Dynamic list-based voice testing

By dynamically generating a vocabulary list of speech balance and perceptual balance, the existing speech auditory test equipment is solved, and the problem of expensive and poor subject experience is realized, flexible and convenient speech auditory tests are carried out at home, and the usability of the test is improved and accuracy.

CN119072743APending Publication Date: 2024-12-03COCHLEAR LIMITED
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380035957.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-04-27
Filing Date
2023-04-26
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing voice audition testing equipment is expensive and requires professional equipment and personnel operation. The subject experience is poor and it is difficult to conduct effective voice testing at home, which lacks flexibility and convenience.

Method used

By dynamically generating a vocabulary list with speech balance and perceptual balance, using search algorithms to generate a test vocabulary suitable for specific subjects, and providing voice tests in combination with computing devices, allowing speech auditory tests at home, reducing professional equipment and Reliance of personnel.

Benefits of technology

It realizes reliable voice audition testing at home, reduces testing costs and complexity, provides flexible and convenient testing methods, enables repeated testing without worrying about the risk of learning effects, and enhances the usability and accuracy of testing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119072743A_ABST
    Figure CN119072743A_ABST
Patent Text Reader

Abstract

Techniques are presented herein to dynamically generate test material to perform voice testing on a user, such as a hearing aid user or a cochlear implant. Dynamic vocabulary list generation techniques are disclosed. These techniques generate a list of vocabularies having a quality intended to implement a particular voice test. For example, the disclosed techniques may be used to generate a list of vocabularies with a predetermined voice balance and / or perceptual balance. The disclosed techniques also provide for generation of audio signals associated with a list of vocabularies used during voice testing.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] background Technical Field

[0002] The present invention relates generally to speech testing. Background Art

[0003] Medical devices have provided a wide range of therapeutic benefits to recipients / users over recent 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 for many years in performing life-saving and / or lifestyle improvement 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 some aspects, the technology described herein relates to a method that includes compiling a vocabulary pool, dynamically generating a subset of the vocabulary pool having a predetermined phonetic balance from the vocabulary pool, and performing a speech test on a subject using the subset of the vocabulary pool.

[0006] In other aspects, the technology described herein is directed to a method that includes compiling data indicative of a vocabulary pool having a predetermined speech distribution. Applying a search algorithm to the data indicative of the vocabulary pool to generate data indicative of a subset of the vocabulary pool such that the speech distribution of the subset of the vocabulary pool is within the bounds of the predetermined speech distribution. Generating a test vocabulary set for a speech test for a subject from the data indicative of the subset of the vocabulary pool.

[0007] In still other aspects, the technology described herein relates to a method comprising compiling data indicating a vocabulary pool having a predetermined speech distribution. Applying a search algorithm to the data indicating the vocabulary pool to generate data indicating a subset of the vocabulary pool such that the speech distribution of the subset of the vocabulary pool is within the bounds of the predetermined speech distribution. Generating an audio signal for each word in the vocabulary subset for presentation to the subject in a speech test for the subject such that the audio signal presented to the subject during the speech test is perceptually balanced. 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 It is wearable Figure 1A A side view of a user 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 1D yes Figure 1A Block diagram of a cochlear implant system;

[0013] Figure 2 is a flow chart illustrating a particular exemplary embodiment of a process flow for generating a dynamic vocabulary list for use in speech testing;

[0014] Figure 3 is a flow chart illustrating a general process flow for generating a dynamic vocabulary list for use in speech testing;

[0015] Figure 4 is a first user interface including dynamically generated possible answers presented to a subject during a speech test;

[0016] Figure 5 is a second user interface including dynamically generated possible answers presented to the subject during the speech test;

[0017] Figure 6 is a flow chart showing a general process for performing speech testing on a subject;

[0018] Figure 7 A cochlear implant fitting system is shown with which aspects of the technology presented herein may be implemented; and

[0019] Figure 8is a schematic diagram illustrating an implantable stimulation system to which aspects of the technology presented herein may be applied. DETAILED DESCRIPTION

[0020] Presented herein are techniques for dynamically generating test materials to administer speech tests to, for example, hearing device users (e.g., users of hearing aids, cochlear implants, etc.). Specifically, dynamic vocabulary list generation techniques are disclosed, in which a vocabulary list having specific properties that are optimally suited for implementing a specific speech test is generated. For example, the disclosed techniques can be used to generate a vocabulary list having a predetermined phonetic balance and / or perceptual balance. The disclosed techniques also provide for the generation of an audio signal associated with the vocabulary list used during the speech test. For example, an audio signal having a specific volume level, signal-to-noise ratio, or speaker characteristics (e.g., identity, gender, pitch, timbre, speed of articulation, etc.) can be generated. Finally, the disclosed techniques also provide a dynamically generated user interface to implement the speech test.

[0021] 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 a dedicated tinnitus treatment device and a tinnitus treatment device system. In other embodiments, the technology presented herein can also be implemented by a vestibular device (e.g., a vestibular implant), a visual device (i.e., a bionic eye), a sensor, a pacemaker, a drug delivery system, a defibrillator, a functional electrical stimulation device, a catheter, an epileptic seizure device (e.g., a device for monitoring and / or treating epileptic events), a sleep apnea device, an electroporation device, etc., or used in combination with them.

[0022] Figures 1A-1D An exemplary cochlear implant system 102 is shown with which aspects of the technology presented herein may be implemented. The cochlear implant system 102 includes an external component 104 / implantable component 112. Figures 1A-1D In the example of a cochlear implant, the implantable component is sometimes referred to as a "cochlear implant." Figure 1A A cochlear implant 112 is shown implanted in a user's head 154, and Figure 1B is a schematic diagram of the external component 104 worn on the head 154 of the user. Figure 1C is another schematic diagram of a cochlear implant system 102, and Figure 1D Further details of cochlear implant system 102 are shown. For ease of description, the Figures 1A-1D.

[0023] Cochlear implant system 102 includes an external component 104 configured to be attached directly or indirectly to a user's body, and an implantable component 112 configured to be implanted in the user's body. Figures 1A-1D In the example of FIG. 1 , external component 104 includes a sound processing unit 106 and 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 ​​a user.

[0024] exist Figures 1A-1D In the example of the present invention, the sound processing unit 106 is an outside-the-ear (OTE) sound processing unit, sometimes referred to herein as an OTE component, which 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 user's head (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.

[0025] It should be appreciated 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 may include a behind-the-ear (BTE) sound processing unit or a micro-BTE sound processing unit and a separate external component. Generally speaking, the BTE sound processing unit includes a housing that is shaped to be worn on the outer ear of the user and is 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 also be appreciated that alternative external components can be located in the ear canal of the user, worn on the body, etc.

[0026] 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 user. 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 user. 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 user. 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 references to the external hearing mode and the invisible hearing mode are merely illustrative, and cochlear implant 112 may also operate in alternative modes.

[0027] exist Figure 1A and 1C In the present invention, a cochlear implant system 102 is shown as having an external device 110, which is configured to implement various aspects of the technology presented. The external device 110 is a computing device, such as a computer (e.g., a laptop computer, a desktop computer, a tablet computer), a mobile phone, a remote control unit, etc. As further described below, the external device 110 includes a speech test module, as further described below, which is configured to implement various aspects of the speech test technology presented herein. According to the technology presented herein, the external device 110 can be used to provide a speech test to a user. Specifically, a speaker associated with the external device 110 can be used to play an audio signal associated with a vocabulary list dynamically generated to meet the expected goals of the speech test. The display of the external device 110 displays possible answers for the vocabulary that can correspond to the vocabulary contained in the audio signal. Then, the user selects an appropriate answer from the possible answers by user input to the external device 110. The external device 110 and the cochlear implant system 102 (e.g., the OTE sound processing unit 106 or the cochlear implant 112) communicate wirelessly via a two-way communication link 126. The bidirectional communication link 126 may include, for example, short-range communications such as a Bluetooth link, a Bluetooth Low Energy (BLE) link, a proprietary link, or the like.

[0028] External device 110 may also be configured to communicate externally via, for example, a connection to the Internet. This connection allows external device 110 to transmit the results of the speech test to an external entity, such as a clinician and / or an audio prosthesis provider. These entities may use the results of the speech test to customize treatment for a particular user, better tune cochlear implant system 102 for the user (as described below with reference to Figure 7 The debugging system described herein is used as a basis for additional research and improvement of audio prosthesis technology, as well as for other uses.

[0029] Return to Figures 1A-1D In 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).

[0030] The OTE sound processing unit 106 also includes an external coil 108, a charging coil 121, 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.

[0031] 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 user's skin / tissue (tissue) 115. 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 1D ) is connected to the RF interface circuit system 140.

[0032] As mentioned, the stimulation assembly 116 is configured to be at least partially implanted in the cochlea of ​​the user. 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 user.

[0033] The stimulation assembly 116 extends through an opening in the user's cochlea (e.g., a cochleostomy, a round window, etc.) and has a lead region 136 and an airtight feedthrough ( Figure 1D The implantable component 112 also includes an electrode 144 (not shown) 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.

[0034] 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 tightly coupled wireless link 148 formed between the external coil 108 and the implantable coil 114. In some examples, the tightly 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 1D Only one exemplary arrangement is shown.

[0035] 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 received input signals (received at one or more of the input devices) into output signals for stimulating the first ear of the user (i.e., the external sound processing module 124 is configured to perform sound processing on the input signals 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 signals into output signals representing electrical stimulation for delivery to the user.

[0036] As mentioned above, Figure 1D An embodiment is shown in which an external sound processing module 124 in the sound processing unit 106 generates an output signal. In an alternative embodiment, 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.

[0037] Return to Figure 1D In 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 use the output signal to generate an electrical stimulation signal (e.g., a current signal) for delivery to the cochlea of ​​the user. In this way, the cochlear implant system 102 electrically stimulates the auditory nerve cells of the user, thereby bypassing the missing or defective hair cells that normally convert acoustic vibrations into neural activity in a manner that causes the user to perceive one or more components of the received sound signal.

[0038] As described 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 user's auditory nerve cells. Figure 1DAs 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.

[0039] 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 of the implantable sound sensors 160) into an output signal for stimulating the first ear of the user (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 user using the output signal 156, thereby bypassing the missing or defective hair cells that normally convert the acoustic vibrations into neural activity.

[0040] 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 cochlear implant system 102 may operate differently in different embodiments. For example, in an alternative embodiment of the external hearing mode, cochlear implant 112 may use the signals captured by sound input device 118 and implantable sound sensor 160 to generate stimulation signals for delivery to the user.

[0041] A typical hearing device, such as a cochlear implant, has many settings or parameters that determine the sound processing operation of the device. The personalized programs, commands, data, settings, parameters, instructions, modes, and / or other information that define the specific characteristics of a hearing device (e.g., cochlear implant system 102) for processing electrical input signals and generating stimulation data therefrom are generally referred to collectively as "sound processing settings." These parameters are determined and set by a medical practitioner (clinician) in a process known as "tuning." As described below with reference to Figure 7As described in detail, the external device 110 may be configured to send data to the debugging system via, for example, a computer network, such as a wide area network (WAN) or a local area network (LAN) (see Figure 7 This allows the clinician to use online techniques to personalize the programs, commands, data, settings, parameters, instructions, modes and / or other information that define the specific characteristics used by cochlear implant system 102.

[0042] Determining parameter settings during the debugging process can be based on the results of specific tests on the user. These tests can be used to determine how well the user performs with their hearing implant. Unfortunately, the related technologies that rely on providing these tests generally only provide limited insights into how well the user performs with their medical device. For example, related technologies for measuring hearing results may be inconvenient without being incorporated into a medical device platform, resulting in the tests and test data being unavailable for further data analysis.

[0043] A more beneficial approach may be to provide one or more performance metrics that capture the essence of the treatment results delivered by the medical device. Unfortunately, in the field of hearing devices, such consistency measures may not be widely available. The closest proxy for these universal measurements may be speech audiometry. Speech audiometry refers to language dependency testing. The core test in speech audiometry presents a list of words in the absence of background noise and measures the test subject's basic speech understanding of the words. Speech audiometry is used to characterize the extent and nature of the test subject's hearing loss and to verify the treatment provided by a medical device (e.g., cochlear implant devices, hearing aids, and other solutions for restoring hearing).

[0044] Depending on the exact use case, testing can be performed in many variations:

[0045] Tests can vary in the word lists used. For example, the word list used to test adults may be different from the word list used to test children.

[0046] • Tests can vary by language (not only in the specific vocabulary used to test the subject, but also in the speech presented to the subject).

[0047] • Tests may vary in the amount of background noise accompanying the test audio.

[0048] The test can be performed on one or both ears of the subject.

[0049] The test may present the test audio via bone conduction, air conduction, or both.

[0050] The test audio may be presented to the subject through headphones with or without a hearing device.

[0051] Tests can be presented at different signal-to-noise ratios (SNR).

[0052] • Testing can be performed against a fixed speech recognition threshold (SRT) or the test can be adapted to explore the limits of the subject's SRT.

[0053] The test can be scored using different scoring techniques, such as vocabulary scoring or phonetic scoring techniques.

[0054] There are currently several major barriers preventing widespread adoption of short-word listening tests as a standard measure in hearing therapy. These barriers may include:

[0055] 1. Speech audiometry testing requires expensive equipment, such as soundproof booths and digital audiometers, which are usually only available in dedicated centers.

[0056] 2. Classical speech audiometry requires a professional (i.e., an audiologist) who is trained to supervise speech audiometry tests. Moreover, the test subject experience is poor. Taking the test is painful and unpleasant: like a school test that the test subject may fail.

[0057] 3. Speech audiometry requires specialized speech materials. For clinical diagnostic purposes, official speech lists have been carefully developed according to international standards, such as the International Organization for Standardization (ISO) standard 8253. Meeting these standards may involve validation studies that establish the diagnostic validation of specific test materials. There are only a few official speech audiometry lists for any given language. Excessive use of these materials outside of diagnostic scenarios can be harmful because there is a risk that the subject will learn the contents of the list, biasing future hearing assessments. Therefore, these official speech materials should be reserved for clinical assessment of subjects.

[0058] Therefore, clinical speech audiometry testing can be expensive, and its use of expensive and specialized equipment can be problematic. For example, in clinical speech audiometry, an audiologist controls an expensive audiometer in a shielded soundproof room in a specialized hearing center, delivering official speech audiometry materials through a calibrated receiver. Use of this equipment may require long distances to the clinic, and is limited by the availability of professionals. Due to the limited availability of these speech audiometry tests, and because the results of these tests are maintained in the medical record system of the speech audiometry professional, the results of these tests may not be available to the personnel who develop and debug hearing devices.

[0059] In addition, although the above clinical settings meet an important need when high accuracy is needed to make influential professional medical decisions, this is not always strictly necessary. For example, the speech audiometry test results used by the cochlear implant automatic adjustment system only need to be reliable enough to better correlate with the clinic test. Moreover, classical speech audiometry is not an accurate measure of the systematic errors produced by specific users of hearing devices. Classical speech audiometry provides an average vocabulary score that can be used for clinical verification and validation, but does not provide detailed and accurate information about which specific errors are produced by specific subjects. Therefore, classical speech audiometry may not always be particularly useful to drive additional device adjustment changes or the next set of listening experiences in a personalized hearing training program. For these purposes, the list must be longer, which is impossible in clinical scenarios.

[0060] Moreover, the experience during traditional speech audiometry may be painful for the subject. For example, some subjects may deal with speech audiometry in an adversarial manner, as an exam rather than as an assessment, which may affect the results of the assessment. In speech audiometry, the hearing test is usually difficult when exploring the boundaries of the test subject's hearing. The subject may feel labored with these boundaries, and because the subject is encouraged to constantly report any speech fragments they have understood, the subject may guess or bet on the correct response. Moreover, personality may affect the assessment, especially for subjects who are easily embarrassed by understanding too little. These types of feelings and anxieties may cause the subject to be reluctant to express what they think they understand.

[0061] Another challenge brought by speech audiometry is that in each language, the official clinical materials are unique and very valuable. Official speech audiometry materials are developed very carefully, and the vocabulary is perfectly balanced in both phonetics and perception. At least according to ISO 8253, both phonetic balance and perceptual balance may be required for effective speech audiometry materials. Phonetic balance refers to the phonetic distribution of the vocabulary list. The phonetically balanced vocabulary lists in the corpus are usually the same and correspond to the statistics of the language. Perceptual balance refers to the equivalence of the list with other lists regarding the degree to which the test participant can perceive the test material. It should be irrelevant whether list A or list B is used to test the speech comprehension of the subject. Perceptual balance ensures that the test gives the same hearing estimate regardless of the vocabulary list used. Meeting these phonetic balance and perceptual balance goals may require a painstaking and slow process of carefully selecting and compiling speech materials and conducting multiple validation studies on young adults with normal hearing. Therefore, it is problematic to reuse official speech audiometry materials for home testing. Usually, only a few lists have not too many vocabularies (for example, in Dutch, 15 lists contain 11 vocabularies). Repeatedly presenting these words in home testing would create a risk of memorizing these lists, resulting in bias on official speech audiometry tests in the clinic. For home testing, the ideal test could be repeated indefinitely without the risk of learning effects due to memorizing the word lists.

[0062] Overcoming these challenges can provide substantial benefits to hearing device users. For example, overcoming these challenges can allow for home speech audiometry, which allows a subject (e.g., a user of a hearing device, such as a cochlear implant user) to perform speech testing in their home environment. Moreover, the results of the home test may have validity for many relevant clinical questions (e.g., tracking performance). For example, the test results can reflect how well an individual performs in terms of their hearing performance, without necessarily being exactly equivalent to the high standards required for clinic testing. Most adult users are eager to improve their hearing with a new device, certainly in the first few weeks and months after implantation. They are highly motivated to reach their hearing potential and may appreciate the ability to perform listening games and hearing tests.

[0063] Furthermore, readily available home speech audiometry could spur substantial innovation. For example, if more robust datasets were more readily available, innovation in the areas of hearing devices and hearing device fitting systems could be possible. For example, more robust and available speech audiometry datasets could facilitate the development of closed-loop AI fitting systems based on speech audiometry results. Other possible innovations could include the development of unbiased and trustworthy outcome prediction models.

[0064] In order to provide robust home speech audiometry, the disclosed techniques enable the development of specialized language materials (e.g., speech balance and perceptual balance vocabulary lists) in addition to clinic speech audiometry materials. In other words, the disclosed techniques provide for the development of specialized language materials (e.g., speech balance and perceptual balance vocabulary lists) that can be used outside of a clinical setting, such as in a subject's home, via a computing device (e.g., Figures 1A-1D The external device 110) repeatedly performs the speech audiometry material.

[0065] Thus, the techniques of the present disclosure may provide one or more of the following benefits:

[0066] Dynamic speech lists that allow repeated speech audiometry testing without the risk of learning effects;

[0067] A voice-balanced voice list;

[0068] A perceptually balanced list of voices;

[0069] Low development effort to develop test materials for each language;

[0070] A phonological list consisting of a limited test corpus, containing no more than + / -1000 short words;

[0071] Eliminates the need for a grapheme-to-phonetic (g2p) component for each language. This component requires considerable work to transcribe open set answers or vocabulary segments and is not readily available on the open market. Depending on the difficulty of the spelling of a particular language, this can be a significant barrier and cost;

[0072] Elimination of extensive validation studies; and

[0073] Immediate feedback that can be used to motivate subjects to continue with testing and rehabilitation procedures.

[0074] One aspect of the technology presented herein is to generate a "dynamic" list of speech test material. The dynamic list is generated by a processing device, such as Figures 1A-1D The dynamic lists are randomly generated by a computer of an external device 110. The words in the dynamic lists are selected from the vocabulary pool to have properties that meet the goals of certain tests (speech and / or perceptual balance). These dynamic lists are then used to perform, for example, a home speech audiometry exam. The use of such a home test can provide an accurate screening for inadequate performance of a hearing prosthesis or a characterization of the degree of overall hearing loss. Moreover, because the test is performed on the subject's computing device (e.g., Figures 1A-1D The test can be performed periodically by an application running on an external device 110. In addition, the test can be incorporated into a game, or positive feedback about the subject's progress can be provided to help motivate the subject to perform the test. For example, the application can set goals, or provide rewards to the subject in response to performing a specific test.

[0075] Finally, allowing subjects to perform home tests will greatly increase the amount of data available for evaluating error patterns specific to specific subjects. For example, it is suspected that subjects make systematic errors in the speech they misidentify that may not be very obvious from the clinic speech test. Therefore, two subjects who score the same 60% in the clinic speech audiometry test may actually make very different errors, and the difference between these errors may not be very obvious from the several clinic errors that the subjects usually make. Knowing the difference between these errors can allow two subjects to more appropriately debug their hearing devices for their respective hearing defects. At present, there is simply not enough easily available data to determine how two subjects who score the same in the speech audiometry test are systematically different. Allowing subjects to perform speech audiometry tests regularly in a home environment can generate a sufficient amount of data, which provides greater accuracy in estimating the personalized error pattern of a specific subject. Once a specific error pattern is identified, an optimized audiogram can be provided to the subject or specialized rehabilitation training can be provided to help the subject distinguish similar sounds.

[0076] The first step of generating the dynamic vocabulary list of the technology disclosed in this disclosure is to determine the composition of the vocabulary pool.The content of the vocabulary pool should all have very similar phonetic structures, for example, auxiliary-vowel-auxiliary (CVC) structure, and should be the well-known vocabulary of the test language, so that they are very familiar to most subjects.The audio recording of the high-quality natural sample of the vocabulary in the vocabulary pool should be provided, for example, the high-quality recording spoken by the standard pronunciation of each vocabulary by a professional speaker.According to other embodiments, speech synthesis technology (for example, text-to-speech technology) can be used to generate the high-quality computer voice audio data of the vocabulary in the vocabulary pool.The use of speech synthesis technology can reduce the cost and time required for obtaining high-quality audio data.The use of speech synthesis technology can have additional benefits, for example, standardizing speaker characteristics (identity, gender, tone, timbre, pronunciation speed and other characteristics known to those skilled in the art) between various languages.This standardization can produce more consistent scores between various languages.

[0077] Once the vocabulary pool is populated, an algorithm can be used to generate a vocabulary list as a subset of the vocabulary pool. If a phonetically balanced vocabulary list is required for a specific test, the algorithm tracks the average phonetic distribution of the vocabulary pool. When selecting vocabulary to form a new list, the algorithm strives to match this phonetic distribution. For example, the algorithm can randomly select a first vocabulary to use for the list. For subsequent vocabulary, the algorithm can search different vocabulary in the vocabulary pool in a random manner to bridge the phonetic distribution gap. According to a specific embodiment, the algorithm selects a random vocabulary to add to the list. If the selected vocabulary makes the phonetic distribution closer to the known average phonetic distribution of the vocabulary pool, the selected vocabulary is added to the vocabulary list. On the other hand, if the selected vocabulary forces the phonetic distribution of the list away from the average phonetic distribution of the vocabulary pool, the vocabulary is discarded. This process is repeated until a vocabulary list is generated with, for example, a predetermined number of vocabulary and an average phonetic distribution within the bounds of the average phonetic distribution of the vocabulary list.

[0078] Reference now Figure 2 , wherein a flowchart 200 is depicted, which illustrates an exemplary search algorithm configured to implement the dynamic speech audiometry test vocabulary list generation technique of the present disclosure. Flowchart 200 begins at operation 205, where a random vocabulary is selected from a vocabulary pool and the random vocabulary is added to the vocabulary list. In operation 210, another vocabulary is randomly selected from the vocabulary pool. If it is determined in operation 215 that the currently selected vocabulary causes the speech distribution of the vocabulary list to be closer to the target value, then in operation 220, the vocabulary is added to the vocabulary list. On the other hand, if it is determined that the currently selected vocabulary drives the speech distribution of the vocabulary list further away from the target value, then in operation 225, the vocabulary is discarded and the process flow returns to operation 210.

[0079] The target speech distribution discussed in operation 215 may be an average speech distribution of the vocabulary pool, or it may be another speech distribution. For example, the target speech distribution may be selected so that the vocabulary list generated by flowchart 200 is configured to test specific features of the subject's hearing.

[0080] Returning to operation 220, after the currently selected word is added to the vocabulary list, it is determined whether the speech distribution is within the bounds of the target value in operation 230. If the speech distribution is not yet within the bounds of the target value, the process of flowchart 200 returns to operation 210 and another word is randomly selected from the vocabulary pool.

[0081] On the other hand, if the speech distribution is within the bounds of the target value, the process flow of flowchart 200 proceeds to operation 235. Operation 235 determines whether the vocabulary list is large enough to implement the intended speech audiometry test. If the vocabulary list is not large enough, the processing of the flowchart returns to operation 210 and another vocabulary is randomly selected from the vocabulary pool. If the vocabulary list is large enough, the processing of flowchart 200 proceeds to operation 240 and the search algorithm is completed.

[0082] Thus, flow chart 200 provides a process flow in which operations 210-235 are repeated until a vocabulary list of sufficient size is generated that has a speech distribution within bounds of a target value.The vocabulary list itself can be used to conduct speech audiometry testing.

[0083] Flowchart 200 is only one example of how the vocabulary selected to be included in the test vocabulary list can be determined. According to another example, after randomly selecting a first vocabulary to be included in the test vocabulary list, the remaining vocabulary in the vocabulary pool can be scored to determine to what extent each vocabulary will drive the speech distribution of the test vocabulary list toward the target speech distribution. The next vocabulary with the best score can be randomly selected from the vocabulary to be included in the test vocabulary list. This process will then be repeated until the test vocabulary list is filled with a speech distribution within the limits of the target speech distribution and a sufficient number of vocabulary. For example, after selecting a second vocabulary, the remaining vocabulary in the vocabulary pool will be scored again, but this time based on the speech distribution provided by the first vocabulary and the second vocabulary. Then, a third vocabulary with the best score is randomly selected from the vocabulary. Then, this process is repeated as needed to fill a test vocabulary list of sufficient size.

[0084] The above search algorithm and other algorithms known to those skilled in the art can be embodied as an artificial intelligence (AI) element based on a phonetic distribution table, such as a machine learning algorithm or model. The use of this AI element can ensure that the dynamic vocabulary list is phonetically balanced.

[0085] In addition to the speech balance vocabulary selection techniques described above, the technology of the present disclosure also provides for generating a perceptually balanced vocabulary list. The perceptual balance of a vocabulary list can vary with the specific vocabulary in the list and the quality of the audio recording associated with the vocabulary. For example, certain common vocabulary can be easily perceived based on its popularity in a particular language. Perceptual balance may also be affected by the volume of the audio signal associated with the vocabulary and the SNR in the audio signal associated with the vocabulary. Therefore, when dynamically generating a vocabulary list for a speech audiometry test, the perceptual balance of the vocabulary list may also be a consideration. For example, when selecting vocabulary from a vocabulary pool to be included in a vocabulary list, the popularity of the vocabulary in the language may be a criterion considered when determining whether to include the vocabulary in the vocabulary list. Similarly, the quality of the audio recording associated with the vocabulary may also be considered. For example, when selecting vocabulary to be included in a dynamic vocabulary list, the SNR of the audio recording associated with the vocabulary may be evaluated to ensure the perceptual balance of the vocabulary list. For example, when selecting vocabulary to be included in a dynamic vocabulary list, the volume setting of the audio signal associated with the vocabulary may also be set to ensure the perceptual balance of the vocabulary list. The technology of the present disclosure may utilize a computer model configured to predict the intelligibility of pronunciation. Such a computer model can assign a speech intelligence index or a speech intelligibility index to the pronunciation. Based on such index values, the perceptual balance of the test vocabulary list can be determined so that the final test vocabulary list has a perceptual balance within predetermined limits of the target perceptual balance value.

[0086] Reference now Figure 3 , wherein a flowchart 300 is depicted, which illustrates a general process flow for implementing the dynamic vocabulary list generation technique of the present disclosure.

[0087] Flowchart 300 begins at operation 305, where a vocabulary pool is obtained (e.g., generated, compiled, received, etc.). For example, operation 305 may include compiling a vocabulary pool having a predetermined speech distribution. The vocabulary pool may also be compiled such that a predetermined number of words within the vocabulary pool have similar speech structures, such as CVC structures.

[0088] In operation 310, a subset of the vocabulary pool having a predetermined speech balance is dynamically generated from the vocabulary pool. For example, operation 310 may be embodied as using a search algorithm (e.g., Figure 2 Because operation 310 may be embodied as a computer-implemented method, operation 310 may include the following operations: applying a search algorithm to data indicative of a vocabulary pool to generate data indicative of a subset of the vocabulary pool such that the speech distribution of the subset of the vocabulary pool is within the bounds of a predetermined speech distribution, and then generating a test vocabulary set for a speech test for the subject from the data indicative of a list of vocabulary pools.

[0089] Finally, in operation 315, a speech test is performed using a subset of the vocabulary pool. For example, a speech audiometry test can be performed using a subset of the vocabulary pool. Operation 315 can include generating an audio signal for each vocabulary in the vocabulary subset in the speech test to be presented to the subject. The audio signal presented to the subject during the speech test can be perceptually balanced. For example, the audio signal presented to the subject can be presented at different volume levels so that the overall test is perceptually balanced. The audio signal presented to the subject can also be presented at different background noise levels or at different SNRs to ensure a perceptually balanced test. The volume, background noise, and / or SNR levels can be pre-existing features of the audio signal presented during the speech test, or these features can be dynamically set during the speech test. Similarly, the audio signal itself can be pre-existing, such as a pre-existing audio recording or a pre-existing audio data file generated using speech synthesis technology. Alternatively, the audio signal can be dynamically generated using speech synthesis technology during the presentation of the speech test.

[0090] If through Figure 3 As indicated by operation 315 of flowchart 300, the disclosed technology includes performing a speech test using a dynamically generated vocabulary list. The disclosed technology can implement such a speech test using a test answer dynamically generated based on a subset of a vocabulary pool. Next, a user interface can be generated to implement the speech test by presenting the test answer to the subject as part of the speech test.

[0091] Reference now Figure 4 , which depicts a user interface 400 that can be dynamically generated according to the techniques of the present disclosure to perform a speech test. The user interface 400 can be displayed on a computing device associated with a subject (e.g., Figures 1A-1D The application may present the audio signal to the subject through a speaker connected to the computing device (e.g., an internal speaker of the computing device, a wired or wireless headset connected to the computing device, etc.), while presenting the user interface 400 to the subject through a display of the computing device.

[0092] The user interface 400 includes a limited number of possible answers 405a-d that the subject can indicate as corresponding to the audio signal played as part of the voice test. Therefore, the subject will hear an audio signal of a vocabulary from the vocabulary of the dynamically generated vocabulary list. Then, the subject will select a possible answer in the possible answers 405a-d that the subject believes corresponds to the audio signal. Each possible answer in the possible answers 405a-d includes an associated response value 410a-d, respectively, and the subject can enter the associated response value through a user input device, and examples of user input devices include keyboards and numeric keypads. Although four possible answers 405a-d are displayed in the user interface 400, other embodiments can provide more or less responses to the subject. For example, a traditional numeric keypad has values ​​"0" to "9", thereby providing input of up to ten possible answers. According to other examples, the subject can select a possible answer in the possible answers 405a-d using a computer mouse, a stylus, or a touch screen function of a screen on which the possible answers 405a-d are displayed. Once the subject has entered an answer, the user interface 400 may be updated with a new set of possible answers 405a-d, and the subject will be presented with a new audio signal corresponding to another word from the dynamically generated word list.

[0093] The user interface 400 may be different from the way related art speech audiometry tests are performed in clinical scenarios. In a clinical setting, "open set recognition" may be used. Specifically, in a clinical speech audiometry test, possible answers are not presented to the subject. Instead, a keyboard may be provided to the subject, through which the subject can type any vocabulary they think they hear as part of the test. Because the subject can enter any vocabulary, the set of possible answers is "open". On the other hand, the user interface 400 presents a limited number of possibilities to the subject. The subject selects the vocabulary that he thinks is the correct vocabulary from the possible answers 405a-d. Therefore, while the clinical speech audiometry test may use open set recognition, the user interface 400 provides a closed set option.

[0094] However, the closed set technique of the present disclosure can be implemented so that the results of the test are substantially equivalent to the open set technique. For example, if a subject is presented with nine possible answer options, the probability that the subject will randomly select the correct answer is only 11%. This low probability may be sufficient to achieve close equivalence with the open set recognition technique. Moreover, the number of possible answers 405a-d can be selected so as to provide a speech audiometry test that is equivalent to an open set test within a predetermined error threshold.

[0095] The technology of the present disclosure also includes the technology for determining which values ​​should be presented to the subject as possible answers 405a-d. Possible answers 405a-d can be selected so that they dynamically adapt interference factors to the vocabulary presented to the subject by audio signals. For example, if the proposed speech audiometry test is intended to be relatively easy, possible answers 405a-d can be selected so that incorrect answers are very different from correct answers in voice. If the intention is to make the test more challenging, possible answers 405a-d can be selected so that incorrect answers are only different from correct answers in a single voice. In other words, possible answers 405a-d can be selected according to the average voice distance of the vocabulary with the correct answer. Therefore, possible answers 405a-d can be selected so that the test results of the closed set technology using user interface 400 achieve the results equivalent to the open set test of the relevant technology clinic.

[0096] Other embodiments may be directed toward optimizing incorrect possible answers toward the goal of estimating the subject's speech discrimination, estimating a speech confusion matrix, and / or identifying the speech pairs most commonly confused by the subject. Thus, possible answers 405a-d may be selected so that the results of the speech audiometry test provide a reliable estimate of the subject's discrimination ability at the speech level.

[0097] The closed set technology of user interface 400 can also eliminate the need for testing g2p components. Because the subject may only select from the options displayed on the screen, all possible responses are already known in advance. These responses can belong to the second response vocabulary pool, which can be a super set of the vocabulary pool from which the dynamic vocabulary list was generated. Therefore, there can only be substitution errors. The technology of the present disclosure also allows the inclusion of "I don't know (IDo Not Know)" or "None of the Above" options in possible answers 405a-d. By including these options, the speech audiometry test provided by user interface 400 can test for whole vocabulary deletion errors.

[0098] The disclosed techniques may also be adapted to facilitate speech audiometry testing for children or people with reading difficulties, such as Figure 5 The user interface 500 is similar to Figure 4 The user interface 500 is similar to the user interface 400 of FIG. 5 , but differs in that the possible answers 505a-d are presented as images. Thus, the user interface 500 can be used to provide speech audiometry testing to subjects with reading difficulties and / or subjects who have not yet learned to read. In other words, subjects who cannot read Figure 4 A subject who is aware of possible answers 405a-d may identify images of possible answers 505a-d, thereby allowing the subject to select the correct associated response value 510a-d.

[0099] Now turn to Figure 6, wherein a flowchart 600 is depicted, which provides a process flow for implementing the speech audiometry testing technology of the present disclosure. Flowchart 600 begins at operation 605, where an audio signal of a vocabulary of a subset of the vocabulary pool is played for the subject. Thus, operation 605 can be embodied as playing a dynamically generated vocabulary list (e.g., as described above with respect to Figure 2 and 3 Operation 605 may also be embodied as generating an audio signal by speech synthesis technology and then presenting the audio signal to the subject. Presenting the audio signal to the subject may be accomplished in operation 605 so that the speech test is perceptually balanced. Thus, operation 605 may include presenting an audio signal with different volumes, different background noise levels, and / or different SNRs.

[0100] In operation 610, a visual indication of the vocabulary and a visual indication of each of the plurality of alternative vocabulary are presented to the subject via a user interface. Thus, operation 610 may be embodied as displaying or presenting a video similar to Figure 4 User interface 400 or Figure 5 500. As discussed above, visual indications of alternative vocabulary may be selected, for example, to provide a test having a predetermined difficulty level, to provide a test to assess a subject's loss of discrimination, to provide a test to determine a subject's loss of sensitivity, or otherwise customize a test as would be appreciated by one skilled in the art.

[0101] In operation 615, a selection of a visual indication of a vocabulary from the vocabulary subset or a visual indication of one of the plurality of alternative vocabularies is received. This input is received via a user input device configured to interact with a user interface.

[0102] Once the test is completed through the process flow of flowchart 600, the results of the test can be scored. For example, compare the phonetic transcription of the target vocabulary and the subject's response. The most important speech errors can be provided to an audio expert or the subject's speech confusion matrix can be calculated. The average reaction time between playing the audio signal in operation 605 and receiving the response in operation 615 can also be used in the scoring. The measurement of this reaction time can indicate the subject's listening effort during the test. Additional scoring techniques can also be used without departing from the technology disclosed herein. For example, the technology disclosed herein can utilize the scoring technology disclosed in International Application No. PCT / IB2020 / 000952 (designating the United States and published on May 27, 2021 as International Publication No. WO / 2021 / 099834), the contents of which are incorporated herein by reference in their entirety. Once scored, the results of the test can then be used to customize the subject's treatment, such as as described below with reference Figure 7Describes the custom fitting of a hearing device.

[0103] Through the above techniques, test material specific hearing tests (e.g., vocabulary lists and audio signals or recorders) can be provided with reduced workload compared to related technologies. Moreover, the techniques of the present disclosure allow for additional benefits and provide additional use cases, including building hearing test kits of varying difficulty. These test kits can then be used to implement hearing games to support rehabilitation. The test kits can provide the following different variations:

[0104] ·Present tests that vary in level, i.e. soft tests vs. loud tests.

[0105] • Tests with varying vocabulary lists. Some lists may be speech-balanced, while others may be configured to target or train on a specific speech.

[0106] • Tests can be generated that add background noise to the test audio signal to aid in training hearing in noisy environments. Such tests can have a fixed SNR or the SNR in such tests can vary.

[0107] Adaptive testing. Because the technology provided herein dynamically generates a vocabulary list and an audio signal for conducting a test, test material can be generated to search for a subject's speech recognition threshold SRT. The SRT can be tested based on a varying presentation level (i.e., volume), a varying SRT, or both. The technology presented herein can change these values ​​"on the fly" during a speech test.

[0108] Tests can be generated to train working memory by providing word triplets instead of single words. For example, an audio signal associated with a triple can be played to the subject, and the subject is asked to identify the word only after the audio of all three has been completed. The subject can be tasked to enter the answers to the words in forward or reverse order. The test can also measure auditory memory by lengthening the word sequence to 4, 5, 6 or more words for entry in forward or reverse order.

[0109] · Tests can assess listening ability by measuring reaction time or by increasing the number of words used to test for listening fatigue.

[0110] • Tests can be generated that force the subject to respond within a certain time to train their reaction speed.

[0111] Tests can be generated that train subjects to recognize different types of speech. For example, the use of text-to-speech technology can allow the generation of an audio signal associated with a dynamically generated vocabulary list using a mixture of different voices, including a mixture of male voices, female voices, voices with regional pronunciations, and voices spoken at different rates.

[0112] • Tests can be generated to test or train subjects to recognize speech with varying sound qualities. For example, reverberation or telephone filtering can be added to the audio signal presented to the subject during the test.

[0113] Testing can be supervised with immediate feedback to the subject. For example, after the subject enters their answer, the user interface can highlight the correct answer to speed up training.

[0114] • Tests can be generated that measure tone recognition in tonal languages ​​by providing tone variants in a response set.

[0115] All of the above test types can then be used for customized treatment or audio prosthesis fitting. Figure 7 , a block diagram is depicted illustrating an exemplary debugging system 770 configured to debug a hearing device based at least in part on speech testing performed according to the techniques presented herein. The debugging system 770 is typically a computing device that includes a plurality of interfaces / ports 778(1)-778(N), a memory 780, a processor 784, and a user interface 786. The interfaces 778(1)-778(N) may include, for example, any combination of a network port (e.g., an Ethernet port), a wireless network interface, a universal serial bus (USB) port, an Institute of Electrical and Electronics Engineers (IEEE) 1394 interface, a PS / 2 port, etc. In Figure 7 In the example of FIG. 7 , interface 778(1) is connected to cochlear implant system 102 having components implanted in user 771. Interface 778(1) may be connected directly to cochlear implant system 102 or to an external device that communicates with the cochlear implant system (e.g., Figures 1A-1D Interface 778(1) may be configured to communicate with cochlear implant system 102 via a wired or wireless connection (eg, telemetry, Bluetooth, etc.).

[0116] The user interface 786 includes one or more output devices, such as a display screen (e.g., a liquid crystal display (LCD)) and a speaker, for presenting visual or auditory information to a clinician, audiologist, or other user. The user interface 786 may also include one or more input devices, such as a keypad, keyboard, mouse, touch screen, etc.

[0117] The memory 780 includes hearing ability profile management logic 781 that can be executed to generate or update the user's hearing ability profile 783 stored in the memory 780. The hearing ability profile management logic 781 can be executed to receive a user's hearing ability profile 783 from, for example, an imaging system via one of the other interfaces 778(2)-778(N). Figure 7The hearing ability profile management logic 781 may also be executed to obtain speech test data obtained using the techniques disclosed herein. For example, the hearing ability profile management logic 781 may be connected to the user's cognitive hearing ability using one of the other interfaces 778(2)-778(N). Figures 1A-1D The hearing ability profile management logic 781 may download the speech test result data from the external device and use the speech test result to generate or update the user's hearing ability profile 783. Alternatively, the hearing ability profile management logic 781 may download the speech test result from an external server or computing device via a network connection such as the Internet. This externally acquired data may then be used by the hearing ability profile management logic 781 to generate or update the user's hearing ability profile 783.

[0118] In some embodiments, memory 780 includes subjective assessment logic 785, which is configured to perform a subjective assessment of the user's cognitive hearing ability and provide the results for use by hearing ability profile management logic 781. Subjective assessment logic 785 may include the application described above that is executed to provide the speech testing technology disclosed herein. Therefore, debugging system 770 can not only use the results of the speech test to debug cochlear implant system 102, but debugging system 770 can also be used to perform the speech test of the present disclosure. In other embodiments, subjective assessment logic 785 is omitted, and hearing ability profile management logic 781 is executed to receive the user's cognitive hearing ability from an external device (such as an external device) via one of the other interfaces 778 (2)-778 (N). Figure 7 (not shown) to obtain the results of a subjective assessment of the user's cognitive hearing ability.

[0119] The memory 780 also includes profile analysis logic 787. The profile analysis logic 787 is executed to analyze the user's auditory profile (ie, the relevant results of the objective and subjective assessments) to identify relevant stimulation parameters that are optimized for the user's cognitive auditory abilities.

[0120] The memory 780 may include 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 processor 784 is, for example, a microprocessor or microcontroller that executes instructions for the auditory ability profile management logic 781, the subjective assessment logic 785, and the profile analysis logic 787. Thus, in general, the memory 780 may include one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (by the processor 784), it is operable to perform the techniques described herein.

[0121] The relevant stimulation parameters identified by the execution profile analysis logic 787 are sent to the cochlear implant system 102 to be instantiated as the current relevant stimulation parameters for the cochlear implant. However, in some embodiments, the relevant stimulation parameters identified by the execution profile analysis logic 787 are first displayed at the user interface 786 for further evaluation and / or adjustment by the user. Thus, the user is able to refine the relevant stimulation parameters before sending the stimulation parameters to the cochlear implant system 102.

[0122] The general operation for analyzing the user's auditory profile to identify relevant stimulation parameters optimized for the user's cognitive hearing abilities has been described above. However, it should be appreciated that the profile analysis logic 787 may operate according to one or more selected criteria set by the user via the user interface 786. For example, the user may configure the stimulation parameters that may be adjusted or set limits on how the stimulation parameters may be adjusted.

[0123] 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. Figure 8 An exemplary device that may benefit from the techniques disclosed herein is described in more detail in Figure 7 Debugging system 770 debugging system configuration reference Figure 8 For example, the techniques described herein can be used to prioritize clinician tasks associated with configuring operating parameters of a wearable medical device, such as a wearable device such as Figure 8 The implantable stimulation system described in the present invention can also be applied to consumer devices. These various systems and devices can benefit from the technology described in this article.

[0124] Figure 8 800 is a functional block diagram of an implantable stimulator system 800 that can benefit from the technology described herein. The implantable stimulator system 800 includes a wearable device 100 that acts as an external processor device and an implantable device 30 that acts as an implanted stimulator device. In an example, the implantable device 30 is an implantable stimulator device that is configured to be implanted below the user's tissue (e.g., skin). In an example, the implantable device 30 includes a biocompatible implantable housing 802. Here, the wearable device 100 is configured to be percutaneously connected to the implantable device 30 via a wireless connection to provide additional functionality to the implantable device 30.

[0125] In the example shown, the wearable device 100 includes one or more sensors 812, a processor 814, a transceiver 818, and a power supply 848. The one or more sensors 812 may be one or more units configured to generate data based on sensed activity. In the example where the stimulation system 800 is a hearing prosthesis system, the one or more sensors 812 include a sound input sensor, such as a microphone, an electrical input for an FM hearing system, other components for receiving sound input, or a combination thereof. In the case where the stimulation system 800 is a visual prosthesis system, the one or more sensors 812 may include one or more cameras or other visual sensors. In the case where the stimulation system 800 is a cardiac stimulator, the one or more sensors 812 may include a cardiac monitor. The processor 814 may be a component (e.g., a central processing unit) configured to control the stimulation provided by the implantable device 30. The stimulation may be controlled based on data from the sensor 812, a stimulation schedule, or other data. In the case where the stimulation system 800 is a hearing prosthesis, the processor 814 may be configured to convert a sound signal received from (one or more) sensors 812 (e.g., acting as a sound input unit) into a signal 851. The transceiver 818 is configured to transmit a signal 851 in the form of a power signal, a data signal, a combination thereof (e.g., by interleaving the signal), or other signals. The transceiver 818 may also be configured to receive power or data. The stimulation signal may be generated by the processor 814 and transmitted to the implantable device 30 using the transceiver 818 for providing stimulation.

[0126] In the example shown, implantable device 30 includes transceiver 818, power source 848, and medical device 811 including electronics module 810 and stimulator assembly 830. Implantable device 30 also includes a hermetically sealed biocompatible implantable housing 802 enclosing one or more of the components.

[0127] The electronic module 810 may include one or more other components to provide a medical device function. In many examples, the electronic module 810 includes one or more components for receiving a signal and converting the signal into a stimulation signal 815. The electronic module 810 may also include a stimulator unit. The electronic module 810 may generate a stimulation signal 815 or control the delivery of the stimulation signal to the stimulator assembly 830. In an example, the electronic module 810 includes one or more processors (e.g., a central processing unit or a microcontroller) coupled to a memory component (e.g., a flash memory), which stores instructions that cause the execution of an operation when executed. In an example, the electronic module 810 generates and monitors parameters (e.g., output voltage, output current, or line impedance) associated with generating and delivering stimulation. In an example, the electronic module 810 generates a telemetry signal (e.g., a data signal) including telemetry data. The electronic module 810 may send a telemetry signal to the wearable device 100 or store the telemetry signal in a memory for later use or retrieval.

[0128] The stimulator assembly 830 can be a component configured to provide stimulation to the target tissue. In the example shown, the stimulator assembly 830 is an electrode assembly, which includes an electrode contact array arranged on a lead. The lead can be arranged near the tissue to be stimulated. In the case where the system 800 is a cochlear implant system, the stimulator assembly 830 can be inserted into the cochlea of ​​the user. The stimulator assembly 830 can be configured to deliver the stimulation signal 815 (e.g., electrical stimulation signal) generated by the electronic module 810 to the cochlea, so that the user experiences auditory perception. In other examples, the stimulator assembly 830 is a vibration actuator, which is arranged inside or outside the housing of the implantable device 30 and is configured to generate vibration. The vibration actuator receives the stimulation signal 815 and generates a mechanical output force in the form of vibration based on the stimulation signal. The actuator can deliver vibration to the user's skull in a manner that generates movement or vibration of the user's skull, thereby generating auditory perception by activating the hair cells in the user's cochlea via cochlear fluid motion.

[0129] The transceiver 818 may be a component configured to transcutaneously receive and / or transmit a signal 851 (e.g., a power signal and / or a data signal). The transceiver 818 may be a collection of one or more components that form part of a transcutaneous energy or data transmission system to transmit a signal 851 between the wearable device 100 and the implantable device 30. Various types of signal transfer, such as electromagnetic, capacitive, and inductive transfer, may be used to effectively receive or transmit the signal 851. The transceiver 818 may include or be electrically connected to the coil 20.

[0130] As shown, the wearable device 100 includes a coil 108 for transcutaneously transmitting signals with a concave coil 20. As described above, transcutaneously transmitting signals between the coil 108 and the coil 20 may include transmitting power and / or data from the coil 108 to the coil 20 and / or transmitting data from the coil 20 to the coil 108. The power supply 848 may be one or more components configured to provide operating power to other components. The power supply 848 may be or include one or more rechargeable batteries. The power of the battery can be received from the power supply and stored in the battery. The power can then be distributed to other components for operation as needed.

[0131] It should be understood that although the combination Figure 8 Although specific components are described, the technology disclosed herein can be applied to any of a variety of situations. The above discussion is not intended to indicate that the disclosed technology is only suitable for use in situations similar to those in Figure 8 In general, the methods and systems herein may be practiced using additional configurations and / or some aspects described may be excluded without departing from the methods and systems disclosed herein.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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 that, when executed by one or more processors, cause one or more processors to perform operations similar to the method of the present disclosure.

[0136] 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.

[0137] 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.

[0138] 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: Acquire a vocabulary pool; dynamically generating from the vocabulary pool a subset of the vocabulary pool having a predetermined phonetic balance; as well as A speech test is performed on the subject using the subset of the vocabulary pool.

2. The method of claim 1, wherein dynamically generating the subset of the vocabulary pool comprises selecting vocabulary from the vocabulary pool such that an average speech distribution of the subset of the vocabulary pool is within predetermined bounds of predetermined speech distribution values.

3. The method of claim 1 or claim 2, wherein dynamically generating the subset of the vocabulary pool comprises implementing a search algorithm on a phonetic assignment table populated based on the vocabulary pool.

4. The method according to any one of claims 1-3, wherein dynamically generating the subset of the vocabulary pool comprises: determining an average speech distribution of the vocabulary pool; randomly selecting a word from the word pool; as well as Vocabularies of the subset of the vocabulary pool are accepted or rejected based on the average speech distribution of the vocabulary pool and the speech of the vocabulary.

5. The method according to any one of claims 1-4, wherein compiling the vocabulary pool comprises compiling the vocabulary pool from words having similar phonetic structures.

6. The method according to any one of claims 1-5, wherein performing the speech test on the subject comprises: playing an audio signal of a word from a vocabulary subset; presenting, via a user interface, a visual indication of a vocabulary word from the subset of vocabulary words and a visual indication of each of a plurality of alternative vocabulary words; as well as A selection of one of the visual indications of a word from the subset of words or one of the plurality of alternative words is received via a user input device configured to interact with the user interface.

7. The method of claim 6, further comprising determining the plurality of alternative vocabularies based on a difficulty level of the speech test.

8. The method of claim 7, further comprising determining the plurality of alternative vocabularies based on an average phonetic distance of each of the plurality of alternative vocabularies from a vocabulary from the vocabulary subset.

9. A method according to any one of claims 6-8, wherein performing the speech test includes presenting a visual indication to the subject through the user interface to indicate through the user input device that the audio signal of a vocabulary from the vocabulary subset does not correspond to the visual indication of a vocabulary from the vocabulary subset or any of the visual indications of the multiple alternative vocabulary.

10. The method of any one of claims 1-8, further comprising scoring the speech test.

11. The method of claim 10, wherein scoring the speech test comprises determining a discrimination loss for the subject.

12. A method according to claim 10 or claim 11, wherein scoring the speech test comprises determining the subject's loss of sensitivity.

13. The method of any one of claims 1-12, wherein performing a speech test comprises presenting a perceptually balanced recording of the subset of the vocabulary pool.

14. The method of claim 13, wherein presenting the perceptually balanced recordings of the subset of the vocabulary pool comprises presenting the perceptually balanced recordings of the subset of the vocabulary pool at substantially similar volume levels.

15. The method of any one of claim 13 or claim 14, wherein presenting the perceptually balanced recording of the subset of the vocabulary pool comprises presenting the perceptually balanced recording to achieve a predetermined speech recognition threshold.

16. The method of any one of claims 13-15, wherein presenting the perceptually balanced recording of the subset of the vocabulary pool comprises presenting the perceptually balanced recording of the subset of the vocabulary pool with background noise.

17. The method of any one of claim 16, wherein presenting the perceptually balanced recordings of the subset of the vocabulary pool comprises determining a background noise level for each of the perceptually balanced recordings to achieve a predetermined speech recognition threshold.

18. A method comprising: Obtain data indicating the vocabulary pool; applying a search algorithm to the data indicative of the vocabulary pool to generate data indicative of a subset of the vocabulary pool having a selected speech distribution; as well as A test vocabulary set for a speech test for a subject is generated from the data indicative of the subset of the vocabulary pool.

19. The method of claim 18, wherein the vocabulary pool has a predetermined speech distribution, and wherein the selected speech distribution is a speech distribution within the bounds of the predetermined speech distribution.

20. The method of claim 18, further comprising generating, for each word in the test vocabulary set, an alternative word to be presented to the subject during the speech test.

21. The method of claim 20, wherein generating the replacement vocabulary comprises dynamically generating the replacement vocabulary based on phonetic features of words in the test vocabulary set for which the replacement vocabulary is generated.

22. The method of claim 20, wherein dynamically generating the alternative vocabulary comprises dynamically generating the alternative vocabulary based on a predetermined difficulty level of the speech test.

23. A method according to claim 21 or claim 22, wherein dynamically generating the replacement vocabulary comprises selecting the replacement vocabulary based on a level of phonetic similarity to a vocabulary in the test vocabulary set for which the replacement vocabulary is generated.

24. The method of claim 18, 19, 20, 21 or 22, further comprising: The speech test is administered to the subject using the test vocabulary set.

25. The method of claim 24, wherein administering the speech test to the subject using the test vocabulary set comprises: A series of audio signals are generated for presentation to the subject such that the audio signals presented to the subject during the speech test are perceptually balanced.

26. The method of claim 24, wherein generating the audio signal comprises selecting the audio signal at a varying volume level.

27. The method of claim 24, wherein generating the audio signal comprises generating an audio signal having a varying background noise level.

28. A method comprising: obtaining data indicative of a vocabulary pool having a predetermined speech distribution; generating data indicative of a subset of the vocabulary pool such that a speech distribution of the subset of the vocabulary pool is within the bounds of the predetermined speech distribution; as well as An audio signal is generated for each word in a vocabulary subset for presentation to a subject during a speech test for the subject such that the audio signal presented to the subject during the speech test is perceptually balanced.

29. The method of claim 28, wherein generating the audio signal for each word in the vocabulary subset comprises selecting an audio signal at a varying volume level.

30. The method of claim 28, wherein generating the audio signal for each word in the vocabulary subset comprises selecting an audio signal with varying background noise levels.

31. A method according to claim 28, 29 or 30, wherein generating the audio signal for each word in the vocabulary subset comprises selecting from pre-recorded audio signals.

32. The method of claim 28, 29 or 30, wherein generating the audio signal for each word in the vocabulary subset comprises generating an audio signal using a text-to-speech algorithm.

33. One or more non-transitory computer-readable storage media comprising instructions that, when executed by a processor, cause the processor to: Obtain a predetermined vocabulary pool; generating from the predetermined vocabulary pool a subset of the vocabulary pool having a predetermined phonetic distribution; and A test vocabulary set is generated from the subset of the vocabulary pool to administer a speech test to a subject.

34. The one or more non-transitory computer-readable storage media of claim 32, wherein the phonetic distribution of the subset of the vocabulary pool is within the bounds of a predetermined phonetic distribution.

35. One or more non-transitory computer-readable storage media according to claim 32, wherein the predetermined vocabulary pool has a predetermined speech distribution, and wherein the speech distribution of the subset of the vocabulary pool is within the bounds of the predetermined speech distribution of the predetermined vocabulary pool.

36. The one or more non-transitory computer-readable storage media of claim 32, further comprising instructions that, when executed by the processor, cause the processor to: For each word in the test vocabulary set, an alternative word is generated to be presented to the subject during the speech test.

37. The one or more non-transitory computer-readable storage media of claim 32, wherein the instructions that, when executed by the processor, cause the processor to generate the alternative vocabulary include instructions to: The replacement vocabulary is dynamically generated based on phonetic features of words in the test vocabulary set for which the replacement vocabulary is generated.

38. The one or more non-transitory computer-readable storage media of claim 32, wherein the instructions that, when executed by the processor, cause the processor to generate the alternative vocabulary include instructions to: The replacement vocabulary is dynamically generated based on a predetermined difficulty level of the speech test.

39. The one or more non-transitory computer-readable storage media of claim 36 or 37, further comprising instructions that, when executed by the processor, cause the processor to: The replacement vocabulary is selected based on a level of phonetic similarity to a vocabulary in the test vocabulary set for which the replacement vocabulary is generated.