Method and system for generating annotations video
First Claim
Patent Images
1. A method for processing video comprising:
- receiving a video signal;
receiving a first audio signal containing annotations, wherein each annotation is preceded by a keyword to specify a type of that annotation;
receiving a second audio signal containing environmental sounds corresponding to the video signal; and
converting the annotations into searchable annotations organized as hierarchical shot clusters using a voice-to-text conversion system.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and system for processing video signals is disclosed. The system receives a video signal, a first audio signal containing an annotation and a second audio signal containing environmental sounds corresponding to the video signal. In one embodiment the system generates searchable annotations corresponding to the video and second audio signals via the first audio signal.
-
Citations
19 Claims
-
1. A method for processing video comprising:
-
receiving a video signal; receiving a first audio signal containing annotations, wherein each annotation is preceded by a keyword to specify a type of that annotation; receiving a second audio signal containing environmental sounds corresponding to the video signal; and converting the annotations into searchable annotations organized as hierarchical shot clusters using a voice-to-text conversion system. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A system for processing video comprising:
-
a display device; a video signal displayed on the display device; a first audio signal containing annotations, wherein each annotation is preceded by a keyword to specify a type of that annotation; a second audio signal containing environmental sounds corresponding to the video signal; and a voice-to-text conversion system that converts the annotations into searchable annotations organized as hierarchical shot clusters. - View Dependent Claims (7, 8, 9, 10, 11)
-
-
12. A machine-readable medium having data stored thereon representing sets of instructions which, when executed by a machine, cause the machine to:
-
receive a video signal; receive a first audio signal containing annotations, wherein each annotation is preceded by a keyword to specify a type of that annotation; receive a second audio signal containing environmental sounds corresponding to the video signal; and convert the annotations into searchable annotations organized as hierarchical shot clusters using a voice-to-text conversion system. - View Dependent Claims (13, 14, 15)
-
-
16. An apparatus comprising:
-
an analog to digital (A/V) converter; and a processor coupled to the A/V converter, the processor to receive a video signal, receive a first audio signal containing annotations, wherein each annotation is preceded by a keyword to specify a type of that annotation, receive a second audio signal containing environmental sounds corresponding to the video signal, and convert the annotations into searchable annotations organized as hierarchical shot clusters using a voice-to-text conversion system. - View Dependent Claims (17, 18, 19)
-
Specification