USING VISUAL CUES TO DISAMBIGUATE SPEECH INPUTS

• US 20140214415A1
• Filed: 01/25/2013
• Published: 07/31/2014
• Est. Priority Date: 01/25/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Klein, Christian
• Granted Patent: US 9,190,058 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G06F 2203/0381 Multimodal input, i.e. interface arrangements enabling the user to issue commands by simultaneous use of input devices of different nature, e.g. voice plus gesture on digitizer
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Embodiments related to recognizing speech inputs are disclosed. One disclosed embodiment provides a method for recognizing a speech input including receiving depth information of a physical space from a depth camera, determining an identity of a user in the physical space based on the depth information, receiving audio information from one or more microphones, and determining a speech input from the audio input. If the speech input comprises an ambiguous term, the ambiguous term in the speech input is compared to one or more of depth image data received from the depth image sensor and digital content consumption information for the user to identify an unambiguous term corresponding to the ambiguous term. After identifying the unambiguous term, an action is taken on the computing device based on the speech input and the unambiguous term.

Claims

1. On a computing device, a method for recognizing a speech input, the method comprising:

receiving image information of a physical space from a one or more cameras;

determining an identity of a user in the physical space based on the image information;

receiving audio information from one or more microphones;

determining a speech input from the audio input;

if the speech input comprises an ambiguous term, then comparing the ambiguous term in the speech input to digital content consumption information for the user to identify an unambiguous term corresponding to the ambiguous term; and

after identifying the unambiguous term, taking an action on the computing device based on the speech input and the unambiguous term.

2. The method of claim 1, wherein the digital content consumption information for the user comprises social information, and wherein identifying the unambiguous term comprises identifying another user from the social information.

3. The method of claim 1, wherein the digital content consumption information for the user comprises past content consumption information for the user, and wherein identifying the unambiguous term comprises identifying a content item referred to by the ambiguous term from the historical content consumption information.

4. The method of claim 1, further comprising identifying one or more gestures performed by the user via the image information, and utilizing the one or more gestures to identify the unambiguous term.

5. The method of claim 4, wherein the one or more gestures indicate another person referred to in the ambiguous speech input.

6. The method of claim 5, further comprising identifying the other person indicated by the one or more gestures.

7. The method of claim 4, wherein the one or more gestures indicate an object referred to in the ambiguous speech input.

8. The method of claim 1, wherein the identity of the user is further determined based on information received from the one or more microphones.

9. The method of claim 1, further comprising identifying one or more other persons in the physical environment.

10. The method of claim 1, wherein the digital content consumption information comprises user preference information based on past digital content consumption.

11. On a computing device, a method for recognizing speech of a user, comprising:

receiving depth information of a physical space from a depth camera;

identifying one or more gestures performed by the user based on the depth information;

receiving audio information from one or more microphones;

determining a speech input from the audio input;

if the speech input comprises an ambiguous term, then utilizing the one or more gestures to identify an unambiguous term corresponding to the ambiguous term; and

after identifying the unambiguous term, taking an action on the computing device based on the speech input and the unambiguous term.

12. The method of claim 11, wherein the speech input comprises a command, and wherein the one or more gestures comprise the user pointing to an object in the physical space such that the unambiguous term is an identity of the object.

13. The method of claim 11, wherein the speech input comprises a command, and wherein the one or more gestures comprise the user pointing to another user in the physical space such that the unambiguous term is an identity of the other user.

14. The method of claim 11, wherein the speech input comprises a command, and wherein the one or more gestures comprise the user pointing to a user interface element displayed on a display device such that the unambiguous term is a selected user interface element at which the user is pointing.

15. The method of claim 11, wherein the one or more gestures include a proactive gesture performed prior to the user speaking the speech input to indicate a context of the speech input.

16. The method of claim 11, wherein the one or more gestures include a reactive gesture performed after the user makes the speech input.

17. The method of claim 11, further comprising additionally utilizing digital content consumption information of the user to disambiguate the speech input.

18. A storage device comprising instructions executable by a logic subsystem to:

receive depth information of a physical space from a depth camera;

determine an identity of a user in the physical space based on the depth information;

identify one or more gestures performed by the user based on the depth information;

receive audio information from one or more microphones;

determine a speech input from the audio input;

if the speech input comprises an ambiguous term, then utilize one or more of digital content consumption information for the user and the one or more gestures to identify an unambiguous term corresponding to the ambiguous term; and

after identifying the unambiguous term, take an action on the computing device based on the speech input and the unambiguous term

19. The storage device of claim 18, wherein the instructions are executable to determine that the one or more gestures indicate one or more of another person in the physical space and an object in the physical space.

20. The storage device of claim 18, wherein the digital content information comprises one or more of historical content consumption data, social data, and user preference data.