IDENTIFYING CORRESPONDING POSITIONS IN DIFFERENT REPRESENTATIONS OF A TEXTUAL WORK

• US 20140278354A1
• Filed: 03/13/2013
• Published: 09/18/2014
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Ganong, William F. III
• Granted Patent: US 9,613,641 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G09G 2380/14 Electronic books and readers
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal

Abstract

Described herein are techniques for determining corresponding positions between different representations of a textual work. In some of the techniques, portions of one or more representations may be processed. A determination of a corresponding position may be made in response to a request received from a user, such as a reader that desires to switch between representations. The request may indicate a position in one representation and the representation to which the user would like to switch. In response to receiving the request, one or more portions of one or more representations of a textual work may be processed. In some techniques, a corresponding position between different representations may be determined without processing the entirety of one or more representations of the textual work. For example, a corresponding position may be determined without processing an entire audio representation.

Claims

1. A method for use in identifying a target audio position, in an audio representation of a textual work, that corresponds to a first text position in an electronic representation of the textual work, the method comprising:

estimating a first estimated audio position in the audio representation based at least in part on the first text position in the electronic representation of the textual work;

performing automatic speech recognition (ASR) on a first audio segment appearing in the audio representation at the first estimated audio position to generate a first textual representation of the first audio segment;

identifying at least one second text position in the electronic representation of the textual work by searching the electronic representation of the textual work for text that matches the first textual representation; and

in response to determining that the at least one second text position does not comprise the first text position, estimating a second estimated position in the audio representation based at least in part on the at least one second text position.

2. The method of claim 1, wherein the estimating the first estimated position in the audio representation comprises:

determining a first relative position for the first text position in the electronic representation, the first relative position indicating the first text position relative to an entirety of the electronic representation; and

determining the first estimated audio position based on the first relative position.

3. The method of claim 2, wherein the estimating the second estimated audio position in the audio representation comprises:

determining a second relative position for a second text position of the at least one second text position; and

setting the second estimated audio position based at least in part on a difference between the first relative position and the second relative position.

4. The method of claim 1, further comprising:

refining the second estimated position at least in part by;

selecting a refined estimated position,

determining a new text position in the electronic representation that corresponds to the refined estimated position, and

in response to determining that the new text position does not match the first text position, selecting a next refined estimated position based at least in part on a difference between a first relative position of the first text position and a second relative position of the new text position; and

repeating the refining until the new text position in the electronic representation matches the first text position.

5. The method of claim 1, wherein determining whether the at least one second text position comprises the first text position comprises determining whether a difference between a second text position of the at least one second text position and the first text position is below a threshold.

6. The method of claim 1, further comprising:

determining the first text position at least in part by identifying a portion of the electronic representation presented to a user and setting the first text position to a position appearing in the portion.

7. The method of claim 6, wherein the setting the first text position comprises setting the first text position to a position having a predetermined relative position.

8. The method of claim 1, wherein the searching the electronic representation of the textual work for text that matches the first textual representation comprises searching the electronic representation of the textual work for text exactly matching the first textual representation.

9. The method of claim 1, wherein:

the textual work is a novel;

the electronic representation is an electronic book; and

the audio representation is an audio book.

10. At least one computer-readable storage medium having encoded thereon computer-executable instructions that, when executed by at least one computer, cause the at least one computer to carry out a method of identifying a text position in an electronic version of a textual work that corresponds to a first audio position in an audio representation of the textual work, the method comprising:

performing automatic speech recognition (ASR) on a first audio segment appearing in the audio representation at the first audio position to generate a first textual representation of the first audio segment; and

identifying the text position by searching the electronic version of the textual work for text that matches the first textual representation.

11. The at least one computer-readable storage medium of claim 10, wherein the searching the electronic representation of the textual work for text matching the first textual representation comprises searching the electronic representation of the textual work for text exactly matching the first textual representation.

12. The at least one computer-readable storage medium of claim 10, wherein the searching the electronic representation of the textual work for text matching the first textual representation comprises searching the electronic representation of the textual work for text having an edit distance, when compared to the first textual representation, below a threshold.

13. The at least one computer-readable storage medium of claim 10, wherein the method further comprises:

determining whether a mapping of corresponding positions between the audio representation and the electronic representation includes an entry that includes a position matching the first audio position or the text position,

wherein the performing ASR on the first audio segment is performed in response to determining that the mapping does not include an entry that includes a position matching the first audio position or matching the text position.

14. The at least one computer-readable storage medium of claim 10, further comprising, prior to the performing ASR and the identifying:

identifying at least one word and/or at least one phrase included in the electronic representation of the textual work that is not included in a set of words and/or phrases used by an ASR engine that performs the ASR; and

adding the at least one word and/or the at least one phrase to the set for use by the ASR engine in the performing ASR on one or more segments of the audio representation.

15. The at least one computer-readable storage medium of claim 10, wherein the performing ASR on the first audio segment is performed in response to receiving a request for the first text position corresponding to the first audio position, the request identifying the first audio position.

16. An apparatus comprising:

at least one processor; and

at least one computer-readable storage medium having encoded thereon executable instructions that, when executed by the at least one processor, cause the at least one processor to carry out a method of identifying a digital position in a digital representation of a textual work that corresponds to a hardcopy location in a hardcopy representation of at least a portion of the textual work, the method comprising;

performing a character recognition process on at least a portion of the hardcopy representation to generate a recognized textual representation; and

searching the digital representation for text matching at least some of the recognized textual representation to identify the digital position in the digital representation.

17. The apparatus of claim 16, wherein the method further comprises:

receiving an image of at least the portion of the hardcopy representation, the image comprising image data representing the at least the portion of the hardcopy representation.

18. The apparatus of claim 17, wherein:

the receiving the image comprises receiving the image from a device that generated the image, the device including a camera; and

the method further comprises transmitting, to the device, an indication of the digital position.

19. The apparatus of claim 16, wherein the searching the digital representation for text matching at least some of the textual representation comprises searching an electronic textual representation for text exactly matching the at least some of the textual representation.

20. The apparatus of claim 19, wherein:

the digital position in the digital representation is an audio position in an audio representation;

the searching the digital representation for text matching the at least some of the recognized textual representation comprises;

determining a text position at which text matching the at least some of the recognized textual representation appears in the electronic textual representation; and

determining an audio position in the audio representation corresponding to the text position at which the text appears.