SYSTEM AND METHOD FOR IMPROVING SPEECH RECOGNITION ACCURACY IN A WORK ENVIRONMENT

• US 20140278387A1
• Filed: 03/14/2013
• Published: 09/18/2014
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Vocollect, Inc. (Honeywell International Inc.)
• Original Assignee: Vocollect, Inc. (Honeywell International Inc.)
• Inventors: DiGregorio, David R.
• Granted Patent: US 9,236,050 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• 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 25/48 specially adapted for particular use
• CPC Class Codes: H04R 2201/107 Monophonic and stereophonic headphones with microphone for two-way hands free communication
• CPC Class Codes: H04R 5/033 Headphones for stereophonic communication details thereof, e.g. relating to batteries, cables or control elements H04R1/10

Abstract

Apparatus and method that improves speech recognition accuracy, by monitoring the position of a user'"'"'s headset-mounted speech microphone, and prompting the user to reconfigure the speech microphone'"'"'s orientation if required. A microprocessor or other application specific integrated circuit provides a mechanism for comparing the relative transit times between a user'"'"'s voice, a primary speech microphone, and a secondary compliance microphone. The difference in transit times may be used to determine if the speech microphone is placed in an appropriate proximity to the user'"'"'s mouth. If required, the user is automatically prompted to reposition the speech microphone.

Claims

1. A system for improving a speech recognition process, said system comprising:

a speech microphone configured to capture speech audio from a user and output corresponding electrical signals;

at least one additional microphone, spaced away from the speech microphone and configured to capture speech audio from the user and output corresponding electrical signals;

processing circuitry coupled to receive signals from the microphones that are associated with the captured speech audio, the processing circuitry configured to process the signals associated with the captured speech audio and to determine if the speech microphone is in a desired positioned with respect to a user'"'"'s mouth, the processing circuitry further configured to provide an audio prompt if the speech microphone is not in a desired position; and

a speaker configured to play the audio prompt for a user to advise them to move the speech microphone to a different position.

2. The system of claim 1 wherein the audio prompt advises the user to move the speech microphone closer to the mouth of the user.

3. The system of claim 1, wherein the speech microphone is coupled to at least one of a flexible boom or movable earpiece assembly to allow the user to position said microphone in a plurality of positions with respect to the user'"'"'s mouth.

4. The system of claim 1, where the at least one additional microphone is physically coupled at a fixed location with respect the speech microphone.

5. The system of claim 1 further comprising a headset assembly coupling the speech microphone and compliance microphone, the at least one additional microphone being fixed on the headset assembly.

6. The system of claim 1, where the processing circuitry is further configured to use the signals associated with the captured speech audio from the speech microphone and at least one additional microphone and calculate the difference in transit time for the speech audio to travel from the user'"'"'s mouth to the speech microphone and to travel from the user'"'"'s mouth to the at least one additional microphone.

7. The system of claim 6 wherein the calculated difference is determined as a phase differential Δ

_actual.

8. The system of claim 7, where the processing circuitry is configured to compare the phase differential Δ

_actual to a phase differential threshold Δ

_acceptable to determine if the speech microphone is positioned in a desired position with respect to a user'"'"'s mouth.

9. The system of claim 8 wherein the phase differential threshold Δ

_acceptable is related to a speech recognition parameter.

10. The system of claim 8, wherein a phase differential threshold Δ

_acceptable is selectable.

11. The system of claim 1, wherein the processing circuitry is configured to perform speech recognition on the received signals from the speech microphone that are associated with the captured speech audio.

12. The system of claim 1 further comprising a portable computer terminal, the processing circuitry being contained in the portable computer terminal.

13. The system of claim 1 further comprising a headset assembly containing the speech microphone, at least one additional microphone and speaker, the processing circuitry being contained in the headset assembly.

14. A method for improving a speech recognition process, said method comprising:

capturing speech audio from a user with a speech microphone and at least one additional microphone and outputting corresponding electrical signals, the at least one additional microphone spaced away from the speech microphone;

processing signals associated with the captured speech audio and determining if the speech microphone is in a desired positioned with respect to a user'"'"'s mouth; and

if the speech microphone is not in a desired position, providing an audio prompt to a user to advise them to move the speech microphone to a different position.

15. The method of claim 14 further comprising positioning the at least one additional microphone at a fixed location with respect to the speech microphone.

16. The method of claim 14 further comprising advising the user to move the speech microphone closer to the mouth of the user.

17. The method of claim 14 further comprising using the signals associated with the captured speech audio from the speech microphone and at least one additional microphone and calculating the difference in transit time for the speech audio to travel from the user'"'"'s mouth to the speech microphone and to travel from the user'"'"'s mouth to the at least one additional microphone.

18. The method of claim 17 further comprising determining the calculated difference as a phase differential Δ

_actual and comparing the phase differential Δ

_actual to a phase differential threshold Δ

_acceptable to determine if the speech microphone is properly positioned with respect to a user'"'"'s mouth.

19. The method of claim 17 wherein the phase differential threshold Δ

_acceptable is related to a speech recognition parameter.

20. The method of claim 14 further comprising performing speech recognition on the received signals from the speech microphone that are associated with the captured speech audio.