System and method for excerpt creation by designating a text segment using speech
First Claim
Patent Images
1. A method comprising:
- displaying content from which excerpts may be extracted on a display of a device;
collecting a speech recognition vocabulary set wherein the speech recognition vocabulary set corresponds to only content visible on the display such that at least one vocabulary word in the speech recognition vocabulary set is the same as a word presented on the display;
extracting speech recognition grammar rules or statistical models from the displayed content;
receiving a speech input designating a segment of the content to be excerpted;
recognizing the speech input according to the speech recognition grammar rules or statistical models;
transferring the excerpted content to a predetermined location for storage and retrieval;
providing an organizer for categorizing the excerpted content at the predetermined location; and
creating a link to a source of the excerpted content and displaying the link with the excerpted content.
9 Assignments
0 Petitions
Accused Products
Abstract
A method including displaying content on a display of a device, receiving a speech input designating a segment of the content to be excerpted and transferring the excerpted content to a predetermined location for storage and retrieval.
-
Citations
24 Claims
-
1. A method comprising:
-
displaying content from which excerpts may be extracted on a display of a device; collecting a speech recognition vocabulary set wherein the speech recognition vocabulary set corresponds to only content visible on the display such that at least one vocabulary word in the speech recognition vocabulary set is the same as a word presented on the display; extracting speech recognition grammar rules or statistical models from the displayed content; receiving a speech input designating a segment of the content to be excerpted; recognizing the speech input according to the speech recognition grammar rules or statistical models; transferring the excerpted content to a predetermined location for storage and retrieval; providing an organizer for categorizing the excerpted content at the predetermined location; and creating a link to a source of the excerpted content and displaying the link with the excerpted content. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computer program product stored in a memory comprising computer readable program code embodied in a computer readable medium for:
-
displaying content from which excerpts may be extracted on a display of a device; collecting a speech recognition vocabulary set wherein the speech recognition vocabulary set corresponds to only content visible on the display such that at least one vocabulary word in the speech recognition vocabulary set is the same as a word presented on the display; extracting speech recognition grammar rules or statistical models from the displayed content; receiving a speech input designating a segment of the content to be excerpted; and recognizing the speech input according to the speech recognition grammar rules or statistical models; transferring the excerpted content to a predetermined location for storage and retrieval; providing an organizer for categorizing the excerpted content at the predetermined location; and creating a link to a source of the excerpted content and displaying the link with the excerpted content. - View Dependent Claims (9)
-
-
10. A system comprising:
-
a remote server; and a portable communication device including a display configured to present predetermined content from which excerpts may be extracted, and a processor configured to; request the predetermined content from the remote server; collect a speech recognition vocabulary set wherein the speech recognition vocabulary set corresponds to only content visible on the display such that at least one vocabulary word in the speech recognition vocabulary set is the same as a word presented on the display; extract speech recognition grammar rules or statistical models from the displayed content; recognize a speech input according to the speech recognition grammar rules or statistical models for designating a segment of the content to be excerpted; transfer the excerpted content to a predetermined location for storage and retrieval; provide an organizer for categorizing the excerpted content at the predetermined location; and create a link to a source of the excerpted content and displaying the link with the excerpted content. - View Dependent Claims (11, 12, 13, 14)
-
-
15. An apparatus comprising:
-
at least one input device configured to receive a speech input; a display configured to present predetermined content acquired by the apparatus from which excerpts may be extracted; and a processor configured to; collect a speech recognition vocabulary set wherein the speech recognition vocabulary set corresponds to only content visible on the display such that at least one vocabulary word in the speech recognition vocabulary set is the same as a word presented on the display; extract speech recognition grammar rules or statistical models from the presented content; recognize the speech input according to the speech recognition grammar rules or statistical models for designating a segment of the content to be excerpted; transfer the excerpted content to a predetermined location for storage and retrieval; provide an organizer for categorizing the excerpted content at the predetermined location; and create a link to a source of the excerpted content and displaying the link with the excerpted content. - View Dependent Claims (16, 17, 18, 19, 20)
-
-
21. A user interface comprising:
-
at least one input device configured to receive a speech input; a display configured to present predetermined content acquired by the apparatus from which excerpts may be extracted; and a processor configured to; collect a speech recognition vocabulary set wherein the speech recognition vocabulary set corresponds to only content visible on the display such that at least one vocabulary word in the speech recognition vocabulary set is the same as a word presented on the display; extract speech recognition grammar rules or statistical models from the presented content; recognize the speech input according to the speech recognition grammar rules or statistical models for designating a segment of the content to be excerpted; transfer the excerpted content to a predetermined location for storage and retrieval; provide an organizer for categorizing the excerpted content at the predetermined location; and create a link to a source of the excerpted content and displaying the link with the excerpted content. - View Dependent Claims (22, 23, 24)
-
Specification