METHODS AND APPARATUS TO PRESENT A VIDEO PROGRAM TO A VISUALLY IMPAIRED PERSON

• US 20090259473A1
• Filed: 04/14/2008
• Published: 10/15/2009
• Est. Priority Date: 04/14/2008
• Status: Active Grant

• Current Assignee: AT&T Knowledge Ventures, L.P. (AT&T, Inc.)
• Original Assignee: AT&T Knowledge Ventures, L.P. (AT&T, Inc.)
• Inventors: Schroeter, Horst, Chang, Hisao M.
• Granted Patent: US 8,229,748 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G09B 21/006 using audible presentation of the information
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G11B 2220/2545 CDs
• CPC Class Codes: G11B 2220/2562 DVDs [digital versatile discs]; Digital video discs; MMCDs; HDCDs
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence

Abstract

Methods and apparatus to present a video program to a visually impaired person are disclosed. An example method comprises receiving a video stream and an associated audio stream of a video program, detecting a portion of the video program that is not readily consumable by a visually impaired person, obtaining text associated with the portion of the video program, converting the text to a second audio stream, and combining the second audio stream with the associated audio stream.

Claims

1. A method comprising:

receiving a video stream and an associated audio stream of a video program;

detecting a portion of the video program that is not readily consumable by a visually impaired person;

obtaining text associated with the portion of the video program;

converting the text to a second audio stream; and

combining the second audio stream with the associated audio stream.

2. A method as defined in claim 1, wherein the portion of the video program that is not readily consumable by the visually impaired person is associated with a portion of the associated audio stream that does not contain any spoken words.

3. A method as defined in claim 1, further comprising presenting the combined audio stream and the portion of the video program to the visually impaired person.

4. A method as defined in claim 1, wherein obtaining the text associated with the portion of the video program comprises:

detecting that a first video frame of a portion of the video stream is substantially unchanged from a second video frame of the portion of the video stream; and

performing optical character recognition to extract the text from the first video frame, the text representing written characters presented in the first and second video frames.

5. A method as defined in claim 1, wherein obtaining the text associated with the portion of the video program comprises:

detecting that a portion of the video stream contains scrolling text; and

performing optical character recognition to extract the text from the portion of the video stream.

6. A method as defined in claim 1, wherein obtaining the text associated with the portion of the video program comprises:

detecting a link associated with the portion of the video program; and

obtaining the text from an associated-text server associated with the link, the text representing a text-based description of the portion of the video stream.

7. A method as defined in claim 6, wherein the text obtained from the associated-text server comprises markup language data having a timestamp to synchronize the second audio stream to the associated audio stream.

8. A method as defined in claim 6, wherein the link comprises at least one of an Internet protocol address or a uniform resource locator.

9. A method as defined in claim 1, wherein converting the text to the second audio stream comprises:

querying a text-to-speech (TTS) database to determine whether first audio data corresponding to a word to be converted exists; and

when the first audio data does not exist;

performing TTS synthesis to convert the word to second audio data; and

adding the second audio data to the second audio stream.

10. A method as defined in claim 9, further comprising adding the first audio data to the second audio stream when the first audio data exists.

11. A method as defined in claim 9, wherein performing the TTS synthesis to convert the word to second audio data comprises sending the word to a network-based TTS synthesis server to obtain the second audio data.

12. A method as defined in claim 1, wherein converting the text to the second audio stream comprises performing text-to-speech (TTS) synthesis.

13. A method as defined in claim 12, wherein the TTS synthesis is performed at a set-top box.

14. A method as defined in claim 12, wherein a first portion of the TTS synthesis is performed at a set-top box, and a second portion of the TTS synthesis is performed at a network-based TTS synthesis server.

15. A method as defined in claim 12, wherein the TTS synthesis is performed based on at least one of a language or a speaker persona.

16. A method as defined in claim 1, wherein the associated audio stream comprises a first audio signal associated with a front speaker and a second audio signal associated with a back speaker, and combining the second audio stream with the associated audio stream comprises combining the first audio signal and the second audio stream.

17. A set-top box (STB) comprising:

a network interface to receive a video stream and an associated audio stream;

a detector to identify a portion of the video stream that is not readily consumable by a visually impaired person;

a text locator to obtain text associated with the portion of the video stream;

a text-to-speech (TTS) module to convert the text to a second audio stream; and

a mixer to combine the second audio stream with the associated audio stream.

18. An STB as defined in claim 17, wherein the detector comprises a non-spoken audio segment detector, and the portion of the video stream that is not readily consumable by the visually impaired person is associated with a portion of the associated audio stream that does not contain any spoken words.

19. An STB as defined in claim 17, further comprising a media device interface to present the combined audio stream to the visually impaired person.

20. An STB as defined in claim 17, wherein the detector comprises a text frame detector to identify a first video frame of the portion of the video stream that is substantially unchanged from a second video frame of the portion of the video stream, and the text locator comprises an optical character recognizer to extract the text from the first video frame, the text representing written characters presented in the first and second video frames.

21. An STB as defined in claim 17, wherein the detector comprises a text frame detector to detect that the portion of the video stream that contains scrolling text, and the text locator comprises an optical character recognizer to extract the scrolling text.

22. An STB as defined in claim 17, wherein the text locator comprises:

a metadata handler to detect a link associated with the portion of the video stream; and

a text acquirer to request the text from an associated-text server associated with the link, the text representing a text-based description of the portion of the video stream.

23. An STB as defined in claim 17, wherein the TTS module comprises:

a TTS database querier to determine whether first audio data corresponding to a word to be converted exists; and

a TTS engine to perform TTS synthesis to convert the word to second audio data when the first audio data does not exist, and to add the second audio data to the second audio stream.

24. An STB as defined in claim 23, wherein the TTS engine is to add the first audio data to the second audio stream when the first audio data exists.

25. An STB as defined in claim 23, wherein the TTS engine is to perform the TTS synthesis by sending the word to a network-based TTS synthesis server to obtain the second audio data.

26. An STB as defined in claim 17, wherein the TTS module comprises:

an abbreviation analyzer to convert a first character string into a pronounceable second character string;

a pronunciation and prosody analyzer to add prosody annotations to the pronounceable second character string; and

a TTS engine to convert the annotated pronounceable second character string to second audio data.

27. An STB as defined in claim 17, wherein the TTS module is to convert the text to the second audio stream based on at least one of a language or a speaker persona.

28. An STB as defined in claim 17, wherein the associated audio stream comprises a first audio signal associated with a front speaker and a second audio signal associated with a back speaker, and the mixer is to combine the second audio stream with the associated audio stream by:

converting the second audio stream to a third audio signal; and

combining the first and third audio signals.

29-39. -39. (canceled)