech recognizer and a handwriting recognizer;
(d) wherein the speech recognizer is responsive to voice input conveyed via the microphone to provide text data in accordance with both a shared language model and an acoustic model; and
(e) the handwriting recognizer is responsive to freehand input conveyed via the stylus to provide text data in accordance with both the shared language model and a handwriting model. - View Dependent Claims (82, 83)
-
Specification