Recording information in response to spoken requests

• US 6,456,978 B1
• Filed: 01/31/2000
• Issued: 09/24/2002
• Est. Priority Date: 01/31/2000
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Hicks, David G., Wymore, Ben S., Genly, Christopher H.
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/494,489
• Time in Patent Office: 967 Days
• Field of Search: 704/275, 704/270, 704/256, 704/257, 704/251, 704/246, 704/231, 345/158, 345/700, 348/734
• US Class Current: 704/275
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/4334 Recording operations recording of a television signal H04N5/76; arrangements for recording or accumulating broadcast information or broadcast-related information H04H60/27
• CPC Class Codes: H04N 21/440236 by media transcoding, e.g. video is transformed into a slideshow of still pictures, audio is converted into text
• CPC Class Codes: H04N 21/47214 for content reservation or setting reminders; for requesting event notification, e.g. of sport results or stock market stock exchange data over packet-switching network H04L12/1804; push services over packet-switching network H04L12/1859; notification of incoming messages in packet switching networks H04L51/224
• CPC Class Codes: H04N 21/8405 represented by keywords
• CPC Class Codes: H04N 5/782 on tape

Abstract

A system allows a user to use conversational commands to control the recording of video programming. In some embodiments of the present invention, these natural language commands may be also utilized to manage a video library or to manage a schedule for video recordings. The video recording device may be an analog or digital system.

Claims

1. A system comprising:

a speech recognizer that recognizes spoken commands for recording programming information;

an interface that converts the recognized commands to a format compatible with a video recording device; and

a memory that stores a meaning derived from said speech recognizer and historical information about previously recognized speech and uses the historical information to correct the meaning derived from said speech recognizer.

2. The system of claim 1 wherein said system parses a select clause and a where clause generated by recognition of a spoken command.

3. The system of claim 1 including a digital video recording device that communicates with said interface.

4. The system of claim 3 wherein said speech recognizer determines whether a query includes two different types of variables and if so, does not use the historical information to alter the meaning derived from said speech recognizer.

5. The system of claim 4 wherein said speech recognizer determines whether only one type of variable is included in a spoken command and if so, merges the variable with historical information to derive a meaning for the command.

6. The system of claim 1 including a speech synthesizer and a memory that stores an indication when an attribute recognized by the speech recognizer is spoken by the speech synthesizer.

7. The system of claim 1 including a memory that stores a library of stored video files.

8. The system of claim 1 further including a processor coupled to a speaker and microphone, the output from said speaker being subtracted from the output of said microphone to reduce interference between the audio portion of the programming and a spoken command.

9. The system of claim 1 including a television coupled to a set-top box and a remote control that controls said set-top box.

10. The system of claim 1 including a graphical user interface that operates with said recognizer to enable programming to be recorded in response to a spoken command.

11. A method comprising:

recognizing a spoken command to record programming information;

providing the recognized command to a video recording device;

storing a meaning derived from recognizing a spoken command and historical information about a previously spoken command; and

using the historical information to correct the meaning derived from a current spoken command.

12. The method of claim 11 including parsing select and where variables.

13. The method of claim 11 including determining whether the spoken command includes two different types of variables and if so, refraining from using historical information to alter the meaning derived from the spoken command.

14. The method of claim 13 including determining whether only one type of variable is included in a spoken command and if so, merging the variable with historical information to derive a meaning for the command.

15. The method of claim 11 including responding to voice commands to manage a schedule for recording an audio/visual program.

16. The method of claim 11 including searching through fields representing information about stored audio/visual programs to locate programming to be recorded.

17. A The method of claim 16 including assigning a tag to each audio/visual program stored in said system and identifying a tag in response to said search.

18. An article comprising a medium that stores instructions that enables a processor-based system to:

recognize a spoken command to record programming information;

provide the recognized command to a video recording device; and

store a meaning derived from recognizing a spoken command and historical information about a previously recognized spoken command and use the historical information to correct the meaning derived from a current spoken command.

19. The article of claim 18 further storing instructions that cause a processor-based system to parse select and where variables.

20. The article of claim 18 further storing instructions that enable a processor-based system to determine whether the spoken command includes two different types of variables and if so to refrain from using historical information to alter the meaning derived from the spoken command.

21. The article of claim 20 further storing instructions that cause a processor-based system to determine whether only one type of variable is included in the spoken command and if so, merge the variable with historical information to derive a meaning for the command.

22. The article of claim 18 further storing instructions that cause a processor-based system to respond to spoken commands to organize a library of recorded audio/visual programs.

23. The article of claim 18 further storing instructions that cause a processor-based system to respond to voice commands to manage a schedule for recording an audio/visual program.

24. The article of claim 18 further storing instructions that cause a processor-based system to search for fields representing information about stored audio/visual programs to locate programming to be recorded.

25. The article of claim 24 further storing instructions that cause a processor-based system to assign a tag to each audio/visual program stored in said system and identify a tag in response to said search.

39. The article of claim 24 further storing instructions that enable a processor-based system to search for fields representing information about stored audio/visual programs to locate programming to be recorded.

26. A system comprising:

a speech recognizer that recognizes spoken commands for recording programming information;

an interface that converts the recognized commands to a format compatible with a video recording device;

a processor;

a speaker and microphone coupled to the processor, the output from said speaker being subtracted from the output of said microphone to reduce interference between the audio portion of the programming in a spoken command.

27. A system comprising:

a speech recognizer that recognizes spoken commands for recording programming information;

an interface that converts the recognized commands to a format compatible with a video recording device; and

a processor coupled to a speaker and microphone, the output from said speaker being subtracted from the output of said microphone to reduce interference between the audio portion of the programming and a spoken command.

28. A system comprising:

a speech recognizer that recognizes spoken commands for recording programming information;

an interface that converts the recognized commands to a format compatible with a video recording device;

a memory that stores a meaning derived from said speech recognizer and historical information about previously recognized speech and uses the historical information to correct the meaning derived from said speech recognizer; and

wherein said system parses a select clause and a where clause generated by recognition of a spoken command.

29. The system of claim 28 including a speech synthesizer and a memory that stores an indication when an attribute recognized by the speech recognizer is spoken by the speech synthesizer.

30. The system of claim 28 including a memory that stores a library of stored video files.

31. The system of claim 28 including a television coupled to a set-top box and a remote control that controls said set-top box.

32. The system of claim 28 including a graphical user interface that operates with said recognizer to enable programming to be recorded in response to a spoken command.

33. The system of claim 28 including a digital video recording device that communicates with said interface.

34. An article comprising a medium that stores instructions that enable a processor-based system to:

recognize a spoken command to record programming information;

provide the recognized command to a video recording device;

parse select and where variable;

store a meaning derived from recognizing a spoken command and historical information about a previously recognized spoken command; and

use historical information to correct the meaning derived from a current spoken command.

35. The article of claim 34 further storing instructions that enable a processor-based system to determine whether the spoken command includes two different types of variables and if so to refrain from using historical information to alter the meaning derived from the spoken command.

36. The article of claim 34 further storing instructions that enable a processor-based system to determine whether only one type of variable is included in the spoken command and if so, merge the variable with historical information to derive a meaning for the command.

37. The article of claim 34 further storing instructions that enable a processor-based system to respond to spoken commands to organize a library of recorded audio/visual programs.

38. The article of claim 34 further storing instructions that enable a processor-based system to respond to voice commands to manage a schedule for recording an audio/visual program.

40. The article of claim 34 further storing instructions that enable a processor-based system to assign a tag to each audio/visual program stored in said system and identify a tag in response to said search.

41. A system comprising:

a speech recognizer that recognizes spoken commands for recording programming information;

an interface that converts the recognized commands to a format compatible with a video recording device;

a processor coupled to a speaker and a microphone, the output from said speaker being subtracted from the output of said microphone to reduce interference between the audio portion of the programming and a spoken command; and

wherein said system parses a select clause and a where clause generated by recognition of a spoken command.