System and method for creating a presentation using natural language
First Claim
1. A method comprising:
- at a first time, prior to a presentation on a presentation device;
receiving, on the presentation device, a grammar which assigns semantic representations to natural language input; and
updating the grammar based on a searchable plurality of presentation source files stored on a storage device connected to the presentation device via a network, to yield an updated grammar, wherein the searchable plurality of presentation source files comprise one of audio clips and video clips, wherein the searchable plurality of presentation source files is processed by extracting content from each searchable presentation source file to generate(1) a web-based form of each searchable presentation source file;
(2) a listing of key phrases; and
(3) a corpus of all sentences that appear in all the searchable presentation source files; and
at a second time after the first time, during the presentation, and on the presentation device;
receiving, from a user, a spoken natural language content request for a presentation source file from the searchable plurality of presentation source files;
identifying possible presentation source files in the searchable plurality of presentation source files, wherein the possible presentation source files are identified by using the updated grammar to process the spoken natural language content request;
receiving, from the user, input identifying the presentation source file from the possible presentation source files, wherein the input is in a modality distinct from speech; and
adding the presentation source file to a deck for use in the presentation.
5 Assignments
0 Petitions
Accused Products
Abstract
The invention provides for a system, method, and computer readable medium storing instructions related to controlling a presentation in a multimodal system. The method embodiment of the invention is a method for the retrieval of information on the basis of its content for incorporation into an electronic presentation. The method comprises receiving from a user a content-based request for at least one segment from a first plurality of segments within a media presentation preprocessed to enable natural language content searchability; in response to the request, presenting a subset of the first plurality of segments to the user; receiving a selection indication from the user associated with at least one segment of the subset of the first plurality of segments and adding the selected at least one segment to a deck for use in a presentation.
60 Citations
11 Claims
-
1. A method comprising:
-
at a first time, prior to a presentation on a presentation device; receiving, on the presentation device, a grammar which assigns semantic representations to natural language input; and updating the grammar based on a searchable plurality of presentation source files stored on a storage device connected to the presentation device via a network, to yield an updated grammar, wherein the searchable plurality of presentation source files comprise one of audio clips and video clips, wherein the searchable plurality of presentation source files is processed by extracting content from each searchable presentation source file to generate (1) a web-based form of each searchable presentation source file; (2) a listing of key phrases; and (3) a corpus of all sentences that appear in all the searchable presentation source files; and at a second time after the first time, during the presentation, and on the presentation device; receiving, from a user, a spoken natural language content request for a presentation source file from the searchable plurality of presentation source files; identifying possible presentation source files in the searchable plurality of presentation source files, wherein the possible presentation source files are identified by using the updated grammar to process the spoken natural language content request; receiving, from the user, input identifying the presentation source file from the possible presentation source files, wherein the input is in a modality distinct from speech; and adding the presentation source file to a deck for use in the presentation. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A system comprising:
-
a processor; and a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising; at a first time, prior to a presentation on a presentation device; receiving, on the presentation device, a grammar which assigns semantic representations to natural language input; and updating the grammar based on searchable plurality of presentation source files stored on a storage device connected to the presentation device via a network, to yield an updated grammar, wherein the searchable plurality of presentation source files comprise one of audio clips and video clips, wherein the searchable plurality of presentation source files is processed by extracting content from each searchable presentation source file to generate (1) a web-based form of each searchable presentation source file; (2) a listing of key phrases; and (3) a corpus of all sentences that appear in all the searchable presentation source files; and at a second time after the first time, during the presentation, and on the presentation device; receiving, from a user, a spoken natural language content request for a presentation source file from the searchable plurality of presentation source files; identifying possible presentation source files in the searchable plurality of presentation source files, wherein the possible presentation source files are identified by using the updated grammar to process the spoken natural language content request; receiving, from the user, input identifying the presentation source file from the possible presentation source files, wherein the input is in a modality distinct from speech; and adding the presentation source file to a deck for use in the presentation. - View Dependent Claims (7, 8, 9, 10)
-
-
11. A computer-readable storage medium having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
-
at a first time, prior to a presentation on a presentation device; receiving, on the presentation device, a grammar which assigns semantic representations to natural language input; and updating the grammar based on searchable plurality of presentation source files stored on a storage device connected to the presentation device via a network, to yield an updated grammar, wherein the searchable plurality of presentation source files comprise one of audio clips and video clips, wherein the searchable plurality of presentation source files is processed by extracting content from each searchable presentation source file to generate (1) a web-based form of each searchable presentation source file; (2) a listing of key phrases; and (3) a corpus of all sentences that appear in all the searchable presentation source files; and at a second time after the first time, during the presentation, and on the presentation device; receiving, from a user, a spoken natural language content request for a presentation source file from the searchable plurality of presentation source files; identifying possible presentation source files in the searchable plurality of presentation source files, wherein the possible presentation source files are identified by using the updated grammar to process the spoken natural language content request; receiving, from the user, input identifying the presentation source file from the possible presentation source files, wherein the input is in a modality distinct from speech; and adding the presentation source file to a deck for use in the presentation.
-
Specification