Global speech user interface
First Claim
Patent Images
1. A method of providing a speech user interface for television, comprising operations of:
- analyzing utterances of different speakers to facilitate voiceprint identification of the different speakers;
performing speech recognition to transcribe spoken input into transcribed spoken commands satisfying predetermined criteria;
using the transcribed spoken commands to navigate among predetermined applications concerning operation of a television; and
responsive to voiceprint recognition of a specific speaker, varying display of the television according to identity of the specific speaker;
the operation of varying display of the television comprising each of;
causing the television to display advertisements personalized to the specific speaker;
causing the television to display programming recommendations personalized to the specific speaker;
causing the television to display video-on-demand purchase recommendations personalized to the specific speaker;
expediting an on-screen purchase transaction based upon voiceprint;
causing the television to display an interface and television content personalized to the specific speaker; and
automatically configuring the television or speech user interface according to preferences of the specific speaker.
0 Assignments
0 Petitions
Accused Products
Abstract
A global speech user interface (GSUI) comprises an input system to receive a user'"'"'s spoken command, a feedback system along with a set of feedback overlays to give the user information on the progress of his spoken requests, a set of visual cues on the television screen to help the user understand what he can say, a help system, and a model for navigation among applications. The interface is extensible to make it easy to add new applications.
57 Citations
11 Claims
-
1. A method of providing a speech user interface for television, comprising operations of:
-
analyzing utterances of different speakers to facilitate voiceprint identification of the different speakers; performing speech recognition to transcribe spoken input into transcribed spoken commands satisfying predetermined criteria; using the transcribed spoken commands to navigate among predetermined applications concerning operation of a television; and responsive to voiceprint recognition of a specific speaker, varying display of the television according to identity of the specific speaker; the operation of varying display of the television comprising each of; causing the television to display advertisements personalized to the specific speaker; causing the television to display programming recommendations personalized to the specific speaker; causing the television to display video-on-demand purchase recommendations personalized to the specific speaker; expediting an on-screen purchase transaction based upon voiceprint; causing the television to display an interface and television content personalized to the specific speaker; and automatically configuring the television or speech user interface according to preferences of the specific speaker. - View Dependent Claims (2)
-
-
3. A method of providing a speech user interface for content presentation devices, comprising operations of:
-
performing speech recognition to transcribe spoken input into transcribed spoken commands satisfying predetermined criteria; using the transcribed spoken commands to navigate among predetermined applications concerning operation of a content presentation device; responsive to recognition of a specific speaker by voice identification, varying display of the content presentation device according to identity of the specific speaker; the operation of varying display of the content presentation device comprising each of; causing the content presentation device to display advertisements personalized to the specific speaker; causing the content presentation device to display programming recommendations personalized to the specific speaker; causing the content presentation device to display video-on-demand purchase recommendations personalized to the specific speaker; expediting an on-screen purchase transaction based upon recognition of the specific speaker; causing the content presentation device to display an interface and television content personalized to the specific speaker; and automatically configuring the content presentation device or speech user interface according to preferences of the specific speaker. - View Dependent Claims (4, 5, 6, 7, 8)
-
-
9. A method of providing a speech user interface for content presentation devices, comprising operations of:
-
performing speech recognition to transcribe spoken input into transcribed spoken commands satisfying predetermined criteria; using the transcribed spoken commands to navigate among predetermined applications concerning operation of a content presentation device; responsive thereto, varying display of the content presentation device according to identity of the specific speaker; analyzing utterances of different speakers to facilitate voiceprint identification of the different speakers; and responsive to voiceprint recognition of a specific speaker, varying display of the content presentation device according to identity of the specific speaker; the operation of varying display of the content presentation device comprising each of; causing the content presentation device to display advertisements personalized to the specific speaker; causing the content presentation device to display programming recommendations personalized to the specific speaker; causing the content presentation device to display video-on-demand purchase recommendations personalized to the specific speaker; expediting a purchase transaction based upon voiceprint; causing the content presentation device to display an interface and content personalized to the specific speaker; and automatically configuring the content presentation device or speech user interface according to preferences of the specific speaker. - View Dependent Claims (10)
-
-
11. A method of providing a speech user interface for content presentation devices, comprising operations of:
-
analyzing utterances of different speakers to facilitate voiceprint identification of the different speakers; performing speech recognition to transcribe spoken input into transcribed spoken commands satisfying predetermined criteria; using the transcribed spoken commands to navigate among predetermined applications concerning operation of a content presentation device; and responsive to voiceprint recognition of a specific speaker, varying display of the content presentation device according to identity of the specific speaker; the operation of varying display of the content presentation device comprising causing the television to display advertisements personalized to the specific speaker.
-
Specification