Automated equalization

• US 10,165,362 B2
• Filed: 12/24/2015
• Issued: 12/25/2018
• Est. Priority Date: 12/24/2015
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Maziewski, Przemyslaw, Borwanski, Michal
• Primary Examiner(s): Guerra-Erazo, Edgar X
• Application Number:
  US14/757,884
• Publication Number:
  US 20170188148A1
• Time in Patent Office: 1,097 Days
• Field of Search: 704226, 704271, 704205, 704206, 704270, 704220, 704276, 704275
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• 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 21/0316 by changing the amplitude
• CPC Class Codes: H04R 29/00 Monitoring arrangements; Testing arrangements for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308
• CPC Class Codes: H04R 3/04 for correcting frequency response

Abstract

Techniques for improving speech recognition are described. An example of an electronic device includes an extracting unit to extract a reference spectral profile from a reference signal and a device spectral profile from a device signal. A comparing unit compares the reference spectral profile and the device spectral profile. A delta calculating unit calculates a delta between the reference spectral profile and the device spectral profile. A design unit designs a correction filter based on the computed delta.

Claims

1. An electronic device for improving speech recognition of a device under test (DUT), comprising:

an extracting unit to extract a reference spectral profile from a reference signal and a DUT spectral profile from a DUT signal;

a comparing unit to compare the reference spectral profile and the DUT spectral profile;

a delta calculating unit to compute a delta between the reference spectral profile and the DUT spectral profile to obtain a computed delta;

a design unit to design a correction filter based on the computed delta; and

an application unit to apply the correction filter to a signal produced by a microphone internal to the DUT to improve speech recognition.

2. The electronic device of claim 1, comprising a first calculating unit to calculate the reference signal from a set of recordings.

3. The electronic device of claim 1, wherein the design unit designs the correction filter using a plurality of recordings, and wherein the plurality of recordings are obtained from one or more devices.

4. The electronic device of claim 1, comprising an orientation sensor to determine an orientation of the DUT and employ an appropriate correction filter.

5. The electronic device of claim 1, comprising a proximity sensor to determine a distance from a user to the DUT and employ the appropriate correction filter.

6. The electronic device of claim 1, comprising an angle sensor to determine an angle between the user and the DUT and employ the appropriate correction filter.

7. The electronic device of claim 1, comprising a lid position sensor to determine a position of a lid of the DUT and employ the appropriate correction filter.

8. The electronic device of claim 1, comprising one or more microphones to receive the DUT signal.

9. The electronic device of claim 8, comprising a recording unit to record the DUT signal.

10. A method, comprising:

extracting a reference spectral profile from a reference signal;

extracting a device-under-test (DUT) spectral profile from a DUT signal;

comparing the reference spectral profile and DUT spectral profile;

calculating a delta between the reference spectral profile and the DUT spectral profile;

designing a correction filter using the delta; and

applying the correction filter to a signal produced by a microphone internal to the DUT to improve speech recognition.

11. The method of claim 10, comprising using a set of speech recordings to calculate a reference signal.

12. The method of claim 11, comprising averaging of amplitude spectra of the reference signal to obtain the reference spectral profile.

13. The method of claim 10, comprising recording a speech utterance using the DUT to obtain a recorded speech utterance.

14. The method of claim 13, comprising:

broadcasting the recorded speech utterance using a speaker to obtain a broadcasted speech utterance; and

receiving the broadcasted speech utterance using a microphone internal to the DUT to obtain a DUT signal.

15. The method of claim 14, comprising averaging of amplitude spectra of the DUT signal to obtain the DUT spectral profile.

16. The method of claim 10, comprising calculating the correction filter using a frequency-sampling method or any other technique for designing an audio signal filter.

17. The method of claim 10, wherein applying the correction filter comprises determining at least one of an orientation of the DUT, a distance from a user to the DUT, an angle between the user and the DUT, and a position of a lid of the DUT.

18. At least one non-transitory computer-readable medium, comprising instructions to direct a processor to:

extract a reference spectral profile from a reference signal;

extract a device-under-test (DUT) spectral profile from a DUT signal;

compare the reference spectral profile and the DUT spectral profile;

calculate a delta between the reference spectral profile and the DUT spectral profile;

design a correction filter using the delta; and

apply the correction filter to a signal produced by a microphone internal to the DUT to improve speech recognition.

19. At least one non-transitory computer-readable medium of claim 18, comprising instructions to direct the processor to calculate the reference signal from a set of speech recordings.

20. At least one non-transitory computer-readable medium of claim 19, comprising instructions to direct the processor to average amplitude spectra of the reference signal to obtain the reference spectral profile.

21. At least one non-transitory computer-readable medium of claim 18, comprising instructions to direct the processor to receive a speech utterance via the microphone to obtain the DUT signal.

22. At least one non-transitory computer-readable medium of claim 21, comprising instructions to direct the processor to average amplitude spectra of the DUT signal to obtain the DUT spectral profile.