Vibration sensor and acoustic voice activity detection system (VADS) for use with electronic systems
View Patent ↗A voice activity detector (VAD) combines the use of an acoustic VAD and a vibration sensor VAD as appropriate to the conditions a host device is operated. The VAD includes a first detector receiving a first signal and a second detector receiving a second signal. The VAD includes a first VAD component coupled to the first and second detectors. The first VAD component determines that the first signal corresponds to voiced speech when energy resulting from at least one operation on the first signal exceeds a first threshold. The VAD includes a second VAD component coupled to the second detector. The second VAD component determines that the second signal corresponds to voiced speech when a ratio of a second parameter corresponding to the second signal and a first parameter corresponding to the first signal exceeds a second threshold.
1. A method comprising:
receiving a first signal at a first detector and a second signal at a second detector;
determining when the first signal corresponds to voiced speech;
determining when the second signal corresponds to voiced speech;
determining a state of contact of the first detector with skin of a user;
generating a voice activity detection (VAD) signal to indicate a presence of voiced speech when the state of contact is a first state and the first signal corresponds to voiced speech;
generating the VAD signal when the state of contact is a second state and either of the first signal and the second signal correspond to voiced speech.
2. The method of claim 1 , wherein the first detector is a vibration sensor.
3. The method of claim 2 , wherein the first detector is a skin surface microphone (SSM).
4. The method of claim 1 , wherein the second detector is an acoustic sensor.
5. The method of claim 4 , wherein the second detector comprises two omnidirectional microphones.
6. The method of claim 1 , comprising time-aligning the first signal and the second signal.
7. The method of claim 1 , wherein determining the state of contact comprises detecting the first state when the first signal corresponds to voiced speech at a same time as the second signal corresponds to voiced speech.
8. The method of claim 1 , wherein determining the state of contact comprises detecting the second state when the first signal corresponds to unvoiced speech at a same time as the second signal corresponds to voiced speech.
9. The method of claim 1 , wherein the first parameter is a first counter value that corresponds to a number of instances in which the first signal corresponds to voiced speech.
10. The method of claim 9 , wherein the second parameter is a second counter value that corresponds to a number of instances in which the second signal corresponds to voiced speech.
11. The method of claim 1 , comprising forming the second detector to include a first virtual microphone and a second virtual microphone.
12. The method of claim 11 , comprising forming the first virtual microphone by combining signals output from a first physical microphone and a second physical microphone.
13. The method of claim 12 , comprising forming a filter that describes a relationship for speech between the first physical microphone and the second physical microphone.
14. The method of claim 13 , comprising forming the second virtual microphone by applying the filter to a signal output from the first physical microphone to generate a first intermediate signal, and summing the first intermediate signal and the second signal.
15. The method of claim 14 , comprising generating an energy ratio of signal energies of the first virtual microphone and the second virtual microphone.
16. The method of claim 15 , comprising determining the second signal corresponds to voiced speech when the energy ratio is greater than the second threshold.
17. The method of claim 11 , wherein the first virtual microphone and the second virtual microphone are distinct virtual directional microphones.
18. The method of claim 17 , wherein the first virtual microphone and the second virtual microphone have similar responses to noise.
19. The method of claim 18 , wherein the first virtual microphone and the second virtual microphone have dissimilar responses to speech.
20. The method of claim 17 , comprising calibrating at least one of the first signal and the second signal.
21. The method of claim 20 , the calibrating comprising compensating a second response of the second physical microphone so that the second response is equivalent to a first response of the first physical microphone.
22. The method of claim 1 , wherein the first state is good contact with the skin.
23. The method of claim 1 , wherein the second state is poor contact with the skin.
24. The method of claim 1 , wherein the second state is indeterminate contact with the skin.
25. A system comprising:
a first detector that receives a first signal and a second detector that receives a second signal;
a first voice activity detector (VAD) component coupled to the first detector and the second detector and determining when the first signal corresponds to voiced speech;
a second VAD component coupled to the second detector and determining when the second signal corresponds to voiced speech;
a contact detector that detects contact of the first detector with skin of a user; and
a selector coupled to the first VAD component and the second VAD component and generating a voice activity detection (VAD) signal when the first signal corresponds to voiced speech and the first detector detects contact with the skin, and generating the VAD signal when either of the first signal and the second signal correspond to voiced speech.
26. The system of claim 25 , wherein the first detector is a vibration sensor.
27. The system of claim 26 , wherein the first detector is a skin surface microphone (SSM).
28. The system of claim 25 , wherein the second detector is an acoustic sensor.
29. The system of claim 28 , wherein the second detector comprises two omnidirectional microphones.
30. The system of claim 25 , wherein the contact detector determines the state of contact by detecting the first state when the first signal corresponds to voiced speech at a same time as the second signal corresponds to voiced speech.
31. The system of claim 25 , wherein the contact detector determines the state of contact by detecting the second state when the first signal corresponds to unvoiced speech at a same time as the second signal corresponds to voiced speech.
32. The system of claim 25 , comprising a first counter coupled to the first VAD component, wherein the first parameter is a counter value of the first counter, the counter value of the first counter corresponding to a number of instances in which the first signal corresponds to voiced speech.
33. The system of claim 32 , comprising a second counter coupled to the second VAD component, wherein the second parameter is a counter value of the second counter, the counter value of the second counter corresponding to a number of instances in which the second signal corresponds to voiced speech.
34. The system of claim 25 , wherein the second detector includes a first virtual microphone and a second virtual microphone.
35. The system of claim 34 , comprising forming the first virtual microphone by combining signals output from a first physical microphone and a second physical microphone.
36. The system of claim 35 , comprising a filter that describes a relationship for speech between the first physical microphone and the second physical microphone.
37. The system of claim 36 , comprising forming the second virtual microphone by applying the filter to a signal output from the first physical microphone to generate a first intermediate signal, and summing the first intermediate signal and the second signal.
38. The system of claim 37 , comprising generating an energy ratio of signal energies of the first virtual microphone and the second virtual microphone.
39. The system of claim 38 , comprising determining the second signal corresponds to voiced speech when the energy ratio is greater than the second threshold.
40. The system of claim 34 , wherein the first virtual microphone and the second virtual microphone are distinct virtual directional microphones.
41. The system of claim 40 , wherein the first virtual microphone and the second virtual microphone have similar responses to noise.
42. The system of claim 41 , wherein the first virtual microphone and the second virtual microphone have dissimilar responses to speech.
43. The system of claim 40 , comprising calibrating at least one of the first signal and the second signal.
44. The system of claim 43 , wherein the calibration compensates a second response of the second physical microphone so that the second response is equivalent to a first response of the first physical microphone.
45. The system of claim 25 , wherein the first state is good contact with the skin.
46. The system of claim 25 , wherein the second state is poor contact with the skin.
47. The system of claim 25 , wherein the second state is indeterminate contact with the skin.