SYSTEM AND METHOD FOR CONTENT RENDERING INCLUDING SYNTHETIC NARRATION
First Claim
1. A media device implemented method for capturing voice information comprising:
- receiving a request to create speech modulation;
presenting a piece of content operable for use in creating said speech modulation;
receiving a first voice sample;
determining a voice fingerprint based on said first voice sample; and
storing said voice fingerprint, wherein said voice fingerprint is operable for modulating speech during content rendering wherein a piece of content is rendered in accordance with said voice fingerprint.
2 Assignments
0 Petitions
Accused Products
Abstract
A system and method for capturing a voice information and using the voice information to modulate a content output signal. The method for capturing voice information includes receiving a request to create speech modulation and presenting a piece of textual content operable for use in creating the speech modulation based on the textual input. The method further includes receiving a first voice sample and determining a voice fingerprint based on said first voice sample. The voice fingerprint is operable for modulating speech during content rendering (e.g., audio output) such that a synthetic narration is performed based on the textual input. The voice fingerprint may then be stored and used for modulating the output.
-
Citations
20 Claims
-
1. A media device implemented method for capturing voice information comprising:
-
receiving a request to create speech modulation; presenting a piece of content operable for use in creating said speech modulation; receiving a first voice sample; determining a voice fingerprint based on said first voice sample; and storing said voice fingerprint, wherein said voice fingerprint is operable for modulating speech during content rendering wherein a piece of content is rendered in accordance with said voice fingerprint. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system for content presentation comprising:
-
a voice fingerprint determination module operable for determining a voice fingerprint based on a voice sample; a sample presentation module operable for presenting a sample of a portion of content operable for use in creating said voice fingerprint; a content access module operable to access content and select a portion of said content for audio rendering; a modulation module operable to audibly render said portion of content based on modulation based on said voice fingerprint. - View Dependent Claims (10, 11, 12, 13, 14)
-
-
15. A computer readable media comprising instructions that when executed by an electronic system implement a method for generating voice information, said method comprising:
-
receiving a request to create speech modulation; presenting content operable for use in creating said speech modulation; receiving a first voice sample; determining a voice fingerprint based on said first voice sample; and storing said voice fingerprint, wherein said voice fingerprint is operable for modulating speech during content rendering. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification