SYSTEMS AND METHODS FOR PROCESSING INDICIA FOR DOCUMENT NARRATION

• US 20100318363A1
• Filed: 01/14/2010
• Published: 12/16/2010
• Est. Priority Date: 01/15/2009
• Status: Active Grant

• Current Assignee: T Play Holdings LLC (SoftBank Group Corp.)
• Original Assignee: K-NFB Reading Technology Inc.
• Inventors: Albrecht, Paul, Kurzweil, Raymond C., Chapman, Peter
• Granted Patent: US 8,352,269 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems

Abstract

Disclosed are techniques and systems to provide a narration of a text in multiple different voices. Further disclosed are techniques and systems for processing indicia in a document to determine a portion of words and associating a particular a voice model with the portion of words based on the indicia. During a readback process, an audible output corresponding to the words in the portion of words is generated using the voice model associated with the portion of words.

Claims

1. A computer implemented method comprising:

processing, by one or more computers, indicia in a document to determine a first portion of words in a document;

determining, by the one or more computers, a voice model associated with the first portion of words based on the first indicium; and

generating, by the one or more computers, an audible output corresponding to the words in the first portion of words using the voice model associated with the first portion of words.

2. The method of claim 1, further comprising:

processing, by the one or more computers, second indicia in a document to determine a second portion of words in the document, the second portion of words being different from the first portion of words;

determining, by the one or more computers, a voice model associated with the second portion of words based on the second indicia, the voice model associated with the second portion of words being different from the voice model associated with the first portion of words; and

generating, by the one or more computers, an audible output corresponding to the words in the second portion of words using the voice model associated with the second portion of words.

3. The method of claim 1, wherein the first indicia comprises text-based tags.

4. The method of claim 1, wherein the audible output corresponding to the words in the first portion of words does not include audible output corresponding to the first indicia.

5. The method of claim 1, wherein the first indicia is generated based on a user-applied highlighting.

6. The method of claim 5, further comprising generating the first indicia by applying, in response to a user-based selection of the first portion of words, a first highlighting indicium to the user-selected first portion of words.

7. The method of claim 1, wherein generating the audible output comprises using a text-to-speech application.

8. The method of claim 1, wherein generating the audible output comprises using an audio recording.

9. The method of claim 8, wherein the audio recording is an audio recording of a person speaking the selected words.

10. The method of claim 2, wherein the voice model associated with the first portion of words comprises a voice model configured to generate an audible output in a first language and the voice model associated with the second portion of words comprises a voice model configured to generate an audible output in a second language that is different from the first language.

11. The method of claim 2, wherein the voice model associated with the first portion of words comprises a voice model configured to generate an audible output at a first reading speed and the voice model associated with the second portion of words comprises a voice model configured to generate an audible output at a second reading speed that is different from the first reading speed.

12. The method of claim 2, wherein the voice model associated with the first portion of words comprises a voice model configured to generate an audible output at a first volume and the voice model associated with the second portion of words comprises a voice model configured to generate an audible output at a second volume that is different from the first volume.

13. The method of claim 1, wherein the first set of indicia comprises an indicia that includes a pair of text based brackets.

14. The method of claim 13, wherein the indicia that includes the pair of text based brackets comprises an indicia consisting of an opening bracket, a word or name, and a closing bracket.

15. The method of claim 2, further comprising:

modifying one or both of the first and second voice models by at least one of modifying a reading speed associated with the voice model, modifying a volume associated with the voice model, modifying the gender of the character associated with the voice model, modifying the age of the character and modifying a language of the voice model.

16. A computer program product residing on a computer readable medium, the computer program product comprising instructions for causing a processor to:

process indicia in a document to determine a first portion of words in a document;

determine a voice model associated with the first portion of words based on the first indicium; and

generate an audible output corresponding to the words in the first portion of words using the voice model associated with the first portion of words.

17. The computer program product of claim 16, wherein the computer program product further comprises instructions for causing the processor to:

process second indicia in a document to determine a second portion of words in the document, the second portion of words being different from the first portion of words;

determine a voice model associated with the second portion of words based on the second indicia, the voice model associated with the second portion of words being different from the voice model associated with the first portion of words; and

generate an audible output corresponding to the words in the second portion of words using the voice model associated with the second portion of words.

18. The computer program product of claim 17, wherein the computer program product further comprises instructions for causing the processor to:

modify one or both of the first and second voice models by at least one of modifying a reading speed associated with the voice model, modifying a volume associated with the voice model, modifying the gender of the character associated with the voice model, modifying the age of the character and modifying a language of the voice model.

19. A system comprising:

a memory; and

a computing device configured to;

process indicia in a document to determine a first portion of words in a document;

determine a voice model associated with the first portion of words based on the first indicium; and

generate an audible output corresponding to the words in the first portion of words using the voice model associated with the first portion of words.

20. The system of claim 19, wherein the computing device is further configured to:

process second indicia in a document to determine a second portion of words in the document, the second portion of words being different from the first portion of words;

determine a voice model associated with the second portion of words based on the second indicia, the voice model associated with the second portion of words being different from the voice model associated with the first portion of words; and

generate an audible output corresponding to the words in the second portion of words using the voice model associated with the second portion of words.

21. The system of claim 19, wherein the computing device is further configured to:

modify one or both of the first and second voice models by at least one of modifying a reading speed associated with the voice model, modifying a volume associated with the voice model, modifying the gender of the character associated with the voice model, modifying the age of the character and modifying a language of the voice model.