Implantable sensor training

Abstract

Methods for training a signal analysis module are presented herein. The method comprises: generating an external audio input based on sound signals captured by one or more external microphones; generating, with a signal analysis module, an implantable audio input based on the sound signals captured by the one or more implantable microphones; analyzing the implantable audio input relative to the external audio input; and adjusting operation of the signal analysis module based on analyzing the implantable audio input relative to the external audio input.

Description

background Technical Field

[0002] The present invention generally relates to implantable sensors, such as implantable microphones. Background Art

[0003] Medical devices have provided a wide range of therapeutic benefits to recipients over the last several decades. Medical devices may include internal or implantable components / devices, external or wearable components / devices, or combinations thereof (e.g., devices having external components that communicate with implantable components). Medical devices, such as traditional hearing aids, partially or fully implantable hearing prostheses (e.g., bone conduction devices, mechanical stimulators, cochlear implants, etc.), pacemakers, defibrillators, functional electrical stimulation devices, and other medical devices, have been successful over the years in performing life-saving and / or lifestyle-improving functions and / or recipient monitoring.

[0004] Over the years, the types of medical devices and the range of functions performed by them have increased. For example, many medical devices, sometimes referred to as "implantable medical devices," now typically include one or more instruments, devices, sensors, processors, controllers, or other functional mechanical or electrical components that are permanently or temporarily implanted in a recipient's body. These functional devices are typically used to diagnose, prevent, monitor, treat, or manage disease / injury or its symptoms, or to study, replace, or modify anatomical structures or physiological processes. Many of these functional devices utilize power and / or data received from an external device that is part of or operates in conjunction with the implantable component. Summary of the invention

[0005] In one aspect, a method is provided. A first method includes: generating an external audio input based on sound signals captured by one or more external microphones; generating an implantable audio input based on the sound signals captured by the one or more implantable microphones using a signal analysis module; analyzing the implantable audio input relative to the external audio input; and adjusting operation of the signal analysis module based on analyzing the implantable audio input relative to the external audio input.

[0006] In another aspect, a medical device is provided. The medical device includes: one or more external sensors; one or more implantable sensors; a signal analysis module; and one or more processors, wherein the one or more processors are configured to: generate an external signal input based on signals captured by the one or more external sensors; generate an implantable signal input based on signals captured by the one or more implantable sensors by the signal analysis module; analyze the implantable signal input relative to the external signal input; and adjust the operation of the signal analysis module based on analyzing the implantable signal input relative to the external signal input.

[0007] In another aspect, one or more non-transitory computer-readable storage media are provided. The one or more non-transitory computer-readable storage media include instructions that, when executed by a processor, cause the processor to: receive, at a machine learning device, an implantable sound signal captured by one or more implantable microphones of a hearing device, the machine learning device being trained to convert the implantable sound signal into a substantial match with an external audio input generated based on an external sound signal captured by one or more external microphones; process, by the machine learning device, the implantable sound signal to generate an implantable audio input; and output the implantable audio input to a recipient of the hearing device. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Embodiments of the present invention are described herein with reference to the accompanying drawings, in which:

[0009] Figure 1A is a schematic diagram illustrating a cochlear implant system with which aspects of the technology presented herein may be implemented;

[0010] Figure 1B Yes Wear Figure 1A A side view of a recipient of a sound processing unit of a cochlear implant system;

[0011] Figure 1C yes Figure 1A A schematic diagram of components of a cochlear implant system;

[0012] Figure 2 yes Figure 1A Block diagram of a cochlear implant system;

[0013] Figure 3 is a flow chart illustrating a method for determining whether a hearing device is to be operated in a training mode or whether the hearing device is to process an audio input using a trained system according to embodiments presented herein.

[0014] Figure 4 is a block diagram illustrating a method of training a signal analysis module at an internal component of a hearing device according to embodiments presented herein.

[0015] Figure 5 is a block diagram illustrating a method of training a signal analysis module at an external component of a hearing device according to embodiments presented herein.

[0016] Figure 6 is a block diagram illustrating a method of training a signal analysis module at an external device communicating with a hearing device according to embodiments presented herein.

[0017] Figure 7is a flow chart illustrating a method of training a signal analysis module according to embodiments presented herein.

[0018] Figure 8 is a flow chart illustrating a method of processing an implantable sound signal using a signal analysis module according to embodiments presented herein; and

[0019] Fig. 9 is a schematic diagram illustrating a vestibular stimulator system with which aspects of the technology presented herein may be implemented. DETAILED DESCRIPTION

[0020] Presented herein are techniques for improving the performance of implantable (subcutaneous) sensors, such as implantable microphones (e.g., subcutaneous microphones, middle ear microphones, oral microphones, etc.). For example, in certain embodiments, machine learning or deep learning methods (using neural networks or deep neural networks (DNNs) with multiple hidden layers) can be used to convert signals from implantable sensors to substantially match (e.g., more closely resemble) signals received by external sensors. For example, in the context of hearing devices, sounds and vibrations captured simultaneously by external microphones / sensors and implantable microphones / sensors can be used to train and / or update a previously trained machine learning system or neural network, which can be applied to (e.g., used to process) signals captured by implantable microphones / sensors.

[0021] When compared to conventional microphones used in hearing aids and cochlear implant sound processors, implantable (subcutaneous) microphones have unfavorable characteristics, such as high background noise, non-flat frequency response, low sensitivity to external sounds, and high sensitivity to internal sounds / vibrations of the body (including heartbeat, breathing, and even vibrations induced from the contralateral hearing aid). These unfavorable characteristics result in relatively poor speech understanding, sound quality, and satisfaction for the recipient when using a subcutaneous microphone. This problem is exacerbated in systems where the recipient can switch between (and therefore compare) an external microphone (e.g., using "external hearing") and an implantable microphone (e.g., using "invisible hearing"). Since each system changes in different ways (external microphone covers get dirty, implantable microphone characteristics change with biological changes (e.g., generation, medical intervention, etc.)), these differences in sound / performance can increase over time, which can make the differences jarring every time the recipient switches between external hearing and invisible hearing.

[0022] A machine learning system or neural network may be trained (e.g., using data from a large number of participants or using recipient-specific data) such that acoustic signals received at an implantable microphone may be converted (processed) to closely resemble acoustic signals received at an external microphone. More specifically, sounds and vibrations captured simultaneously by an external sensor (e.g., an external microphone) and an implantable sensor (e.g., an implantable microphone and / or an implantable vibration sensor (e.g., an accelerometer)) may be used to train a "signal analysis module" that is used to generate an improved implantable microphone output signal (e.g., to train a machine learning system and / or update a previously trained machine learning system to convert an internally captured sound signal to a signal that more closely resembles an externally captured sound signal). As further described below, in some embodiments, this training may use group data from many comparisons to train a general machine learning system for use in many recipients. In the same or other embodiments, this training may use recipient-specific data to train and / or update the system while the system is being used for that recipient.

[0023] A signal analysis module (e.g., a signal analysis machine learning system or neural network) can process the acoustic signal (e.g., remove unwanted signals from or transmitted by the body, fill in missing information / frequency content (e.g., with low sound intensities and frequencies that have poor responses), etc.) so that the sound quality of the invisible hearing mode more closely matches the sound quality of the external hearing mode before delivery as sound in the hearing prosthesis. By continuously training and updating the signal analysis module, the external hearing mode and the invisible hearing mode can produce similar sound quality regardless of any changes that may occur in the microphone characteristics.

[0024] In one embodiment, a single large machine learning system can be used to enhance the implantable microphone signal. In other embodiments, multiple machine learning systems can be deployed. In this case, a specific machine learning system can be selected by another machine learning algorithm (e.g., a DNN) that analyzes the current situation and selects the correct machine learning system to maximize performance for that situation (e.g., one machine learning system may be best for removing body noise, another machine learning system may be best for soft external sounds, and another machine learning system may be best in a noisy acoustic situation with multiple competing talkers).

[0025] At least some exemplary embodiments according to the teachings detailed herein utilize advanced learning signal processing techniques that are trained to detect higher order and / or nonlinear statistical properties of signals. As discussed above, the exemplary signal processing technique is a DNN. At least some exemplary embodiments utilize a DNN (or any other advanced learning signal processing technique) to process a signal representing a captured sound, the processed signal being used to evoke auditory perception. At least some exemplary embodiments require training a signal processing algorithm to process a signal indicating a captured sound. That is, some exemplary methods utilize a learning algorithm or system (e.g., a DNN) or any other system that would otherwise enable the teachings detailed herein to analyze captured sounds.

[0026] A "neural network" is a specific type of machine learning system. Any disclosure herein of the class "neural network" constitutes disclosure of the genus "machine learning system". While the embodiments herein focus on neural networks of that class, it should be noted that other embodiments may accordingly utilize other classes of machine learning systems, and any disclosure herein of neural networks constitutes disclosure of any other class of machine learning systems that may implement the teachings detailed herein and variations thereof. For clarity, at least some embodiments according to the teachings detailed herein are embodiments that have the ability to learn without being explicitly programmed. Therefore, with respect to some embodiments, any disclosure herein of an apparatus or system constitutes disclosure of an apparatus and / or system that has the ability to learn without being explicitly programmed, and any disclosure of a method constitutes an action that enables learning without being explicitly programmed therefor.

[0027] For ease of description only, the technology presented herein is mainly described with reference to a specific implantable medical device system, i.e., a cochlear implant system. However, it should be understood that the technology presented herein can also be partially or completely implemented by other types of implantable medical devices. For example, the technology presented herein can be implemented by other auditory prosthesis systems including one or more other types of auditory prostheses (e.g., middle ear auditory prostheses, bone conduction devices, direct sound stimulators, electroacoustic prostheses, auditory brain stimulators, combinations or variations thereof, etc.). The technology presented herein can also be implemented by proprietary tinnitus treatment devices and tinnitus treatment device systems. In other embodiments, the technology presented herein can also be implemented by vestibular devices (e.g., vestibular implants), visual devices (i.e., bionic eyes), sensors, pacemakers, drug delivery systems, defibrillators, functional electrical stimulation devices, catheters, epileptic seizure devices (e.g., devices for monitoring and / or treating epileptic events), sleep apnea devices, electroporation devices, etc., or used in combination with them.

[0028] Figures 1A-1C and Figure 2An exemplary cochlear implant system 102 is shown with which aspects of the technology presented herein may be implemented. Cochlear implant system 102 includes an external component 104 and an implantable component 112. Of these, the implantable component is sometimes referred to as a "cochlear implant." Figure 1A The cochlear implant 112 is shown implanted in the head 154 of the recipient, and Figure 1B is a schematic diagram of the outer member 104 worn on the head 154 of the recipient. Figure 1C is another schematic diagram of a cochlear implant system 102, and Figure 2 Additional details of cochlear implant system 102 are shown. For ease of description, the following will be generally described together. Figure 1A , 1B , 1C and 2.

[0029] Cochlear implant system 102 includes an external component 104 configured to be attached directly or indirectly to the body of a recipient, and an implantable component 112 configured to be implanted in the body of the recipient. External component 104 includes a sound processing unit 106, while cochlear implant 112 includes an implantable coil 114, an implant body 134, and an elongated stimulation assembly 116 configured to be implanted in the cochlea of ​​the recipient.

[0030] The sound processing unit 106 is an outside-the-ear (OTE) sound processing unit (sometimes referred to herein as an OTE component) that is configured to send data and power to the implantable component 112. Generally speaking, the OTE sound processing unit is a component having a generally cylindrical housing 111 and configured to be magnetically coupled to the head of a recipient (e.g., including an integrated external magnet 150 configured to be magnetically coupled to an implantable magnet 152 in the implantable component 112). The OTE sound processing unit 106 also includes an integrated external (head component) coil 108 configured to be inductively coupled to the implantable coil 114.

[0031] It should be understood that the OTE sound processing unit 106 is merely illustrative of an external device that can operate with the implantable component 112. For example, in alternative examples, the external component can include a behind-the-ear (BTE) sound processing unit or a micro-BTE sound processing unit and a separate external unit. Generally speaking, the BTE sound processing unit includes a housing that is shaped to be worn on the recipient's outer ear and connected to a separate external coil assembly via a cable, wherein the external coil assembly is configured to be magnetically coupled and inductively coupled to the implantable coil 114. It should be understood that alternative external components can be located in the recipient's ear canal, worn on the body, etc.

[0032] As described above, cochlear implant system 102 includes sound processing unit 106 and cochlear implant 112. However, as further described below, cochlear implant 112 can operate independently of sound processing unit 106 for at least a period of time to stimulate a recipient. For example, cochlear implant 112 can operate in a first general mode (sometimes referred to as an "external hearing mode"), in which sound processing unit 106 captures sound signals, which are then used as a basis for delivering stimulation signals to the recipient. Cochlear implant 112 can also operate in a second general mode (sometimes referred to as an "invisible hearing" mode), in which sound processing unit 106 cannot provide sound signals to cochlear implant 112 (e.g., sound processing unit 106 is not present, sound processing unit 106 is powered off, sound processing unit 106 is malfunctioning, etc.). Therefore, in the invisible hearing mode, cochlear implant 112 captures the sound signals itself via an implantable sound sensor, and then uses these sound signals as a basis for delivering stimulation signals to the recipient. Further details regarding the operation of cochlear implant 112 in the external hearing mode are provided below, followed by details regarding the operation of cochlear implant 112 in the invisible hearing mode. It should be understood that the reference to the external hearing mode and the invisible hearing mode is merely illustrative, and cochlear implant 112 may also operate in alternative modes.

[0033] exist Figure 1A and 1C , a cochlear implant system 102 is shown with an external device 110 configured to implement various aspects of the presented technology. The external device 110 is a computing device, such as a computer (e.g., a laptop, a desktop computer, a tablet), a mobile phone, a remote control unit, etc. As further described below, the external device 110 includes a telephone enhancement module, as further described below, which is configured to implement various aspects of the auditory rehabilitation technology presented herein for independent telephone use. The external device 110 and the cochlear implant system 102 (e.g., an OTE sound processing unit 106 or a cochlear implant 112) communicate wirelessly via a two-way communication link 126. The two-way communication link 126 may include, for example, short-range communications, such as a Bluetooth link, a Bluetooth low energy (BLE) link, a proprietary link, etc.

[0034] Back to Figure 1A , 1B , 1C and Figure 2In the example of the OTE sound processing unit 106, one or more input devices are configured to receive input signals (e.g., sound or data signals). The one or more input devices include one or more sound input devices 118 (e.g., one or more external microphones, audio input ports, telecoils, etc.), one or more auxiliary input devices 128 (e.g., audio ports, such as direct audio input (DAI), data ports, such as universal serial bus (USB) ports, cable ports, etc.), and wireless transmitter / receiver (transceiver) 120 (e.g., for communicating with external devices 110). However, it should be understood that the one or more input devices may include additional types of input devices and / or fewer input devices (e.g., the wireless short-range radio transceiver 120 and / or one or more auxiliary input devices 128 may be omitted).

[0035] The OTE sound processing unit 106 also includes an external coil 108, a charging coil 130, a tightly coupled transmitter / receiver (RF transceiver) 122 (sometimes referred to as a radio frequency (RF) transceiver 122), at least one rechargeable battery 132, and an external sound processing module 124. The external sound processing module 124 may include, for example, one or more processors and a memory device (memory) including sound processing logic. The memory device may include any one or more of the following: non-volatile memory (NVM), ferroelectric random access memory (FRAM), read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. The one or more processors are, for example, microprocessors or microcontrollers that execute instructions of the sound processing logic stored in the memory device.

[0036] The implantable component 112 includes an implant body (main module) 134, a lead region 136, and an intracochlear stimulation assembly 116, all configured to be implanted beneath the skin / tissue (tissue) 115 of a recipient. The implant body 134 generally includes a hermetically sealed housing 138 in which an RF interface circuit system 140 and a stimulator unit 142 are disposed. The implant body 134 also includes an internal / implantable coil 114, which is generally external to the housing 138 but is connected to the stimulator unit 142 via a hermetic feedthrough ( Figure 2 ) is connected to the RF interface circuit system 140.

[0037] As described, the stimulation assembly 116 is configured to be at least partially implanted in the cochlea of ​​a recipient. The stimulation assembly 116 includes a plurality of longitudinally spaced intracochlear electrical stimulation contacts (electrodes) 144 that collectively form a contact or electrode array 146 for delivering electrical stimulation (electrical current) to the cochlea of ​​the recipient.

[0038] The stimulation assembly 116 extends through an opening in the recipient's cochlea (e.g., a cochlear fenestration, a round window, etc.) and has a lead region 136 and an airtight feedthrough ( Figure 2 144 is connected to the proximal end of the stimulator unit 142. The lead region 136 includes a plurality of conductors (wires) that electrically couple the electrode 144 to the stimulator unit 142. The implantable component 112 also includes an electrode outside the cochlea, sometimes referred to as an extracochlear electrode (ECE) 139.

[0039] As described, the cochlear implant system 102 includes an external coil 108 and an implantable coil 114. An external magnet 152 is fixed relative to the external coil 108, and the implantable magnet 152 is fixed relative to the implantable coil 114. The magnets fixed relative to the external coil 108 and the implantable coil 114 facilitate operational alignment of the external coil 108 with the implantable coil 114. This operational alignment of the coils enables the external component 104 to transmit data and power to the implantable component 112 via a closely coupled wireless link 148 formed between the external coil 108 and the implantable coil 114. In some examples, the closely coupled wireless link 148 is a radio frequency (RF) link. However, various other types of energy transfer (e.g., infrared (IR), electromagnetic, capacitive, and inductive transfer) may be used to transfer power and / or data from the external component to the implantable component, and thus, Figure 2 Only one exemplary arrangement is shown.

[0040] As described above, the sound processing unit 106 includes an external sound processing module 124. The external sound processing module 124 is configured to convert an input signal received (received at one or more of the input devices) into an output signal for stimulating the first ear of the recipient (i.e., the external sound processing module 124 is configured to perform sound processing on the input signal received at the sound processing unit 106). In other words, the one or more processors in the external sound processing module 124 are configured to execute the sound processing logic in the memory to convert the received input signal into an output signal representing electrical stimulation for delivery to the recipient.

[0041] As stated, Figure 2 An embodiment is shown in which an external sound processing module 124 in the sound processing unit 106 generates an output signal. In alternative embodiments, the sound processing unit 106 can send less processed information (e.g., audio data) to the implantable component 112, and the sound processing operations (e.g., conversion of sound to output signals) can be performed by a processor within the implantable component 112.

[0042] Back to Figure 2In a specific example, the output signal is provided to the RF transceiver 122, which transmits the output signal (e.g., in an encoded manner) transcutaneously to the implantable component 112 via the external coil 108 and the implantable coil 114. That is, the output signal is received at the RF interface circuit system 140 via the implantable coil 114 and provided to the stimulator unit 142. The stimulator unit 142 is configured to utilize the output signal to generate an electrical stimulation signal (e.g., a current signal) for delivery to the cochlea of ​​the recipient. In this way, the cochlear implant system 102 electrically stimulates the auditory nerve cells of the recipient, thereby bypassing the missing or defective hair cells that normally convert acoustic vibrations into neural activity in a manner that causes the recipient to perceive one or more components of the received sound signal.

[0043] As described in detail above, in the external hearing mode, the cochlear implant 112 receives processed sound signals from the sound processing unit 106. However, in the invisible hearing mode, the cochlear implant 112 is configured to capture and process the sound signals for electrical stimulation of the recipient's auditory nerve cells. Figure 2 As shown in , the cochlear implant 112 includes a plurality of implantable sound sensors 160 and an implantable sound processing module 158. Similar to the external sound processing module 124, the implantable sound processing module 158 may include, for example, one or more processors and a memory device (memory) including sound processing logic. The memory device may include any one or more of the following: non-volatile memory (NVM), ferroelectric random access memory (FRAM), read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. The one or more processors are, for example, microprocessors or microcontrollers that execute instructions of the sound processing logic stored in the memory device.

[0044] In the invisible hearing mode, the implantable sound sensor 160 is configured to detect / capture a signal (e.g., an acoustic sound signal, a vibration, etc.), which is provided to the implantable sound processing module 158. The implantable sound processing module 158 is configured to convert the received input signal (received at one or more implantable sound sensors 160) into an output signal for stimulating the first ear of the recipient (i.e., the processing module 158 is configured to perform a sound processing operation). In other words, the one or more processors in the implantable sound processing module 158 are configured to execute the sound processing logic in the memory to convert the received input signal into an output signal 156 provided to the stimulator unit 142. The stimulator unit 142 is configured to generate an electrical stimulation signal (e.g., an electric current signal) for delivery to the cochlea of ​​the recipient using the output signal 156, thereby bypassing the missing or defective hair cells that normally convert the acoustic vibrations into neural activity.

[0045] It should be understood that the above description of the so-called external hearing mode and the so-called invisible hearing mode is merely illustrative, and that the cochlear implant system 102 may operate differently in different embodiments. For example, in an alternative embodiment of the external hearing mode, the cochlear implant 112 may use the signals captured by the sound input device 118 and the implantable sound sensor 160 to generate stimulation signals for delivery to the recipient.

[0046] exist Figure 1A , 1B , 1C and Figure 2In the example of , aspects of the techniques presented herein may be performed by one or more components of cochlear implant system 102, such as external sound processing module 124, implantable sound processing module 158, and / or external device 110, among others. This is generally illustrated by dashed box 162. That is, dashed box 162 generally represents the possible location of some or all of a "signal analysis module" 162 (which is sometimes referred to herein as a "signal analysis machine learning device" or "signal analysis machine learning logic"), which, when implemented, is configured to perform aspects of the techniques presented herein. As described above, external sound processing module 124, implantable sound processing module 158, and / or external device 110 may include, for example, one or more processors and memory devices (memory), the memory devices including all or part of signal analysis machine learning device 162. The memory devices may include any one or more of the following: NVM, RAM, FRAM, ROM, magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. The one or more processors are, for example, microprocessors or microcontrollers that execute instructions stored in a memory device for the signal analysis machine learning device 162. In some embodiments, the signal analysis machine learning device 162 may be a neural network or DNN. As further described below, the signal analysis machine learning device 162 may be implemented internally (e.g., implanted within the body of a recipient) and / or externally (e.g., outside the body of a recipient).

[0047] The signal analysis machine learning device (signal analysis module) presented herein (e.g., signal analysis machine learning device 162) is a functional block (e.g., one or more processors operating based on code, algorithm(s), etc.) that is trained through a machine learning process to convert sound signals captured by implantable sound sensor 160 into signals that are more like sound signals captured and processed at external component 104. As further described below, converting sound signals captured by implantable sound sensor 160 into signals that are more like sound signals captured and processed at external component 104 includes modeling and estimating external sound signals based on implantable sound signals.

[0048] Figure 3 3 is a flow chart of an exemplary method 300 for determining whether a hearing device is to operate in a training mode or whether the hearing device is to process an audio input using a trained system according to embodiments presented herein. As discussed below, a signal analysis machine learning device can be trained to process an audio signal captured by an implantable microphone so that the audio signal output approximately matches the output of the same audio signal captured by an external microphone of an external device. Training of the signal analysis machine learning device can occur when both the external microphone and the implantable microphone are available.

[0049] Method 300 begins at 310 by determining whether an external processor is available. For example, cochlear implant system 102 may determine whether the external processor is on, such as when the recipient is using external hearing or is charging an implanted battery with sound processing unit 106. In some embodiments, cochlear implant system 102 may additionally determine whether the external processor is receiving an optimal signal. For example, cochlear implant system 102 may determine whether sound processing unit 106 is receiving a clear audio signal.

[0050] If an external processor is available (and optionally, the sound processor is receiving the best signal), then a signal is selected from the external microphone and used to train the signal analysis machine learning device at 320. For example, if sound processing unit 106 is on and a clear audio signal is being received (e.g., at sound input device 118), cochlear implant system 102 can enter a training mode, and the audio signal captured by the external microphone can be used in conjunction with the audio signal captured by one or more implantable microphones to train signal analysis machine learning device 162. As described below, training of the signal analysis machine learning device can be performed at external device 110, external component 104, or cochlear implant 112.

[0051] If the external processor is not available (and / or the external processor is not receiving the best signal), at 330, a signal is selected from an internal or implanted component of cochlear implant system 102 and processed by the trained signal analysis machine learning device. For example, if sound processing unit 106 is not turned on or if the audio signal received at sound processing unit 106 is unclear, training may not be performed and cochlear implant system 102 may be operated in invisible hearing mode. In invisible hearing mode, the audio signal may be detected / captured by implantable sound sensor 160 and processed by trained signal analysis machine learning device 162.

[0052] As described above, certain aspects presented herein use a signal analysis machine learning device (sometimes referred to herein as a signal analysis module) to determine how to convert an implantable audio input to more closely resemble an external audio input. A signal analysis module is a functional block (e.g., one or more processors operating based on code, (multiple) algorithms, etc.) that is trained through a machine learning process to modify a sound signal captured at an implantable microphone to more closely resemble an external audio input generated based on a sound signal captured at an external microphone. In some examples, the signal analysis machine learning device (sometimes referred to herein as a signal analysis module 362) is configured to estimate an external audio signal from the implantable audio signal using a trained model. In some embodiments, the signal analysis module 362 may include a neural network or DNN and a mechanism for training the network.

[0053] Figure 4 is a functional block diagram illustrating training a signal analysis module 362 at a cochlear implant 112 according to an embodiment presented herein. As shown, the sound input device(s) 118 of the external component 104 captures a sound signal, and at 402, the sound signal is output to a pre-processing module 404. The pre-processing module 404 can process the sound signal to generate an external audio signal by, for example, noise reduction, removing background noise, improving microphone directivity, removing or reducing unwanted sounds (e.g., wind noise, very high saturation signals, etc.). At 406, the external audio signal is output to a wireless encoder 408 for encoding, and at 410, the wireless encoder 408 outputs the external audio signal to an antenna output 412 for transmission to the cochlear implant 112.

[0054] At cochlear implant 112, antenna input 414 receives the external audio signal from antenna output 412 of external component 104 and transmits the external audio signal to wireless decoder 418 for decoding at 416. At 420, wireless decoder 418 outputs the external audio signal.

[0055] Additionally, at the cochlear implant 112, the implantable sound sensor 160 captures the sound signal received at the sound input device(s) 118 of the external component 104 (e.g., at approximately the same time as the sound input device(s) 118 captured the sound signal). At 434, the implantable sound sensor 160 transmits the implantable sound signal to the signal analysis module 362 for processing. The signal analysis module 362 has been trained to receive the implantable sound signal from the implantable sound sensor 160 and convert the implantable sound signal to more closely match the external audio signal generated at the external component 104 based on the sound signal captured by the sound input device(s) 118. This conversion of the implantable sound signal can also be considered to model and estimate the external sound signal based on the implantable sound signal.

[0056] The signal analysis module 362 processes the implantable sound signal and, at 436, outputs an estimate of the external audio signal. The loss function 422 receives the estimate of the external audio signal from the signal analysis module 362 and receives the actual external audio signal from the wireless decoder 418. The loss function 422 analyzes the estimate of the external audio signal relative to the actual external audio signal. For example, the loss function 422 compares the estimate of the external audio signal with the actual external audio signal and calculates an error function to identify any differences between the two signals. At 424, the loss function 422 outputs an indication of the difference between the two signals.

[0057] As discussed above, the signal analysis module 362 has been trained to estimate the external audio signal as closely as possible based on the implantable audio signal. Therefore, the differences between the implantable audio signal and the external audio signal identified by the loss function 422 can be used to train the signal analysis module 362 and adjust its parameters. As the signal analysis module 362 continues to be trained, the estimate of the external audio signal based on the implantable audio signal can continue to match the actual external audio signal more closely.

[0058] The signal analysis module 362 receives the output of the loss function 422 and adjusts operations based on the output of the loss function 422. For example, the signal analysis module 362 can set or update weights associated with the signal analysis module 362 to improve processing of the implantable audio signal to better model and estimate the external audio signal. By adapting new or updated weights during training, the signal analysis module 362 can continue to improve processing of the implantable sound signal so that its estimate of the external audio signal more closely matches the actual external audio signal.

[0059] When the hearing device is in the external hearing mode, the recipient of the hearing device receives the external audio signal, and when the hearing device is in the stealth mode, the recipient receives an estimate of the external audio signal based on the implantable audio signal. Therefore, the source selector 430 of the cochlear implant 112 can receive the external audio signal from the wireless decoder 418 and the implantable audio signal from the signal analysis module 362. The source selector 430 can determine which signal to select for output to the recipient of the cochlear implant system 102 based on the mode associated with the cochlear implant system 102. When the cochlear implant system 102 is in the external hearing mode, the source selector 430 selects the external audio signal, and when the cochlear implant system 102 is in the stealth mode, the source selector 430 selects the external audio signal estimated from the implantable audio signal. When the recipient switches the mode associated with the cochlear implant system 102, the source selector 430 switches the selected audio signal. At 432, the source selector 430 outputs the selected audio signal.

[0060] The sound processing chain 440 receives the selected audio signal. The sound processing chain 440 may include, for example, a filter bank, an envelope extraction module, a channel selection module, a loudness mapping module, and / or additional sound processing modules. The sound processing chain 440 generally operates to convert the received sound signal into an output signal that can be used to deliver a stimulus to a recipient in a manner that evokes the perception of the sound signal. At 442, the sound processing chain 440 transmits the processed sound signal to an output 444 to deliver the stimulus to the recipient, thereby evoked the perception of the sound signal.

[0061] Figure 5is a functional block diagram illustrating training of the signal analysis module 362 at the external component 104 according to embodiments presented herein. Figure 5 In the depicted example, the signal analysis module 362(1) is located at the external component 104 and is trained when the hearing device is in the training mode. The signal analysis module 362(2) at the cochlear implant 112 receives information from the training of the signal analysis module 362(1) and is used to process the sound signals captured by the implantable sound sensor 160.

[0062] As shown, the sound input device(s) 118 of the external component 104 may capture a sound signal, and at 502, the sound input device(s) 118 may output the sound signal to the pre-processing module 404 to be processed as described above with respect to Figure 4 The preprocessing module 404 preprocesses the external sound signal, and at 504, the preprocessing module 404 outputs the external audio signal.

[0063] At the cochlear implant 112, the implantable sound sensor 160 captures the sound signal (e.g., at approximately the same time as the sound input device(s) 118 captures the sound signal), and the implantable sound sensor 160 outputs the implantable sound signal at 524. The wireless encoder 525 encodes the implantable sound signal, and at 528, the wireless encoder 525 transmits the implantable sound signal to the antenna output 530 for transmission to the external component 104.

[0064] At external component 104, antenna input 510 receives implantable sound signals from antenna output 530 of cochlear implant 112 and transmits the implantable sound signals to wireless decoder 514 at 512. Wireless decoder 514 decodes the implantable sound signals and outputs the implantable sound signals at 516. Signal analysis module 362(1) processes the implantable sound signals (as described above with respect to Figure 4 ) to modify the implantable sound signal to more closely match the external audio signal, and generate an estimate of the external audio signal. At 520, the signal analysis module 362(1) outputs an estimate of the external audio signal.

[0065] The loss function 506 receives an estimate of the external audio signal from the signal analysis module 362(1) and receives the actual external audio signal from the pre-processing module 404. Figure 4 As described above, the loss function 506 analyzes the estimate of the external audio signal relative to the actual external audio signal and calculates an error function and / or identifies any differences between the two audio signals. At 538, the loss function 506 outputs an indication of the difference between the estimate of the external audio signal and the actual external audio signal. Figure 4 As described, the signal analysis module 362 ( 1 ) may set or update the weight based on the difference between the estimation of the external audio signal and the actual external audio signal.

[0066] although Figure 5 Training of the signal analysis module 362(1) occurs at the external component 104, but the signal analysis module 362(2) of the cochlear implant 112 uses the new weights or updated weights to improve processing of sound signals captured at the implantable sound sensor 160 (e.g., when the hearing device is in stealth mode). To transmit the new weights or updated weights to the signal analysis module 362(2), the wireless encoder 408 receives the new weights / updated weights from the signal analysis module 362(1), encodes the weights, and at 508, transmits the encoded weights to the antenna output 412 for transmission to the cochlear implant 112.

[0067] At cochlear implant 112, antenna input 414 may receive the new / updated weights from antenna output 412. At 530, antenna input 414 outputs the new / updated weights to wireless decoder 418 for decoding, and at 534, wireless decoder 418 transmits the new / updated weights to signal analysis module 362(2) of cochlear implant 112. After receiving the new / updated weights, signal analysis module 362(2) of cochlear implant 112 may provide improved processing of subsequent sound signals received at implantable sound sensor 160.

[0068] In order to provide the audio signal to the recipient of the hearing device, the external component 104 may additionally transmit the external audio signal to the cochlear implant 112. To perform the transmission, the wireless encoder 408 of the external component 104 encodes the external audio signal and, at 508, outputs the external audio signal to the antenna output 412 for transmission to the cochlear implant 112. The antenna input 414 may receive the external audio signal from the antenna output 412 and, at 530, the antenna input 414 transmits the external audio signal to the wireless decoder 418. The wireless decoder 418 may decode the external audio signal and, at 532, output the external audio signal.

[0069] Signal analysis module 362(2) receives the sound signal from implantable sound sensor 160 and processes the sound signal based on previous training. For example, signal analysis module 362(2) processes the sound signal output at implantable sound sensor 160 to resemble the sound signal that pre-processing module 404 would have output if sound input device(s) 118 had received the same sound input. At 536, signal analysis module 362(2) outputs the processed sound signal.

[0070] The source selector 430 receives the external audio signal from the wireless decoder 418 and receives an estimate of the external audio signal from the implantable audio signal from the signal analysis module 362(2), and outputs the external audio signal or an estimate of the external audio signal from the implantable audio signal at 538, as described above with respect to Figure 4 For example, source selector 430 outputs an estimate of the external audio signal based on the implantable audio signal when the hearing device is in the stealth mode, and outputs the external audio signal when the hearing device is in the external hearing mode. Based on the source selection, the recipient of cochlear implant system 102 receives the processed sound signal from the (multiple) sound input device 118 of the external component 104 or the implantable sound sensor 160 of the cochlear implant 112. At 538, source selector 430 transmits the selected audio signal to sound processing chain 440, and sound processing chain 440 is as described above with respect to Figure 4 At 538, the sound processing chain 440 transmits the processed audio signal to the output 444 to deliver the stimulus to the recipient, thereby evoking the perception of the sound signal.

[0071] Figure 6 is a functional block diagram illustrating training of the signal analysis module 362 at the external device 100 according to an embodiment presented herein. Figure 6 In the depicted example, a communication link is provided between external component 104 and external device 110, and a second communication link is provided between external device 110 and cochlear implant 112. Figure 6 In the depicted example, signal analysis module 362(3) is located at external device 110 and is trained when the hearing device is in training mode. Signal analysis module 362(2) at cochlear implant 112 receives information related to training of signal analysis module 362(3) for processing sound signals captured by implantable sound sensor 160.

[0072] As shown, at the external component 104, the sound input device(s) 118 captures sound signals and, at 602, outputs the external sound signals to the pre-processing module 404 to be processed in accordance with the above description of Figure 4 At 604, the pre-processing module 404 outputs the external audio signal to the wireless encoder 408 for encoding, as described above with respect to Figure 4 At 606, wireless encoder 408 outputs the external audio signal to antenna output 412 for transmission to cochlear implant 112 (eg, when the hearing device is in external hearing mode) and to external device 110 for use in training signal analysis module 362(3).

[0073] At the cochlear implant 112, the implantable sound sensor 160 captures the sound signal (e.g., at approximately the same time as the sound input device(s) 118 captures the sound signal) and outputs the implantable sound signal at 636. The wireless encoder 526 receives the implantable sound signal and encodes the implantable sound signal. At 638, the wireless encoder 526 outputs the implantable sound signal to the antenna output 530 for transmission to the external device 110 for use in training the signal analysis module 362 (3).

[0074] At the external device 110, the antenna input 608 receives the external audio signal from the antenna output 412 of the external component 104, and at 610, outputs the external audio signal to the wireless decoder 612 for decoding. The wireless decoder 612 decodes the external audio signal and, at 614, outputs the external audio signal. Additionally, the antenna input 622 receives the implantable sound signal from the antenna output 530 of the cochlear implant 112, and, at 624, the antenna input 622 outputs the implantable sound signal to the wireless decoder 626 for decoding. The wireless decoder 626 decodes the implantable sound signal and, at 628, outputs the implantable sound signal to the signal analysis module 362(3) for processing. As described above, the signal analysis module 362(3) has been trained to modify the implantable sound signal to generate an implantable audio signal that more closely resembles the external audio signal from the external component 104. The signal analysis module 362(3) processes the implantable sound signal and, at 630, outputs an estimate of the external audio signal.

[0075] The loss function 632 receives the external audio signal from the wireless decoder 612 and receives the estimate of the external audio signal from the signal analysis module 362, and analyzes the actual external audio signal relative to the estimate of the external audio signal. In particular, the loss function 632 calculates an error function and / or identifies the difference between the two sound signals, as described above with respect to Figure 4 and 5As described. At 634, the loss function 632 outputs an indication of the difference(s) between the two signals. The signal analysis module 362(3) receives an input identifying the difference(s) between the actual external audio signal and the estimate of the external audio signal, and sets or updates weights / parameters to estimate the external audio signal as closely as possible based on the implantable sound signal based on the difference(s). The signal analysis module 362(3) adjusts operation based on the new or updated weights / parameters. When training of the signal analysis module 362(3) is completed within the training mode session, at 628, the signal analysis module 362(3) at the external device 110 outputs the new or updated weights / parameters for transmission to the signal analysis module 362(2) at the cochlear implant 112. The wireless encoder 616 encodes the new or updated weights / parameters and, at 614, outputs the encoded weights / parameters to the antenna output 620 for transmission to the cochlear implant 112.

[0076] At cochlear implant 112, antenna input 652 receives the new or updated weights / parameters from antenna output 412 and outputs the new or updated weights / parameters to wireless decoder 418 at 640. Wireless decoder 418 decodes the new or updated weights / parameters and transmits the new or updated weights / parameters to signal analysis module 362(2) at cochlear implant 112 at 642. By implementing the new or updated weights / parameters received from signal analysis module 362(3) at external device 110, signal analysis module 362(2) at cochlear implant 112 can improve processing of implantable sound signals, thereby better modeling and estimating external audio signals based on the training of signal analysis module 362(3) at external device 110.

[0077] To provide an external audio signal to a recipient of the hearing device (e.g., when the hearing device is in an external hearing mode), antenna input 414 at cochlear implant 112 receives the external audio signal from antenna output 412 and, at 646, outputs the signal to wireless decoder 418. Wireless decoder 418 decodes the external audio signal and, at 648, outputs a decoded external component sound signal.

[0078] The source selector 430 receives the external audio signal from the wireless decoder 418 and the estimate of the external audio signal from the signal analysis module 362(2), and selects a single audio signal based on the mode of the hearing device. For example, if the hearing device is in the external hearing mode, the source selector 430 selects the external audio signal, and if the hearing device is in the stealth mode, the source selector 430 selects the estimate of the external audio signal based on the implantable audio signal. Based on the source selection, the recipient of the cochlear implant system 102 receives an audio signal from the (multiple) sound input device 118 of the external component 104 or the implantable sound sensor 160 of the cochlear implant 112. At 650, the source selector 430 transmits the selected audio signal to the sound processing chain 440, and the sound processing chain 440 processes the audio signal as described above with respect to Figure 4 At 652, the sound processing chain 440 transmits the processed sound signal to the output 444 to deliver the stimulus to the recipient, thereby evoking the perception of the sound signal.

[0079] Figure 7 is a flow chart of an exemplary method 700 of training a signal analysis module according to certain embodiments presented herein. The method 700 may be performed at a hearing device system comprising a hearing device having an external component and an internal component. According to certain embodiments presented herein, the method 700 may optionally be performed at one or more remote devices in communication with the hearing device.

[0080] The method 700 begins at 710 when an external audio input is generated based on a sound signal captured by one or more external microphones. For example, the sound input device(s) 118 may capture a sound signal, and the external component 104 may generate the external audio input based on the sound signal. In some embodiments, generating the external audio input may include pre-processing the audio input (e.g., to remove noise, etc.).

[0081] At 720, the signal analysis module generates an implantable audio input based on the sound signal captured by the one or more implantable microphones. For example, the implantable sound sensor 160 can capture the sound signal, and the signal analysis module 362 can process the sound signal to generate the implantable audio input. In some embodiments, the signal analysis module 362 can remove noise, fill in frequency content, or process the sound signal captured by the implantable sound sensor 160 in a different manner.

[0082] At 730, the hearing system analyzes the implantable audio input relative to the external audio input. For example, the hearing system may determine a difference between the implantable audio input and the external audio input. At 740, the operation of the signal analysis module is adjusted based on the analysis of the implantable audio input relative to the external audio input. For example, new or updated weights / parameters may be determined for the signal analysis module based on the analysis of the implantable audio input relative to the external audio input. The new or updated weights / parameters may be used to update the training of the signal analysis module. The new or updated weights / parameters may be transmitted to the signal analysis module of the internal component for use when triggering the stealth mode for the hearing device.

[0083] Figure 8 8 is a flow chart of an exemplary method 800 for processing an implantable sound signal using a signal analysis module to generate an implantable audio input according to certain embodiments presented herein. At 810, the signal analysis module receives an implantable sound signal captured by one or more implantable microphones (e.g., of a hearing device). The signal analysis module is trained to convert the implantable sound signal into a substantial / approximate match to an external audio input generated based on an external sound signal captured by one or more external microphones (e.g., of a hearing device). For example, the signal analysis module 362 may receive a sound signal captured by the implantable sound sensor 160.

[0084] At 820, the signal analysis module processes the implantable sound signal to generate an implantable audio input. At 830, the signal analysis module may output the implantable audio input to the recipient. For example, the signal analysis module 362 may output the implantable audio input to be processed by the sound processing chain 440 and used to deliver stimulation to the recipient to evoke perception of the sound signal.

[0085] As previously mentioned, the technology disclosed herein can be applied to any of a variety of situations and used with a variety of different devices. Fig. 9 An exemplary device that may benefit from the techniques disclosed herein is described in more detail in FIG. As described below, an adaptation system configuration reference may be used Fig. 9 For example, the techniques described herein can be used to configure a wearable medical device (e.g., Fig. 9 The technology disclosed herein can be applied to other medical devices, such as neurostimulators, pacemakers, defibrillators, sleep apnea management stimulators, epilepsy treatment stimulators, tinnitus management stimulators, and vestibular stimulation devices, as well as other medical devices that deliver stimulation to tissues. In addition, the technology described herein can also be applied to consumer devices. These different systems and devices can benefit from the technology described herein.

[0086] Fig. 9 An exemplary vestibular stimulator system 902 is shown, which can be used to implement the embodiments presented herein. As shown, the vestibular stimulator system 902 includes an implantable component (vestibular stimulator) 912 and an external device / component 904 (e.g., an external processing device, a battery charger, a remote control, etc.). The external device 1004 includes a transceiver unit 960 and an external sensor 961. In this way, the external device 904 is configured to transmit data (and possible power) to the vestibular stimulator 912.

[0087] The vestibular stimulator 912 includes an implant body (main module) 934, a lead region 936, and a stimulation assembly 916, all configured to be implanted beneath the skin / tissue (tissue) 915 of a recipient. The implant body 934 generally includes a hermetically sealed housing 938 in which are disposed an RF interface circuit system, one or more rechargeable batteries, one or more processors, a stimulator unit, and an implantable sensor 963. The implant body 934 also includes an internal / implantable coil 914, which is generally external to the housing 938 but connected to the transceiver via a hermetic feedthrough (not shown).

[0088] The stimulation assembly 916 includes a plurality of electrodes 944(1)-(3) disposed in a carrier member (e.g., a flexible silicone body). In this particular example, the stimulation assembly 916 includes three (3) stimulation electrodes, referred to as stimulation electrodes 944(1), 944(2), and 944(3). The stimulation electrodes 944(1), 944(2), and 944(3) serve as an electrical interface for delivering electrical stimulation signals to the vestibular system of a recipient.

[0089] The stimulation assembly 916 is configured so that a surgeon can implant the stimulation assembly near the recipient's otolith organ via, for example, the recipient's oval window. It should be appreciated that this particular embodiment with three stimulation electrodes is merely illustrative, and the techniques presented herein can be used with stimulation assemblies with different numbers of stimulation electrodes, stimulation assemblies with different lengths, etc.

[0090] In operation, the vestibular stimulator 912, the external device 904, and / or another external device can be configured to implement the techniques presented herein. That is, the vestibular stimulator 912 (possibly in combination with the external device 904 and / or another external device) can include a signal analysis module, as described elsewhere herein, which can be used to substantially match the signal output by the implantable sensor with the signal of the external sensor (e.g., to approximately match the response of the implantable sensor 963 within the vestibular stimulator 912 with the response of the external sensor 961 of the external device 904).

[0091] It should be understood that although specific uses of the present technology have been illustrated and discussed above, the disclosed technology can be used with various devices according to many examples of the present technology. The above discussion is not intended to indicate that the disclosed technology is only suitable for implementation in systems similar to those shown in the accompanying drawings. In general, additional configurations can be used to practice the processes and systems herein, and / or some aspects described can be excluded without departing from the processes and systems disclosed herein.

[0092] The present disclosure describes some aspects of the present invention technology with reference to the accompanying drawings, in which only some possible aspects are shown. However, other aspects may be embodied in many different forms and should not be construed as being limited to the aspects set forth herein. Instead, these aspects are provided to make the present disclosure detailed and complete and to fully convey the scope of possible aspects to those skilled in the art.

[0093] It should be understood that the various aspects (e.g., parts, components, etc.) described herein with respect to the figures are not intended to limit the systems and processes to the specific aspects described. Therefore, additional configurations can be used to practice the methods and systems herein, and / or some aspects described can be excluded without departing from the methods and systems disclosed herein.

[0094] According to certain aspects, a system and a non-transitory computer-readable storage medium are provided. The system is configured with hardware, and the hardware is configured to perform operations similar to the method of the present disclosure. One or more non-transitory computer-readable storage media include instructions, and the instructions, when executed by one or more processors, cause the one or more processors to perform operations similar to the method of the present disclosure.

[0095] Similarly, where steps of a process are disclosed, these steps are described for the purpose of illustrating the present methods and systems, and are not intended to limit the present disclosure to a particular sequence of steps. For example, the steps may be performed in a different order, two or more steps may be performed simultaneously, additional steps may be performed, and disclosed steps may be eliminated without departing from the present disclosure. Furthermore, the disclosed processes may be repeated.

[0096] Although specific aspects are described herein, the scope of the present technology is not limited to these specific aspects. Those skilled in the art will recognize other aspects or improvements within the scope of the present technology. Therefore, specific structures, actions or media are disclosed only as illustrative aspects. The scope of the present technology is limited by the following claims and any equivalents therein.

[0097] It should also be understood that the embodiments presented herein are not mutually exclusive and that various embodiments can be combined with another embodiment in any of a variety of different ways.

Claims

1. A method comprising: generating external audio input based on sound signals captured by one or more external microphones; generating, using a signal analysis module, an implantable audio input based on acoustic signals captured by one or more implantable microphones; analyzing the implantable audio input relative to the external audio input; as well as Operation of the signal analysis module is adjusted based on analyzing the implantable audio input relative to the external audio input.

2. The method of claim 1, wherein adjusting the operation of the signal analysis module comprises: Setting or updating weights associated with the signal analysis module.

3. The method according to claim 1, wherein the signal analysis module is a deep neural network.

4. The method of claim 1, wherein the signal analysis module is trained to process the sound signals captured by the one or more implantable microphones to substantially match the external audio input.

5. The method of claim 1, 2, 3 or 4, wherein analyzing the implantable audio input relative to the external audio input comprises calculating an error function.

6. The method according to claim 1, 2, 3 or 4, wherein the method is performed at a device external to the hearing device.

7. The method of claim 1, 2, 3 or 4, wherein the method is performed at an implantable device of a hearing device.

8. The method of claim 1, 2, 3 or 4, wherein the method is performed at a remote device in communication with the hearing device.

9. The method of claim 1, 2, 3, or 4, wherein generating the external audio input comprises one or more of: performing noise reduction, removing a noise floor, or adjusting microphone directionality associated with the sound signals captured by one or more external microphones.

10. The method of claim 1, 2, 3 or 4, wherein generating the implantable audio input comprises removing noise not present in the external audio input from the sound signals captured by one or more implantable microphones.

11. The method of claim 1, 2, 3 or 4, wherein generating the implantable audio input comprises substantially matching a frequency response associated with the external audio input.

12. The method of claim 1, 2, 3 or 4, wherein generating the implantable audio input comprises filling in missing frequency content in the sound signal captured by one or more implantable microphones.

13. The method of claim 1, 2, 3 or 4, further comprising determining that the hearing device is in a training mode.

14. A medical device comprising: one or more external sensors; one or more implantable sensors; Signal analysis module; as well as one or more processors, wherein the one or more processors are configured to: generating an external signal input based on signals captured by the one or more external sensors; generating, by the signal analysis module, an implantable signal input based on signals captured by the one or more implantable sensors; analyzing the implantable signal input relative to the external signal input; as well as Operation of the signal analysis module is adjusted based on analyzing the implantable signal input relative to the external signal input.

15. The medical device according to claim 14, wherein: When adjusting the operation of the signal analysis module, the one or more processors are further configured to: Setting or updating weights associated with the signal analysis module. The medical device according to claim 14 , wherein the signal analysis module is a deep neural network.

17. The medical device of claim 14, 15 or 16, wherein the signal analysis module is trained to process the signals captured by the one or more implantable sensors to substantially match the external signal input.

18. The medical device according to claim 14, 15 or 16, wherein: The one or more processors are further configured to calculate an error function when analyzing the implantable signal input relative to the external signal input.

19. The medical device according to claim 14, 15 or 16, wherein: When the external signal input is generated, the one or more processors are further configured to: Noise reduction is performed to remove the noise floor or to adjust microphone directionality associated with the signal captured by one or more external sensors.

20. The medical device of claim 14, 15 or 16, wherein: When generating the implantable signal input, the one or more processors are further configured to remove noise not present in the external signal input from the signal captured by the one or more implantable sensors.

21. The medical device according to claim 14, 15 or 16, wherein: When generating the implantable signal input, the one or more processors are further configured to substantially match a frequency response associated with the external signal input.

22. The medical device of claim 14, 15 or 16, wherein: When generating the implantable signal input, the one or more processors are further configured to fill in missing frequency content in the signal captured by one or more implantable sensors.

23. The medical device of claim 14, 15 or 16, wherein the one or more processors are further configured to determine that the medical device is in a training mode.

24. The medical device of claim 14, 15 or 16, wherein the one or more implantable sensors and the one or more external sensors comprise acoustic sensors.

25. One or more non-transitory computer-readable storage media comprising instructions that, when executed by a processor, cause the processor to: receiving, at a machine learning device, implantable sound signals captured by one or more implantable microphones of a hearing device, the machine learning device being trained to convert the implantable sound signals to substantially match external audio input generated based on external sound signals captured by one or more external microphones; processing the implantable sound signal by the machine learning device to generate an implantable audio input; as well as The implantable audio input is output to a recipient of the hearing device.

26. The one or more non-transitory computer-readable storage media of claim 25, wherein the machine learning device is a deep neural network.

27. One or more non-transitory computer-readable storage media according to claim 25 or 26, wherein: When processing the implantable sound signal, the processor is further configured to remove noise from the implantable sound signal that is not present in the external audio input.

28. One or more non-transitory computer-readable storage media according to claim 25 or 26, wherein: When processing the implantable sound signal, the processor is further configured to substantially match a frequency response associated with the external audio input.

29. One or more non-transitory computer-readable storage media according to claim 25 or 26, wherein: When processing the implantable sound signal, the processor is further configured to fill in missing frequency content in the implantable sound signal.

Images