Systems and methods for detecting degradation of a microphone included in an auditory prosthesis system

Patent metadata

Field	Value
Publication number	US-9775998-B2
Application number	US-201314907272-A
Country	US
Kind code	B2
Filing date	Jul 23, 2013
Priority date	Jul 23, 2013
Publication date	Oct 3, 2017
Grant date	Oct 3, 2017

Abstract

An exemplary system includes a sound processor associated with a patient and a microphone ( 102 ). The microphone is configured to detect an audio signal presented to the patient and output an output signal ( 302 ) representative of the audio signal. The sound processor is configured to 1) receive the output signal, 2) identify at least one temporal portion of the output signal that has a classification attribute associated with a reference signal, 3) determine ( 304 ) a signal characteristic value ( 306 ) associated with the at least one temporal portion, 4) determine ( 308 ) that a difference ( 312 ) between the signal characteristic value associated with the at least one temporal portion and a reference signal characteristic value ( 310 ) associated with the reference signal meets a threshold condition, the meeting of the threshold condition indicating that a quality level of the microphone is below an acceptable level and 5) perform a predetermined action associated with the quality level of the microphone.

First claim

What is claimed is:

1. A system for detecting microphone degradation in an auditory prosthesis system, the system comprising:
a sound processor associated with a patient and configured to maintain data representative of a reference signal characteristic value and a classification attribute both associated with a reference signal; and
a microphone communicatively coupled to the sound processor and configured to detect an audio signal presented to the patient and output an output signal representative of the audio signal;
wherein the sound processor is further configured to
receive the output signal for a predetermined amount of time that is greater than one day,
identify at least one temporal portion of the output signal that has the classification attribute,
determine a signal characteristic value associated with the at least one temporal portion,
determine that a difference between the signal characteristic value associated with the at least one temporal portion and the reference signal characteristic value associated with the reference signal meets a threshold condition for the predetermined amount of time that is greater than one day, the meeting of the threshold condition for the predetermined amount of time that is greater than one day indicating that a quality level of the microphone is below an acceptable level, and
perform, in response to the determination that the difference between the signal characteristic value associated with the at least one temporal portion and the reference signal characteristic value associated with the reference signal meets the threshold condition for the predetermined amount of time that is greater than one day, a predetermined action associated with the quality level of the microphone.

2. The system of claim 1 , wherein the classification attribute identifies the at least one temporal portion as including speech.

3. The system of claim 1 , wherein the sound processor is configured to identify the at least one temporal portion of the output signal that has the classification attribute by identifying at least one characteristic of the output signal that corresponds to the classification attribute.

4. The system of claim 3 , wherein:
the classification attribute is associated with speech; and
the at least one characteristic includes at least one of a modulation frequency, an onset flank, an offset flank, an occurrence of a voiced segment, and an occurrence of an unvoiced segment.

5. The system of claim 1 , wherein the sound processor is configured to:
identify the at least one temporal portion of the output signal that has the classification attribute by identifying a plurality of temporal portions of the output signal that have the classification attribute; and
determine the signal characteristic value by
determining a plurality of signal characteristic values associated with the plurality of temporal portions, and
averaging the plurality of signal characteristic values to obtain an averaged signal characteristic value.

6. The system of claim 1 , wherein the signal characteristic value comprises a spectral energy of the at least one temporal portion and the reference signal characteristic value comprises a spectral energy of the reference signal.

7. The system of claim 1 , wherein the signal characteristic value comprises a spectral shape value of the at least one temporal portion and the reference signal characteristic value comprises a spectral shape value of the reference signal.

8. The system of claim 7 , wherein the sound processor is configured to determine the spectral shape value of the at least one temporal portion by measuring at least one of a spectral gravity value of the at least one temporal portion, a kurtosis value of the at least one temporal portion, and a skewness value of the at least one temporal portion.

9. The system of claim 1 , wherein the signal characteristic value comprises a sound pressure level of the at least one temporal portion and the reference signal characteristic value comprises a sound pressure level of the reference signal.

10. The system of claim 1 , wherein the sound processor is configured to:
maintain data representative of the classification attribute by maintaining a plurality of classification attributes including the classification attribute as one of the plurality of classification attributes; and
identify the at least one temporal portion of the output signal that has the classification attribute by classifying the at least one temporal portion as corresponding to the classification attribute from among the plurality of classification attributes.

11. The system of claim 10 , wherein the plurality of classification attributes each correspond to one of speech in quiet, speech with noise, and music.

12. The system of claim 10 , wherein the sound processor is configured to:
maintain data representative of the reference signal characteristic value by maintaining a plurality of class-specific reference signal characteristic values each corresponding to one of the plurality of classification attributes, the plurality of class-specific reference signal characteristic values including the reference signal characteristic value; and
determine that the difference between the signal characteristic value associated with the at least one temporal portion and the reference signal characteristic value associated with the reference signal meets the threshold condition by:
selecting the reference signal characteristic value from among the plurality of class-specific reference signal characteristic values based on the classifying of the temporal portion as corresponding to the classification attribute, and
determining that a difference between the selected reference signal characteristic value and the signal characteristic value meets the threshold condition.

13. The system of claim 1 , wherein the sound processor is configured to perform the predetermined action associated with the quality level of the microphone by adjusting one or more control parameters that govern an operation of at least one of the sound processor and a cochlear implant implanted within the patient.

14. The system of claim 1 , wherein the sound processor is configured to perform the predetermined action associated with the quality level of the microphone by providing a notification that the quality level of the microphone is below the acceptable level.

15. The system of claim 14 , wherein the sound processor is configured to provide the notification by activating at least one of:
a light-emitting device communicatively coupled to the sound processor.
a speaker communicatively coupled to the sound processor; and
a diagnostic interface communicatively coupled to the sound processor.

16. A system for detecting microphone degradation in an auditory prosthesis system, the method comprising:
a storage facility configured to maintain data representative of a reference signal characteristic value and a classification attribute associated with a reference signal; and
a processing facility communicatively coupled to the storage facility and configured to
receive, for a predetermined amount of time that is greater than one day, an output signal representative of an audio signal as detected by a microphone,
identify at least one temporal portion of the output signal that has the classification attribute,
determine a signal characteristic value associated with the at least one temporal portion,
determine that a difference between the signal characteristic value associated with the at least one temporal portion and the reference signal char

Assignees

• Advanced Bionics Ag

Inventors

• Fredelake Stefan

Classifications

• H04R25/305 Primary

  Self-monitoring or self-testing · CPC title

• A61N1/36038

  Cochlear stimulation · CPC title

• G10L25/60

  for measuring the quality of voice signals · CPC title

• G10L21/038

  using band spreading techniques · CPC title

• G10L25/78

  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 title