VOICE COMMAND RECOGNITION APPARATUS AND METHOD

• US 20150340040A1
• Filed: 02/06/2015
• Published: 11/26/2015
• Est. Priority Date: 05/20/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: MUN, Min Young, CHOI, Young Sang
• Granted Patent: US 9,953,654 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 25/03 characterised by the type of extracted parameters
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10

Abstract

A voice command recognition apparatus and method thereof are described. The voice command recognition apparatus includes audio sensors placed at different locations; a context determiner configured to determine user context based on a voice received at the audio sensors, wherein the context comprises a vocalization from a user. A command recognizer in the voice command recognition apparatus is configured to activate to recognize a voice command or remain inactive according to the recognized context.

Claims

1. A voice command recognition apparatus, comprising:

audio sensors placed at different locations;

a context determiner configured to determine user context based on a voice received at the audio sensors, wherein the context comprises a vocalization from a user; and

a command recognizer configured to activate to recognize a voice command or remain inactive according to the recognized context.

2. The voice command recognition apparatus of claim 1,

wherein the context determiner is further configured to comprise a distance calculator configured to calculate a distance from the user based on a time the voice reaches the audio sensors,

wherein the command recognizer is further configured to activate to recognize the command from the voice or remain inactive according to the calculated distance.

3. The voice command recognition apparatus of claim 1,

wherein the context determiner is further configured to comprise

a user recognizer configured to determine whether the voice is from a pre-stored specific user, and

a distance calculator configured to, in response to a determination that the voice is from the specific user, calculate a distance from the user based on an arrival time of the voice to the audio sensors, and

wherein the command recognizer is further configured to activate to recognize the voice command or remain inactive according to the calculated distance.

4. The voice command recognition apparatus of claim 1,

wherein the context determiner is further configured to comprise

a distance calculator configured to calculate a distance from the user based on a time the voice reaches the audio sensors, and

an ambient noise comparator configured to compare magnitude of difference between the voice and ambient noise,

wherein the command recognizer is further configured to activate to recognize the command from the voice or remain inactivated according to the difference between the calculated distance and the difference between the voice and the ambient noise.

5. The voice command recognition apparatus of claim 1,

wherein the context determiner is further configured to comprise

a distance calculator configured to calculate a distance from the user based on the time the voice reaches the audio sensors, and

a movement recognizer configured to recognize a movement of the user,

wherein the command recognizer is further configured to activate to recognize the command from the voice or remain inactive according to the calculated distance and the recognized movement.

6. The voice command recognition apparatus of claim 1, further comprising:

an event detector configured to detect an event,

wherein the context determiner is further configured to comprise

a distance calculator configured to calculate a distance from the user based on the time the voice reaches the respective audio sensors, and

a operation recognizer configured to recognize an operation of a device based on the event detected by the event detector,

wherein the command recognizer is further configured to activate to recognize the command from the voice or remain inactive to the calculated distance and the recognized operation.

7. The voice command recognition apparatus of claim 1, further comprising:

a motion sensor configured to detect movement; and

an event detector configured to detect an event,

wherein the context determiner is further configured to comprise

a distance calculator configured to calculate a distance from the user based on the time the voice reaches the audio sensors,

an action recognizer configured to recognize an action from the user based on the detected movement, and

an operation recognizer configured to recognize an operation of the device based on the detected event,

wherein the command recognizer is further configured to the recognized action, and the recognized action, activate to recognize the command from the voice or remain inactive according to the calculated distance.

8. A voice command recognition method, comprising:

receiving a voice at audio sensors placed at different locations of a device;

determining user context based on the voice, wherein the context comprises vocalization from a user; and

activating the device to recognize a command from the voice or remaining inactive based on the user context.

9. The voice command recognition method of claim 8,

wherein the determining of context comprises determining a distance from the user based on the time the voice reaches the audio sensors,

wherein the activating or the remaining inactive are based on the calculated distance.

10. The voice command recognition method of claim 8,

wherein the determining of context comprises

determining whether the voice is from a specific user pre-registered, and,

in response to a determination that the voice is from the specific user, calculating a distance from the user based on the time the voice reaches the audio sensors,

wherein the activating or the remaining inactive are based on the calculated distance.

11. The voice command recognition method of claim 8,

wherein the determining of context comprises

calculating a distance from the user based on the time a voice reaches the audio sensors, and

comparing magnitude of a difference between the voice and ambient noise,

wherein the activating or the remaining inactive are based on the calculated distance and the difference between the voice and the ambient noise.

12. The voice command recognition method of claim 8,

wherein the determining of context comprises

calculating a distance from the user based on the time the voice reaches the audio sensors, and

recognizing an action from the user based on movement detected by a motion sensor,

wherein the activating or the remaining inactive are based on the calculated distance and the recognized action.

13. The voice command recognition method of claim 8,

wherein the determining of context comprises

determining a distance from the user based on the time the voice reaches the audio sensors, and

recognizing an operation of the device based on an event detected by an event detector,

wherein the activating or the remaining inactive are based on the calculated distance and the recognized operation.

14. The voice command recognition method of claim 8,

wherein the determining of context comprises calculating a distance from the user based on the time the voice reaches the audio sensors,

recognizing an action from the user based on movement detected by a motion sensor, and

recognizing an operation of the device based on an event detected by an event detector,

wherein the activating or the remaining inactive are based on the calculated distance, the recognized action, and the recognized operation.

15. A computer program embodied on a non-transitory computer readable medium, the computer program being configured to control a processor to perform the method of claim 8.

16. A voice command recognizing apparatus, comprising:

audio sensors placed at different locations of a device;

a distance calculator configured to calculate a distance from a user based on arrival time of a voice relative to each audio sensor, or a time difference in arrival times relative to all the audio sensors; and

a command recognizer configured to activate in response to the calculated distance being within a distance threshold and recognize a voice command from the received voice to control the device.

17. The voice command recognition apparatus of claim 16,

wherein in response to subsequent vocal sounds being absent after a predetermined period of time, the command recognizer is automatically inactivated to a waiting state.

18. The voice command recognition apparatus of claim 16, further comprising:

a user recognizer configured to compare the received voice with a pre-stored voice to determine whether the received voice is from an authorized user, wherein in response to determining that the received voice is from the authorized user, the distance calculator switches from an inactive state to an active state.

19. The voice command recognition apparatus of claim 16, further comprising:

an ambient noise comparator 86 configured to extract a signal-to-noise ratio (SNR) from ambient noise and compare a magnitude of the received voice with a magnitude of the ambient noise received along with the received voice.

20. The voice command recognition apparatus of claim 19,

wherein, in response to the SNR being greater than a threshold and the calculated distance being within the distance threshold, the command recognizer is activated.