Voice control device and method for deciding response of voice control according to recognized speech command and detection output derived from processing sensor data

• US 9,691,382 B2
• Filed: 11/13/2013
• Issued: 06/27/2017
• Est. Priority Date: 03/01/2013
• Status: Active Grant

• Current Assignee: MediaTek, Inc.
• Original Assignee: MediaTek, Inc.
• Inventors: Hsu, Chao-Ling, Cheng, Yiou-Wen, Shih, Xin-Wei, Lin, Jyh-Horng
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US14/078,551
• Publication Number:
  US 20140249820A1
• Time in Patent Office: 1,322 Days
• Field of Search: 704251
• 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 3/167 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 2015/223 Execution procedure of a spoken command

Abstract

A voice control device has a speech command recognizer, a sensor data processor and a decision making circuit. The speech command recognizer is arranged for performing speech command recognition to output a recognized speech command. The sensor data processor is arranged for processing sensor data generated from at least one auxiliary sensor to generate a detection output. The decision making circuit is arranged for deciding a response of the voice control device according to the recognized speech command and the detection output. The same speech command is able to trigger difference responses according to the detection output (e.g., detected motion). Besides, an adaptive training process may be employed to improve the accuracy of the sensor data processor. Hence, the voice control device may have improved performance of the voice control feature due to a reduce occurrence probability of miss errors and false alarm errors.

Claims

1. A voice control device, comprising:

a speech command recognizer, arranged for performing speech command recognition to output a recognized speech command;

a sensor data processor, arranged for processing sensor data generated from at least one auxiliary sensor to determine a motion of a mobile device comprising the voice control device, to generate a detection output; and

a decision making circuit, arranged for deciding a response of the voice control device according to the recognized speech command and the detection output;

wherein when the detection output indicates a first motion of the mobile device, the voice control device has a first response for the recognized speech command; and

when the detection output indicates a second motion of the mobile device, the voice control device has a second response for the same recognized speech command, where the second motion is different from the first motion, and the second response is different from the first response.

2. The voice control device of claim 1, wherein the speech command recognizer includes a predefined command set which is consistently used during the speech command recognition, and determines the recognized speech command according to at least the predefined command set.

3. The voice control device of claim 1, wherein the at least one auxiliary sensor includes at least one of an accelerometer, an ambient temperature sensor, a gravity sensor, an ambient light sensor, and a Gyro sensor.

4. The voice control device of claim 1, wherein the sensor data processor is a motion detector arranged to perform motion detection according to the sensor data.

5. The voice control device of claim 4, wherein the motion detector comprises:

an adaptive training unit, arranged to train at least one motion model by an adaptive training process;

a storage unit, arranged to store the at least one motion model trained by the adaptive training unit; and

a motion evaluation unit, arranged to determine the detection output according to the sensor data and the at least one motion model.

6. The voice control device of claim 5, wherein the adaptive training process is an explicit training process performed before the voice control device is in normal operation.

7. The voice control device of claim 5, wherein the adaptive training process is an implicit training process performed while the voice control device is in normal operation.

8. A voice control method performed by a mobile device, comprising:

performing speech command recognition to output a recognized speech command;

processing sensor data generated from at least one auxiliary sensor to determine a motion of a mobile device comprising the voice control device, to generate a detection output; and

referring to the recognized speech command and the detection output to decide a response of voice control;

wherein when the detection output indicates a first motion of the mobile device, the voice control has a first response for the recognized speech command; and

when the detection output indicates a second motion of the mobile device, the voice control has a second response for the same recognized speech command, where the second motion is different from the first motion, and the second response is different from the first response.

9. The voice control method of claim 8, wherein the step of performing the speech command recognition comprises:

determining the recognized speech command according to at least a predefined command set which is consistently used during the speech command recognition.

10. The voice control method of claim 8, wherein the sensor data is received from the at least one auxiliary sensor, including at least one of an accelerometer, an ambient temperature sensor, a gravity sensor, an ambient light sensor, and a Gyro sensor.

11. The voice control method of claim 8, wherein the step of processing the sensor data comprises:

performing motion detection according to the sensor data.

12. The voice control method of claim 11, further comprising:

performing an adaptive training process to obtain at least one motion model;

wherein the step of performing the motion detection comprises;

determining the detection output according to the sensor data and the at least one motion model.

13. The voice control method of claim 12, wherein the adaptive training process is an explicit training process performed before the voice control is in normal operation.

14. The voice control method of claim 12, wherein the adaptive training process is an implicit training process performed while the voice control is in normal operation.

15. A non-transitory machine readable medium storing a program code, wherein when the program code is executed by a processor, the program code instructs the processor to perform following steps:

performing speech command recognition to output a recognized speech command;

processing sensor data generated from at least one auxiliary sensor to determine a motion of a mobile device comprising the voice control device, to generate a detection output; and

referring to the recognized speech command and the detection output to decide a response of voice control;

wherein when the detection output indicates a first motion of the mobile device, the voice control has a first response for the recognized speech command; and

when the detection output indicates a second motion of the mobile device, the voice control has a second response for the same recognized speech command, where the second motion is different from the first motion, and the second response is different from the first response.