Media item selection using user-specific grammar

• US 10,430,024 B2
• Filed: 11/13/2013
• Issued: 10/01/2019
• Est. Priority Date: 11/13/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Sachidanandam, Vignesh, Downing, Joe, Cirrincione, Cory, Pham, Catherine
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US14/079,409
• Publication Number:
  US 20150134334A1
• Time in Patent Office: 2,148 Days
• CPC Class Codes: G06F 16/433 using audio data
• CPC Class Codes: G06F 16/632 Query formulation
• CPC Class Codes: G06F 16/73 Querying
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

A storage machine holds instructions executable by a logic machine to receive a digital representation of a spoken command. The digital representation is provided to a speech recognizer trained with a user-specific grammar library. The logic machine then receives from the speech recognizer a confidence rating for each of a plurality of different media items. The confidence rating indicates the likelihood that the media item is named in the spoken command. The logic machine then automatically plays back the media item with a greatest confidence rating.

Claims

1. A method, comprising:

receiving a digital representation of a spoken command;

providing the digital representation to a speech recognizer trained with a user-specific grammar library;

receiving from the speech recognizer a confidence rating for each of a plurality of different media items, the confidence rating indicating a likelihood that the media item is named in the spoken command;

weighting each confidence rating based on one or more identifiers mined by the user-specific grammar library;

narrowing the plurality of different media items to a selected media item based on the weighted confidence ratings;

prior to playing the selected media item, providing to a user an identification of the selected media item and indicating that the selected media item is queued for automatic playback absent a user input from the user during a queuing time interval;

absent the user input to cancel playback of the selected media item, automatically playing back the selected media item following the queuing time interval;

cancel playback of the selected media item with the greatest confidence rating responsive to receiving the user input during the queuing time interval indicating to cancel playback of the selected media item with the greatest confidence rating; and

indicate to the user a plurality of media items with the next greatest confidence ratings, excluding the selected media item with the greatest confidence rating.

2. The method of claim 1, wherein the user-specific grammar library includes item identifiers for a plurality of media items in a media library of the user.

3. The method of claim 2, wherein the user-specific grammar library further includes parent container identifiers for a plurality of parent containers comprising the plurality of media items in the user'"'"'s media library.

4. The method of claim 3, further comprising:

automatically playing back a plurality of media items included in a parent container if the parent container has a confidence rating greater than or equal to a greatest confidence rating of an individual media item.

5. The method of claim 3, wherein the user-specific grammar library includes item identifiers and parent container identifiers for media items found in media libraries belonging to members of a social graph of the user.

6. The method of claim 5, wherein the user-specific grammar library includes item identifiers and parent container identifiers for media items trending outside of the user'"'"'s social graph on an online social network.

7. The method of claim 6, wherein the user-specific grammar library includes item identifiers and parent container identifiers for media items related to a computer usage history of the user and/or an online network usage history of the user.

8. The method of claim 1, further comprising:

automatically playing back the selected media item only when a weighted confidence rating for the selected media item is larger than a threshold.

9. The method of claim 8, further comprising:

indicating to the user a plurality of media items with weighted confidence ratings closest to the threshold if no individual media item has a weighted confidence rating larger than the threshold;

receiving a second user input choosing one of the plurality of media items with weighted confidence ratings closest to the threshold for playback; and

playing back the chosen media item.

10. A computer system, comprising:

a logic machine; and

a storage machine holding instructions that, when executed by the logic machine, cause the logic machine to;

receive a digital representation of a user command from a user;

determine a confidence rating for a plurality of different media items, the confidence rating indicating a likelihood that the media item is named in the user command;

narrow the plurality of different media items to a selected media item having a greatest confidence rating;

prior to playing the selected media item with the greatest confidence rating, provide to the user an identification of the selected media item with the greatest confidence rating and indicate that the selected media item with the greatest confidence rating is queued for automatic playback absent user input during a queuing time interval;

cancel playback of the selected media item with the greatest confidence rating responsive to receiving the user input during the queuing time interval indicating to cancel playback of the selected media item with the greatest confidence rating; and

indicate to the user a plurality of media items with the next greatest confidence ratings, excluding the selected media item with the greatest confidence rating.

11. The computer system of claim 10, where the plurality of different media items includes media items in a media library of the user.

12. The computer system of claim 11, further comprising a communications system in communication with a media server, and wherein the plurality of different media items further includes media items accessible via the media server.

13. The computer system of claim 12, wherein determining the confidence rating for a media item includes weighting media items in the user'"'"'s media library more than media items accessible via the media server.

14. The computer system of claim 12, wherein the plurality of media items with the next greatest confidence ratings does not include more than one copy of a media item.

15. The computer system of claim 10, where the storage machine further holds instructions that, when executed by the logic machine, cause the logic machine to:

interpret spoken commands of the user as input indicating not to playback the selected media item with the greatest confidence rating.

16. The computer system of claim 10, where the storage machine further holds instructions that, when executed by the logic machine, cause the logic machine to:

interpret gesture commands of the user as input indicating not to playback the selected media item with the greatest confidence rating.

17. A computer system including a logic machine, and a storage machine holding instructions that, when executed by the logic machine, cause the logic machine to:

receive a digital representation of a spoken command;

provide the digital representation to a speech recognizer trained with a user-specific grammar library of a user;

receive from the speech recognizer a confidence rating for each of a plurality of different media items, the confidence rating indicating a likelihood that the media item is named in the spoken command;

narrow the plurality of different media items to a selected media item having a greatest confidence rating;

prior to playing the selected media item with the greatest confidence rating, provide to the user an identification of the selected media item with the greatest confidence rating and indicate that the selected media item with the greatest confidence rating is queued for playback;

absent a user input from the user to cancel playback of the selected media item with the greatest confidence rating, automatically playback the selected media item with the greatest confidence rating following a queuing time interval;

cancel playback of the selected media item with the greatest confidence rating responsive to the user input prior to expiration of the queuing time interval;

indicate to the user a plurality of different media items with the next greatest confidence ratings;

receive a second user input choosing one of the plurality of media items with the next greatest confidence ratings for playback; and

playback the chosen media item.

18. The computer system of claim 17, wherein the user-specific grammar library includes a plurality of item identifiers for a plurality of media items available for playback, and further includes a plurality of parent container identifiers for a plurality of parent containers comprising the plurality of media items available for playback.