Systems and methods for document narration with multiple characters having multiple moods
First Claim
Patent Images
1. A computer implemented method, comprising:
- providing by the computing device a user interface for user selection of a character from a plurality of characters and a user selection of a mood for the character, from multiple preconfigured moods associated with the character, with the moods being instantiations of a voice model associated with the character, with each instantiation of the voice model having one or more attributes of the voice model pre-modified to provide corresponding moods for the character;
receiving, by the computing device, a user selection of the character from the user interface and a user selection of the mood for the character, with the mood selected from the plural ones of the predefined moods;
rendering on a display device associated with the computing device an electronic representation of text;
associating by the computing device, the user selected character and user selected mood of the character to one or more groupings of words in the electronic representation of the text rendered on the display device;
andgenerating, by the computing device, an audible output corresponding to the one or more groupings of words by applying text corresponding to the one or more groupings of words to a text to speech synthesizer using the instantiation of the voice model corresponding to the selected character and the selected mood.
8 Assignments
0 Petitions
Accused Products
Abstract
Disclosed are techniques and systems to provide a narration of a text in multiple different voices. Further disclosed are techniques and systems for providing a plurality of characters at least some of the characters having multiple associated moods for use in document narration.
53 Citations
22 Claims
-
1. A computer implemented method, comprising:
-
providing by the computing device a user interface for user selection of a character from a plurality of characters and a user selection of a mood for the character, from multiple preconfigured moods associated with the character, with the moods being instantiations of a voice model associated with the character, with each instantiation of the voice model having one or more attributes of the voice model pre-modified to provide corresponding moods for the character; receiving, by the computing device, a user selection of the character from the user interface and a user selection of the mood for the character, with the mood selected from the plural ones of the predefined moods; rendering on a display device associated with the computing device an electronic representation of text; associating by the computing device, the user selected character and user selected mood of the character to one or more groupings of words in the electronic representation of the text rendered on the display device; and generating, by the computing device, an audible output corresponding to the one or more groupings of words by applying text corresponding to the one or more groupings of words to a text to speech synthesizer using the instantiation of the voice model corresponding to the selected character and the selected mood. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A computer program product tangibly stored by a computer readable hardware storage device, the computer program product comprising instructions for causing a processor to:
-
provide a user interface for user selection of a character from a plurality of characters and a user selection of a mood for the character, from multiple preconfigured moods associated with the character, with the moods being instantiations of a voice model associated with the character, with each instantiation of the voice model having one or more attributes of the voice model pre-modified to provide corresponding moods for the character; cause a representation of text to be rendered by a display device; receive a user selection of the character and user selection of a mood for the character; associate the user selected character and mood of the selected character to one or more groupings of words in the representation of the text rendered on the display device; and generate an audible output corresponding to the one or more groupings of words by applying text corresponding to the one or more groupings of words to a text to speech synthesize using the instantiation of the voice model corresponding to the selected character and the selected mood for the selected character. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. A system comprising:
-
a memory; a display device; and a computing device coupled to the memory and the display device, the computing device configured to; retrieve a representation of text stored in the system; render on the display device a user interface for user selection of a character from a plurality of characters and a user selection of a mood for the character, from multiple preconfigured moods associated with the character, with the moods being instantiations of a voice model associated with the character, with each instantiation of the voice model having one or more attributes of the voice model pre-modified to provide corresponding moods for the character; receive a user selection of the character and user selection of a mood for the character; render a representation of the text on a display device associated with the computing device; associate the user selected character and mood of the selected character to one or more groupings of words in the representation of the text rendered on the display device; apply a voice model corresponding to the user selected character and mood to the portion of words in a text file corresponding to the document; and generate an audible output corresponding to the one or more groupings of words by applying text corresponding to the one or more groupings of words to a text to speech synthesize using the instantiation of the voice model corresponding to. - View Dependent Claims (18, 19, 20, 21, 22)
-
Specification