Method and Apparatus for Determining a Motion Environment Profile to Adapt Voice Recognition Processing

• US 20140278395A1
• Filed: 07/31/2013
• Published: 09/18/2014
• Est. Priority Date: 03/12/2013
• Status: Abandoned Application

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Motorola Mobility LLC (Lenovo Group Ltd.)
• Inventors: Zurek, Robert A., Bastyr, Kevin J., Davis, Giles T., Ivanov, Plamen A., Schuster, Adrian M.
• Application Number:
  US13/956,131
• Publication Number:
  US 20140278395A1
• Time in Patent Office: Days
• US Class Current: 704/233
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: G10L 21/003 Changing voice quality, e.g. pitch or formants
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 21/0316 by changing the amplitude
• CPC Class Codes: G10L 21/04 Time compression or expansion

Abstract

A method and apparatus for determining a motion environment profile to adapt voice recognition processing includes a device receiving an acoustic signal including a speech signal, which is provided to a voice recognition module. The method also includes determining a motion profile for the device, determining a temperature profile for the device, and determining a noise profile for the acoustic signal. The method further includes determining, from the motion, temperature, and noise profiles, a motion environment profile for the device and adapting voice recognition processing for the speech signal based on the motion environment profile.

Claims

1. A method performed by a device for adapting voice recognition processing, the method comprising:

receiving into the device an acoustic signal comprising a speech signal, which is provided to a voice recognition module;

determining a motion profile for the device;

determining a temperature profile for the device;

determining a noise profile for the acoustic signal;

determining, from the motion, temperature, and noise profiles, a motion environment profile for the device; and

adapting voice recognition processing for the speech signal based on the motion environment profile.

2. The method of claim 1, wherein adapting voice recognition processing for the speech signal comprises modifying the speech signal before providing the speech signal to a voice recognition engine within the voice recognition module.

3. The method of claim 2, wherein determining the motion profile comprises determining a time-averaged velocity for the device based on a set of time-dependent velocity components for the device, and wherein modifying the speech signal comprises modifying at least one of an amplitude or frequency of the speech signal based on at least one of the time-averaged velocity or the time-dependent velocity components.

4. The method of claim 2, wherein determining the noise profile comprises determining at least one of noise level or noise type, and wherein modifying the speech signal comprises modifying at least one phoneme within the speech signal based on at least one of the noise level or the noise type.

7. The method of claim 1, wherein adapting voice recognition processing for the speech signal comprises adapting the voice recognition module, which comprises at least one of:

selecting a voice recognition database based on the motion environment profile;

or

selecting a voice recognition engine based on the motion environment profile.

8. The method of claim 1, wherein determining the temperature profile comprises:

determining a first temperature reading using a temperature sensor internal to the device;

receiving a second location-based temperature reading from a second device external to the device;

determining a temperature difference between the first and second temperature readings; and

determining a temperature indication of whether the device is indoors or outdoors based on the temperature difference, wherein the motion environment profile is determined based on the temperature indication.

9. The method of claim 1, wherein determining the motion profile comprises determining a time-averaged velocity for the device and determining a transportation mode based on the time-averaged velocity.

10. The method of claim 9, wherein determining the motion profile further comprises determining time-dependent velocity components for the device that differ from the time-averaged velocity, and wherein determining the transportation mode is further based on the time-dependent velocity components.

11. The method of claim 1, wherein:

determining the motion profile comprises determining a device speed;

determining the noise profile comprises;

detecting wind noise;

analyzing the wind noise to determine a wind speed; and

setting a noise indication based on a calculated difference between the wind speed and the device speed.

12. The method of claim 11, wherein the noise indication is set to indicate that the device is indoors or outdoors based on an absolute value of the difference between the wind speed and the device speed, wherein:

when the absolute value of the difference between the wind speed and the device speed is greater than a threshold speed, the method further comprising selecting, based on the indoors noise indication, multiple microphones to receive the acoustic signal; and

when the absolute value of the difference between the wind speed and the device speed is less than the threshold speed, the method further comprising selecting, based on the outdoors noise indication, a single microphone to receive the acoustic signal.

13. The method of claim 1, wherein determining a noise profile for the acoustic signal comprises determining that noise in the acoustic signal is stationary or non-stationary, and wherein adapting voice recognition processing comprising adjusting a trigger threshold to make a trigger for voice recognition less discriminating when the noise is determined to be stationary relative to when the noise is determined to be non-stationary.

14. The method of claim 1, wherein determining a noise profile for the acoustic signal comprises determining that noise in the acoustic signal is stationary or non-stationary, and the method further comprising performing noise reduction on the acoustic signal, wherein the noise reduction comprises road noise reduction when the noise is determined to be stationary and wind noise reduction when the noise is determined to be non-stationary.

15. The method of claim 1, wherein determining a motion profile for the device comprises determining a transportation mode for the device, and wherein the transportation mode is determined based on a type of application being run on the device.

16. The method of claim 1, wherein determining a motion profile comprises determining a transportation mode, and wherein adapting voice recognition processing comprises removing at least a portion of percussive noise, resulting from the transportation mode, from the acoustic signal, wherein the percussive noise results from footfalls when the transportation mode comprises traveling by foot or the percussive noise results from road irregularities when the transportation mode comprises traveling by motor vehicle.

5. The method of 2, wherein determining the noise profile comprises detecting at least one of user stress or noise level, and wherein modifying the speech signal comprises modifying at least one of rate of speech, pitch, or frequency of the speech signal based on at least one of the user stress or the noise level.

6. The method of claim 5, wherein modifying the speech signal further comprises phoneme correction based on adaptive training of the device to the user stress or the noise level.

17. A device configured to perform voice recognition, the device comprising:

at least one acoustic transducer configured to receive an acoustic signal comprising a speech signal;

a voice-recognition module configured to perform voice recognition on the speech signal;

a set of motion sensors configured to collect motion data;

a temperature sensor configured to measure a first temperature at the device;

an interface configured to receive a second temperature for the location of the device; and

a processing element configured to determine, from the acoustic signal, the motion data, and the first and second temperatures, a motion environment profile for the device and to adapt voice recognition processing for the speech signal based on the motion environment profile.

18. The device of claim 17, wherein the set of motion sensors comprises at least one of:

an accelerometer;

a velocity sensor;

an air flow sensor;

a global positioning system receiver;

or

network triangulation hardware.

19. The device of claim 17 further comprising a signal processing module configured to adapt voice recognition processing by modifying at least one of a frequency of speech, an amplitude of speech, or a rate of speech for the speech signal.

20. The device of claim 17 further comprising a first and a second voice recognition engine, wherein adapting voice recognition processing comprises selecting the second voice recognition engine, based on the motion environment profile, to replace the first voice recognition engine as an active voice recognition engine.