Audio book smart pause

Patent metadata

Field	Value
Publication number	US-10282162-B2
Application number	US-201615169374-A
Country	US
Kind code	B2
Filing date	May 31, 2016
Priority date	Dec 17, 2013
Publication date	May 7, 2019
Grant date	May 7, 2019

Abstract

A user device that plays back audio books for a user can include a dynamic pause that provides a user with greater flexibility in when to pause playback of an audio book. Dynamic pause includes initiating playback of an audio book using a user device; receiving a pause request as input to the user device, the pause request received at an input time index during playback of the audio book; retrieving a subset of candidate pause points, each candidate pause point comprising a time index within the audio book that corresponds to a break point located within an eBook corresponding to the audio book; selecting one of the candidate pause points from the subset, the time index of the selected candidate pause point determining a pause time index when playback is to be paused; and pausing the playback at the pause time index.

First claim

What is claimed is:

1. A method comprising:
accessing, by a server, an audio book associated with an eBook that includes text;
generating, by the server, a speech-to-text version of the audio book by at least:
performing speech-to-text recognition on the audio book; and
correlating each of a plurality of locations within the text of the eBook to a respective time index in the audio book;

identifying, by the server, a plurality of break points in the eBook, each break point from the plurality of break points corresponding to one of the plurality of locations;
generating, by the server and based on the speech-to-text version of the audio book, a plurality of candidate pause points by at least correlating, for each break point from the plurality of break points, a respective location from the plurality of locations in the eBook of the corresponding break point with one of the respective time indices in the audio book corresponding to the respective location;
receiving, by the server, a request for the plurality of candidate pause points from a user device; and
providing, by the server, the plurality of candidate pause points to the user device.

2. The method of claim 1 , wherein:
each break point of the plurality of break points includes a type of the break point;
the type of the break point is one of a sentence end, paragraph end, chapter end, or font change; and
each candidate pause point of the plurality of candidate pause points includes the type of the break point associated with the candidate pause point.

3. The method of claim 1 , further comprising generating an image-to-text version of the eBook by performing image-to-text recognition on an image format of the eBook.

4. The method of claim 1 , wherein the audio book and the eBook are stored together in a single data construct.

5. The method of claim 1 , wherein identifying the plurality of break points comprises parsing the text of the eBook.

6. The method of claim 1 , further comprising assigning a respective score to each of the plurality of candidate pause points, wherein the respective score for each of the plurality of candidate pause points represents an importance of the corresponding candidate pause point.

7. The method of claim 6 , wherein each of the respective scores is assigned based on a type of the break point associated with the corresponding candidate pause point.

8. A non-transitory computer-readable storage medium storing executable computer program instructions that, when executed by a processor, cause the processor to:
access an audio book associated with an eBook that includes text;
generate a speech-to-text version of the audio book by at least:
performing speech-to-text recognition on the audio book; and
correlating each of the plurality of locations within the text of the eBook to a respective time index in the audio book;

identify a plurality of break points in the eBook, each break point from the plurality of break points corresponding to one of the plurality of locations;
generate, based on the speech-to-text version of the audio book, a plurality of candidate pause points by at least correlating, for each break point from the plurality of break points, a respective location from the plurality of locations in the eBook of the corresponding break point with one of the respective time indices in the audio book corresponding to the respective location;
receive a request for the plurality of candidate pause points from a user device; and
provide the plurality of candidate pause points to the user device.

9. The non-transitory computer readable medium of claim 8 , wherein:
each break point of the plurality of break points includes a type of the break point;
the type of the break point is one of a sentence end, paragraph end, chapter end, or font change; and
each candidate pause point of the plurality of candidate pause points includes the type of the break point associated with the candidate pause point.

10. The non-transitory computer readable medium of claim 8 , wherein the computer program instructions further comprise instructions that cause the processor to generate an image-to-text version of the eBook by performing image-to-text recognition on an image format of the eBook.

11. The non-transitory computer readable medium of claim 8 , wherein the instructions for identifying the plurality of break points further comprise instructions that cause the processor to parse the text of the eBook.

12. The non-transitory computer readable medium of claim 8 , wherein the computer program instructions further comprise instructions that cause the processor to assign a respective score to each of the plurality of candidate pause points, wherein the respective score for each of the plurality of candidate pause points represents an importance of the corresponding candidate pause point.

13. A computer system, comprising:
a processor; and
a computer-readable storage medium comprising executable computer program instructions that, when executed, cause the processor to:
access an audio book associated with an eBook that includes text;
generate a speech-to-text version of the audio book by at least:
performing speech-to-text recognition on the audio book; and
correlating each of the plurality of locations within the text of the eBook to a respective time index in the audio book;

identify a plurality of break points in the eBook, each break point from the plurality of break points corresponding to one of the plurality of locations;
generate, based on the speech-to-text version of the audio book, a plurality of candidate pause points by at least correlating, for each break point from the plurality of break points, a respective location from the plurality of locations in the eBook of the corresponding break point with one of the respective time indices in the audio book corresponding to the respective location;
receive a request for the plurality of candidate pause points from a user device; and
provide the plurality of candidate pause points to the user device.

14. The system of claim 13 , wherein:
each break point of the plurality of break points includes a type of the break point;
the type of the break point is one of a sentence end, paragraph end, chapter end, or font change; and
each candidate pause point of the plurality of candidate pause points includes the type of the break point associated with the candidate pause point.

15. The system of claim 13 , wherein the computer program instructions further comprise instructions that cause the processor to generate an image-to-text version of the eBook by performing image-to-text recognition on an image format of the eBook.

16. The system of claim 13 , wherein the instructions for identifying the plurality of break points further comprise instructions that cause the processor to parse the text of the eBook.

17. The system of claim 13 , wherein the computer program instructions further comprise instructions that cause the processor to assign a respective score to each of the plurality of candidate pause points, wherein the respective score for each of the plurality of candidate pause points represents an importance of the corresponding candidate pause point.

Assignees

• Google Inc
• Google Llc

Inventors

• Duga Brady

Classifications

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G06F15/0291 Primary

  for reading, e.g. e-books (constructional details of portable computers G06F1/1613) · CPC title

• G09B19/04

  Speaking (with audible presentation of the material to be studied G09B5/04) · CPC title

• B42D9/007

  Loose bookmarkers · CPC title

• G06F17/3074

  Physics · mapped topic