Voice detection and discrimination apparatus and method

• US 20030165246A1
• Filed: 03/01/2002
• Published: 09/04/2003
• Est. Priority Date: 02/28/2002
• Status: Active Grant

• Current Assignee: Honeywell Hearing Technologies AS (Honeywell International Inc.)
• Original Assignee: SINTEF
• Inventors: Pettersen, Odd, Kr O., Sorsdal, Svein, Kvaloy, Olav, Svean, Jarle, Ottesen, Georg E., Stensby, Sverre, Henriksen, Viggo
• Granted Patent: US 6,728,385 B2
• Time in Patent Office: Days
• US Class Current: 381/312
• CPC Class Codes: A61F 11/145 electric, e.g. for active noise reduction
• 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
• CPC Class Codes: H04R 1/1016 Earpieces of the intra-aural type
• CPC Class Codes: H04R 1/1083 Reduction of ambient noise active noise reduction per se G10K11/175; protective devices for the ear, e.g. providing acoustic protection A61F11/06
• CPC Class Codes: H04R 2420/07 Applications of wireless loudspeakers or wireless microphones
• CPC Class Codes: H04R 2460/05 Electronic compensation of the occlusion effect

Abstract

An apparatus and a method of voice detection and discrimination apparatus for controlling a voice operated system. A protective ear terminal element (1,2) in the apparatus protects the ear by providing acoustic attenuation. An inner electroacoustic transducer element (M2) on an inner side of the ear terminal element (1,2) detects a first acoustic field and provides a first electronic signal representing the first acoustic field. An outer electroacoustic transducer element (M1) on an outer side of the ear terminal element (1,2) detects a second acoustic field and provides a second electronic signal representing said second acoustic field. An electronics unit (11,E3) is connected with said electroacoustic transducer elements (M1,M2) and comprises first comparison means (27) for comparison of said first and second electronic signals to obtain the difference between said two electronic signals. The electronics unit (11,E3) also comprises a second comparison means (28) for comparing said difference with given criteria. Output means (13,E12) connected to the electronics unit (11,E3) provides an output signal depending on said second comparison. The output signal is an input signal to the voice operated system (29).

Claims

1. Voice detection and discrimination apparatus for controlling a voice operated system comprising

a protective ear terminal element (1,2) for protecting the ear by providing acoustic attenuation,

an inner electroacoustic transducer element (M2) on an inner side of the ear terminal element (1,2) for detecting a first acoustic field and providing a first electronic signal representing said first acoustic field,

an outer electroacoustic transducer element (M1) on an outer side of the ear terminal element (1,2) for detecting a second acoustic field and providing a second electronic signal representing said second acoustic field,

an electronics unit (11,E3) connected with said electroacoustic transducer elements (M1,M2) and comprising first comparison means (27) for comparison of said first and second electronic signals to obtain the difference between said two electronic signals, and second comparison means (28) for comparing said difference with given criteria, and output means (13,E12) connected to said electronics unit for providing an output signal depending on said second comparison, said output signal is an input signal to the voice operated system (29).

2. Apparatus according to claim 1 wherein the output signal comprises instructions, commands, code or the like for said voice operated system, such as a communication system.

3. Apparatus according to claim 1 wherein the criteria are predetermined and stored in storage means (E8,E9,E10) in the apparatus.

4. Apparatus according to claim 1 comprising processing means (E3) for adapting the criteria during use of the apparatus.

5. Apparatus according to claim 1 wherein the criteria comprises a predetermined difference in acoustic signal strength as detected by the two electroacoustic transducer elements (M1,M2) in a noisy environment, typically in the range −

20 to −

40 dB, and a predetermined allowable decrease of the said difference in acoustic signal strength, typically in the range of 2 to 10 dB.

6. Apparatus according to claim 1 comprising a first electronic filter (22) for filtering the electronic signal from the inner electroacoustic transducer element (M2).

7. Apparatus according to claim 1 comprising a second electronic filter (25) for filtering the electronic signal from the outer electroacoustic transducer element (M1).

8. Apparatus according to claim 6 or 7 comprising electronic bandpass filters (22,25), typically with a passband in the range 150-700 Hz.

9. Apparatus according to claim 8 comprising a signal strength detector (23,26) connected with said bandpass filters (22,25) for providing inputs for a signal strength comparison block (27).

10. Apparatus according to claim 9 comprising a decision block (28) connected with said signal strength comparison block (27) for providing said output signal to said voice operated system (29).

11. Apparatus according to claim 1

wherein at least a part of the electronics unit (11,E3) and the output means (13) is contained in a unit being separate from, but connected to said ear terminal (1,2).

12. Apparatus according to claim 1

wherein said ear terminal element (1,2) Comprises an ear plug section (1) and a sealing section (2) forming a hearing protector (1,2) for placement in an ear and for protection of the hearing function.

13. Apparatus according to claim 1

wherein the signal strength comparison means (27) comprises means for estimating the acoustic attenuation of the ear terminal element (1,2) for establishing said predetermined difference.

14. Apparatus according to claim 13 comprising a minimum tracker (60) connected with the detectors (23,26) for obtaining running estimates of the said acoustic attenuation.

15. Apparatus according to claim 1,

wherein the electronics unit (11,E3) comprises signal analysis means (E3) for extracting a voice signal from the inner electroacoustic transducer element (M2), for transmission to the voice operated system.

16. Apparatus according to claim 15,

comprising signal analysis means (E3) for detecting the presence of particular speech components, such as words, in the signal from the inner electroacoustic transducer element (M2), for forming commands, instructions or code for the voice operated system (29).

17. Apparatus according to claim 1

wherein the electroacoustic transducer element(s) (M1,M2) is(are) microphones.

18. Method of detecting a voice and for controlling a voice operated system, employing an ear terminal element (1,2) for protecting the ear by providing acoustic attenuation comprising the following steps;

detecting (M2) the acoustic signal strength on the inner side of said ear terminal element,

detecting (M1) the acoustic signal strength on the outer side of said ear terminal element,

obtaining (23,26,27) a difference value representing the difference in the acoustic signal strength between the inner and outer side of said ear terminal element,

deciding (28) if a voice is present using said value representing said difference and given criteria (28),

providing an output signal depending on said decision using output means (13,E12), the output signal being an input to the voice operated system (29).

19. Method according to claim 18 comprising

providing an output signal (13) in the form of a control signal, commands, instructions, code or the like for said voice operated system (29), such as a communication system.

20. Method according to claim 18 comprising

writing and reading predetermined criteria to and from storage means (E8,E9,E10) in the ear terminal element (1,2).

21. Method according to claim 18 comprising

determining if said difference in the acoustic signal strength (27) between the inner and outer side of said ear terminal element (1,2) has decreased more than a given amount, typically 2-10 dB, from a predetermined amount, typically −

20 to −

40 dB.

22. Method according to claim 18 comprising

filtering (22,25) the signals from the two electroacoustic transducer elements (M2,M1) using bandpass filters (22,25).

23. Method according to claim 18 comprising;

analysing (E3) the voice signal for determining its characteristics, such as duration, frequency, and amplitude,

providing said output signal (13) depending on the said determined voice characteristics.

24. Method according to claim 23 comprising;

obtaining a value representing the running average of the difference in the acoustic signal level between the inner and outer side of the ear terminal element (1,2).

25. Method according to claim 18 comprising

adjusting the said criteria according to the running average of the said difference.

26. Method according to claim 18 comprising

extracting information from the acoustic signals being detected by the electroacoustic transducer elements (M1,M2).

27. Method according to claim 26 comprising

analyzing the signal from the electroacoustic transducer elements (M1, M2) for the presence of particular speech components, such as words.

28. Method according to claim 18 comprising

prior to normal use, performing a calibration operation where an estimate of the attenuation of the hearing protector is obtained by determining the difference in the the sound levels as detected by the two electroacoustic transducer elements in a period where no voice but only noise is present.

29. Method according to claim 18 comprising

during normal operation, performing a verification operation where an estimate of the attenuation of the hearing protector is obtained by determining the difference in the the sound levels as detected by the two electroacoustic transducer elements in a period where no voice but only noise is present, and the obtained attenuation is compared with a predetermined stored attenuation value.