Apparatus and method for detecting voice based on motion information

• US 9,443,536 B2
• Filed: 04/29/2010
• Issued: 09/13/2016
• Est. Priority Date: 04/30/2009
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Cho, Jeong-Mi, Kim, Jeong-Su, Bang, Won-Chul, Kim, Nam-Hoon
• Primary Examiner(s): Bengzon, Greg C
• Application Number:
  US12/770,086
• Publication Number:
  US 20100277579A1
• Time in Patent Office: 2,329 Days
• Field of Search: None
• US Class Current: 1/1
• 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 3/0346 with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• 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

Disclosed are an apparatus and method of deducing a user'"'"'s intention using motion information. The user'"'"'s intention deduction apparatus includes a speech intention determining unit configured to predict a speech intention regarding a user'"'"'s speech using motion information sensed by at least one motion capture sensor, and a controller configured to control operation of detecting a voice section from a received sound signal based on the predicted speech intention.

Claims

1. A voice detection apparatus, comprising:

a speech intention determining processor configured to;

calculate a distance between a mouth of a user and a hand of the user holding a microphone based on motion information sensed by motion capture sensors placed on a head of the user and a wrist of the user,

calculate a direction of the microphone based on a rotation angle sensed by the motion capture sensor placed on the wrist, and

predict a speech intention regarding a speech of the user based on the distance and the direction; and

a controller configured to control operation of detecting a voice section from a received sound signal based on the predicted speech intention.

2. The voice detection apparatus of claim 1, wherein the speech intention determining processor is further configured to determine whether the speech intention is to speak or to terminate speech based on the motion information.

3. The voice detection apparatus of claim 2, wherein the speech intention determining processor is further configured to receive, from the controller, information indicating whether voice is being input, to verify the predicted speech intention.

4. The voice detection apparatus of claim 3, wherein:

in response to the predicted speech intention being to speak and no voice being input, the speech intention determining processor is further configured to determine that a secondarily predicted speech intention is to speak;

in response to the predicted speech intention being to terminate speech and voice being input, the speech intention determining processor is further configured to determine that a secondarily predicted speech intention is to terminate speech; and

otherwise, the speech intention determining processor is further configured to decide the secondarily predicted speech intention as being not associated with voice input.

5. The voice detection apparatus of claim 2, wherein, in response to the predicted speech intention being to speak, the controller is further configured to:

activate a sound sensor;

analyze the sound signal received from the activated sound sensor;

detect the voice section from the sound signal; and

recognize a voice of the voice section.

6. The voice detection apparatus of claim 2, wherein, in response to the predicted speech intention being to terminate speech, the controller is further configured to:

analyze the sound signal already received from an activated sound sensor; and

determine whether the voice section is detected from the sound signal.

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

a multimodal sensor configured to sense sensed information changed when a person speaks,

wherein the controller is further configured to detect the voice section from the received sound signal based on the sensed information sensed by the multimodal sensor.

8. The voice detection apparatus of claim 7, wherein the sensed information comprises image information, or temperature information, or vibration information, or any combination thereof.

17. The voice detection apparatus of claim 5, wherein the controller is further configured to deactivate the sound sensor in response to no voice section being detected.

18. The voice detection apparatus of claim 7, wherein the sensed information comprises temperature information.

19. The voice detection apparatus of claim 7, wherein the sensed information comprises information of an infrared ray irradiated from a face of the user, or the mouth of the user, when speaking.

9. A voice detection method, comprising:

calculating, by a processor, a distance between a mouth of a user and a hand of the user holding a microphone based on motion information sensed by motion capture sensors placed on a head of the user and a wrist of the user;

calculating a direction of the microphone based on a rotation angle sensed by the motion capture sensor placed on the wrist;

predicting a speech intention regarding a speech of the user based on the distance and the direction; and

controlling operation of detecting a voice section based on the predicted speech intention.

10. The voice detection method of claim 9, wherein the predicting of the speech intention comprises determining whether the predicted speech intention is to speak or an intention to terminate speech based on the sensed motion information.

11. The voice detection method of claim 10, wherein the predicting of the speech intention comprises receiving information on whether voice is being input, to verify the predicted speech intention.

12. The voice detection method of claim 11, wherein the predicting of the speech intention comprises:

in response to the predicted speech intention being to speak and no voice being input, determining that a secondarily predicted speech intention is to speak;

in response to the predicted speech intention being to terminate speech and voice being input, determining that the secondarily predicted speech intention is to terminate speech; and

otherwise, deciding the secondarily predicted speech intention as being not associated with voice input.

13. The voice detection method of claim 10, further comprising, in response to the predicted speech intention being to speak:

detecting the voice section from a received sound signal;

recognizing a voice of the voice section; and

executing an application module based on the voice.

14. The voice detection method of claim 10, further comprising, in response to the predicted speech intention being to terminate speech:

analyzing a sound signal already received from an activated sound sensor; and

determining whether the voice section is detected from the sound signal.

15. The voice detection method of claim 9, further comprising:

detecting the voice section based on sound characteristic information extracted from a received sound signal, and sensed information changed when a person speaks.

16. The voice detection method of claim 15, wherein the sensed information comprises image information, or temperature information, or vibration information, or any combination thereof.