System and method for self voice detection in a hearing system

Abstract

An example hearing device is configured to determine a first sound pressure level, SPL, and a second SPL representing a first spectral portion and a second spectral portion, respectively, of an ipsilateral audio signal of audio content. The first and second spectral portions have frequencies included in a first frequency range and a second frequency range, respectively, with the second frequency range being higher than the first frequency range. The device can also determine that the first SPL is at least a threshold amount of SPL greater than the second SPL, and determine that a level of symmetry between the ipsilateral audio signal and a contralateral audio signal is at least a threshold level of symmetry. Based on these determinations, the hearing device can determine that the audio content includes own voice content.

Description

[0001] Background Information

[0002] Hearing devices can be configured to provide a processed version of audio content to enhance a user's hearing. However, if the audio content includes the user's own voice (self-speech content), amplifying and / or processing such content in the same way as other detected audio content may produce an output that sounds unnatural or detrimental to the user. Furthermore, different processing strategies may be required or preferred for other audio content or self-speech content. Therefore, identifying self-speech content within audio content is crucial for the optimal performance of hearing devices.

[0003] US20080189107A1 describes a method for attempting to identify speech content using the signal energy ratio between the direct sound portion and the reverberant sound portion.

[0004] US10025668B2 describes a hearing system having a left hearing device and a right hearing device, each of which includes a behind-the-ear microphone, an in-the-ear microphone, and an adaptive filter for attempting to detect the voice of the wearer of the hearing device.

[0005] US10616694B2 describes a hearing device that analyzes sound based on its correspondence to the type of one's own speech. Depending on the degree of correspondence between the sound and one's own speech, the sound is identified as one's own speech.

[0006] Each of these traditional methods for detecting one's own speech content disadvantageously requires specialized components and / or complex processing. Attached Figure Description

[0007] The accompanying drawings illustrate various embodiments and are part of the specification. The illustrated embodiments are merely examples and do not limit the scope of this disclosure. In all the drawings, the same or similar reference numerals denote the same or similar elements.

[0008] Figures 1-2 An exemplary hearing system based on the principles described herein is shown.

[0009] Figures 3-4 An exemplary diagram for self-speech detection based on the principles described herein is shown.

[0010] Figures 5-6 An exemplary hearing device based on the principles described herein is shown.

[0011] Figure 7 An exemplary diagram for self-speech detection based on the principles described herein is shown.

[0012] Figure 8An exemplary flowchart for self-speech detection based on the principles described herein is shown.

[0013] Figure 9 An exemplary computing device based on the principles described herein is shown.

[0014] Figure 10 An exemplary method based on the principles described herein is shown. Detailed Implementation

[0015] This document describes exemplary systems and methods for self-speech detection in a hearing system. For example, the hearing system may include: a ipsilateral microphone associated with (e.g., located nearby) the user's ipsilateral ear and configured to detect ipsilateral audio signals representing audio content; a contralateral microphone associated with (e.g., located nearby) the user's contralateral ear and configured to detect contralateral audio signals representing audio content; and a hearing device associated with the ipsilateral ear (e.g., configured to provide a processed version of the audio content to the ipsilateral ear). The hearing device may be configured to: determine a first sound pressure level (SPL) of a first spectral portion of the ipsilateral audio signal; determine a second SPL of a second spectral portion of the ipsilateral audio signal; determine that the first SPL is at least a threshold SPL greater than the second SPL; and determine that the level of symmetry between the ipsilateral and contralateral audio signals is at least a threshold symmetry level. Based on determining that the first SPL is at least a threshold SPL greater than the second SPL and determining that the level of symmetry is at least a threshold symmetry level, the hearing device may be configured to: determine that the audio content includes self-speech content representing the user's speech.

[0016] The systems and methods described herein can advantageously provide numerous benefits to users of hearing devices. For example, the hearing devices described herein can provide audio signals that more accurately reproduce audio content, including self-speech content perceived by normal hearing, than conventional hearing systems. Furthermore, the systems and methods described herein can detect self-speech content more accurately without requiring additional components compared to conventional hearing systems. Moreover, the systems and methods described herein can detect self-speech content more reliably and quickly, while using lower computational power compared to conventional hearing systems. Additionally, in some embodiments, the systems and methods described herein can use machine learning algorithms to dynamically adjust one or more of the thresholds described herein, thereby allowing the self-speech detection capabilities of the systems and methods described herein to improve over time. For at least these reasons, the systems and methods described herein can advantageously provide additional functionality and / or features to users of hearing devices compared to conventional hearing systems. These and other benefits of the systems and methods described herein will become apparent herein.

[0017] Figure 1An exemplary hearing system 100 is shown that can be used to transmit sound to a user. The hearing system 100 includes a first hearing device 102-1 and a second hearing device 102-2 (collectively referred to as "hearing device 102"). Figure 1 The positioning of hearing device 102 relative to dashed line 104 is shown, and from the perspective of hearing device 102-1, hearing device 102-1 is associated with the user's ear on the same side, and hearing device 102-2 is associated with the user's ear on the opposite side. For example, if hearing device 102-1 is associated with the user's left ear, then hearing device 102-2 is associated with the user's right ear. Or, if hearing device 102-1 is associated with the user's right ear, then hearing device 102-2 is associated with the user's left ear. As used herein, hearing devices are "associated" with a particular ear by being configured to be worn on or inside a particular ear and / or by providing hearing ability to a particular ear.

[0018] Hearing devices 102 can communicate with each other via communication link 106, which can be a wired or wireless communication link that can be used in a particular implementation.

[0019] Each of the hearing devices 102 can be implemented by any type of hearing device configured to provide or enhance the hearing of a user of the hearing system 100. For example, each of the hearing devices 102 can be implemented by: a hearing aid configured to apply amplified audio content to the user; a sound processor included in a cochlear implant system configured to apply electrical stimulation representing audio content to the user; a sound processor included in an electro-acoustic stimulation system configured to apply electro-acoustic stimulation to the user; headphones; earbuds; hearing devices; smart headphones; or any other suitable hearing device. In some examples, hearing device 102-1 has a different type than hearing device 102-2. For example, hearing device 102-1 can be a hearing aid and hearing device 102-2 can be a sound processor included in a cochlear implant system. As another example, hearing device 102-1 can be a unilateral hearing aid and hearing device 102-2 can be a signal contralateral routing (CROS) hearing aid-crosslinking hearing aid.

[0020] As shown in the figure, hearing device 102-1 may include a processor 108-1, a memory 110-1, a microphone 112-1, and an output transducer 114-1. Similarly, hearing device 102-2 may include a processor 108-2, a memory 110-2, a microphone 112-2, and an output transducer 114-2. Hearing device 102 may include additional or alternative components that may be used in a particular implementation.

[0021] Processors 108 (e.g., processors 108-1 and 108-2) are configured to perform various processing operations, such as processing audio content received by hearing device 102 and sending data to each other. Each processor in processor 108 may be implemented by any suitable combination of hardware and software. Any reference herein to operations performed by hearing device (e.g., hearing device 102-1) should be understood as being performed by the processor of hearing device (e.g., processor 108-1).

[0022] Memory 110 (e.g., memory 110-1 and memory 110-2) may be implemented by any suitable type of non-transitory computer-readable storage medium and may hold (e.g., store) data used by processor 108. For example, memory 110 may store data representing an operating procedure that specifies how each processor 108 processes audio content and delivers the audio content to the user. To illustrate, if hearing device 102-1 is a hearing aid, memory 110-1 may hold data representing an operating procedure that specifies an audio amplification scheme (e.g., amplification level, etc.) used by processor 108-1 to deliver acoustic content to the user. As another example, if hearing device 102-1 is a sound processor included in a cochlear implant system, memory 110-1 may hold data representing an operating procedure that specifies a stimulation scheme used by hearing device 102-1 to instruct the cochlear implant to apply electrical stimulation representing acoustic content to the user.

[0023] Microphone 112 (e.g., microphone 112-1 and microphone 112-2) can be implemented by any suitable audio detection device and configured to detect audio signals presented to the user of hearing device 102. Figure 1 As shown, microphone 112 may be included in (e.g., embedded therein, on its surface, or otherwise located) hearing device 102. One or both of microphones 112 may alternatively be detached from and communicatively coupled to their respective hearing device 102. For example, microphone 112-1 may be removably attached to hearing device 102-1.

[0024] Microphone 112-1 may be referred to herein as a ipsilateral microphone associated with the user's ipsilateral ear. Similarly, microphone 112-2 may be referred to herein as a contralateral microphone associated with the user's contralateral ear. A microphone can be "associated" with a specific ear by being positioned relatively close to it, enabling the microphone to detect audio signals presented to that specific ear. For example, microphone 112-1 may be configured to detect audio signals presented to the ipsilateral ear (therefore, this audio signal may be referred to herein as an "ipsilateral audio signal"). Similarly, microphone 112-2 may be configured to detect audio signals presented to the contralateral ear (therefore, this audio signal may be referred to herein as a "contralateral audio signal"). The ipsilateral and contralateral audio signals may represent the same audio content (e.g., music, sound, noise, self-speech content, etc.), but may have different characteristics due to the different positioning of microphone 112.

[0025] The output transducer 114 can be implemented by any suitable audio output device. For example, the output transducer 114 can be implemented by a speaker (also known as a receiver) of a hearing device or one or more electrodes of a cochlear implant system.

[0026] Figure 2 An alternative hearing system 200, which can be used according to the systems and methods described herein, is shown. Hearing system 200 is similar to hearing system 100 in that it includes a hearing device 102-1 associated with the user's ear on the same side. However, as shown, hearing system 200 does not include a second hearing device associated with the user's contralateral ear. Instead, hearing system 200 includes a contralateral microphone 202 associated with the user's contralateral ear and communicatively coupled to hearing device 102-1 via communication link 204, which may be wired or wireless, depending on the specific implementation.

[0027] As described herein, hearing devices (e.g., hearing devices 102-1 and / or hearing devices 102-2) can be configured to determine when audio content represented by ipsilateral audio signals and contralateral audio signals detected by ipsilateral and contralateral microphones, respectively, includes its own speech content. As will now be described, this can be performed at least in part based on a comparison of the SPL of different spectral portions of the ipsilateral audio signal.

[0028] Figure 3An exemplary figure 300 is shown, illustrating the SPL of an audio signal including its own speech content. Figure 300 includes a y-axis 302 representing the relative SPL and an x-axis 304 representing the relative distance. For example, the x-axis 304 shows two positions: position 306 representing the position at the user's mouth, and position 308 representing the position at the user's ear. Solid line 310 depicts the SPL of a first spectral portion of the audio signal, while dashed line 312 depicts the SPL of a second spectral portion of the audio signal. The first spectral portion corresponds to frequencies encompassing the low-frequency range of the audio signal, while the second spectral portion corresponds to frequencies encompassing the high-frequency range of the audio signal.

[0029] The frequency range of the first spectral portion can be any suitable frequency range below the remaining frequency range of the audio signal. For example, the low-frequency range can be any suitable width (e.g., 10 Hz to 2 kHz) centered on any suitable relatively low audio frequency (e.g., 500 Hz to 2 kHz). For example, the low-frequency range can be 800 Hz to 1200 Hz, 975 Hz to 1025 Hz, or any other suitable range. The SPL of the spectral portion can be any suitable SPL associated with the spectral portion, such as average SPL, median SPL, maximum SPL, minimum SPL, etc. The frequency range of the second spectral portion can be any suitable frequency range above the low-frequency range of the audio signal. For example, the high-frequency range can be any suitable width (e.g., 10 Hz to 2 kHz) centered on any suitable relatively high audio frequency (e.g., 4 kHz to 10 kHz). For example, the high-frequency range can be 4 kHz to 7 kHz, 5 kHz to 6 kHz, or any other suitable range.

[0030] When the audio content includes its own speech, the audio signal can leave the user's mouth with relatively similar SPLs for both the low and high frequency ranges, as shown at position 306. However, the low and high frequency ranges can reach the ear via different acoustic paths. The low frequency range of the audio signal (or at least a portion of it) can be transmitted from the mouth to the ear via direct conduction through the user's head. However, the high frequency range of the audio signal may not be conducted through the head and may instead be transmitted via a non-direct path between the mouth and the ear (including reflections from other surfaces). Therefore, the SPL of the low frequency range may attenuate less than that of the high frequency range as the audio signal travels from the mouth to the ear, as shown at position 308.

[0031] Figure 4An exemplary figure 400 is shown, which further illustrates the SPL of an audio signal representing audio content including its own speech content. Figure 400 includes a y-axis 402 representing the SPL relative to an x-axis 404 representing the frequency. The dashed line 406 represents the audio signal at the source of the audio signal. In this example, the audio signal can have the same SPL across the spectrum of the audio signal at the source of the audio signal, and therefore the dashed line 406 has the same SPL value across all frequency values.

[0032] If the audio signal represents its own speech content, then solid line 408 represents the transmission of the audio signal to the user's ear. As described with reference to Figure 300, when the audio signal represents its own speech content, the low-frequency range of the audio signal may attenuate less compared to the high-frequency range. Conversely, if the audio signal represents audio content that does not include its own speech content, then dashed line 410 represents the transmission of the audio signal to the user's ear (over the same distance). As shown, when the audio content does not include its own speech content, the attenuation of the low-frequency range of the audio signal is a relatively similar amount to that of the high-frequency range because these two frequency ranges travel similar acoustic paths from the audio content source to the user's ear.

[0033] The comparison between audio signals with and without their own speech content is highlighted by arrows 412 and 414, showing that in the low-frequency range, the SPL drop is greater for the audio signal without its own speech content (arrow 414) compared to the audio signal with its own speech content (arrow 412). Meanwhile, arrows 416 and 418 show that in the high-frequency range, the difference in SPL drop between the audio signal without its own speech content (arrow 416) and the audio signal with its own speech content (arrow 418) is smaller. Rather, as this example illustrates, at certain frequency levels, audio signals with their own speech content can attenuate more than audio signals without their own speech content. These differences in the SPL between the spectral portions of the audio signal detected at the user's ear (e.g., close to the user's ear) can be a factor that a hearing device (e.g., hearing device 102-1) can consider when determining whether an audio signal represents audio content that includes its own speech content.

[0034] Figure 5 An exemplary configuration 500 of hearing device 102 is shown, which may represent hearing device 102-1 or 102-2 described herein. As shown, hearing device 102 receives an audio signal 502-1 from the same side and an audio signal 502-2 from the opposite side (collectively referred to as audio signal 502). As described, the audio signal 502-1 from the same side may be detected by a microphone from the same side (e.g., microphone 112-1), while the audio signal 502-2 from the opposite side may be detected by a microphone from the opposite side (e.g., microphone 112-2 or microphone 202).

[0035] The hearing device 102 can perform various operations on the audio signal 502 to determine whether the audio signal 502 includes its own speech content, as represented by analysis functions 504-510. For example, as shown, the hearing device 102 can perform spectral SPL analysis 504, direction analysis 506, total SPL analysis 508, and / or sound content analysis 510 on the same-side audio signal 502-1 and / or the opposite-side audio signal 502-2 to determine whether these audio signals include their own speech content. The hearing device 102 can use any combination of one or more of these analysis functions 504-510 to serve a particular implementation. For example, in some cases, the hearing device 102 can determine, based on spectral SPL analysis 504 and direction analysis 506, that the same-side audio signal 502-1 and / or the opposite-side audio signal 502-2 includes its own speech content, either alone or in combination with total SPL analysis 508 and / or sound content analysis 510. Based on the processing of the ipsilateral audio signal 502-1 and / or the contralateral audio signal 502-2 using one or more of the analysis functions 504-510, the hearing device 102 can output self-speech determination data 512 indicating whether the audio signal 502 includes its own speech content. Each of the analysis functions 504-510 is described herein.

[0036] The hearing device 102 can perform spectral SPL analysis 504 in any suitable manner. For example, the hearing device 102 can determine a first SPL of a first spectral portion of the same-side audio signal. The first spectral portion may have frequencies included in a first frequency range. The hearing device 102 can also determine a second SPL of a second spectral portion of the same-side audio signal. The second spectral portion may have frequencies included in a second frequency range higher than the first frequency range. The hearing device 102 can also determine whether the first SPL is at least a threshold SPL amount greater than the second SPL. The threshold amount can be any suitable threshold SPL amount. For example, the average first SPL of the same-side audio signal excluding its own speech content may be about 10 dB higher than the second SPL. Conversely, the average first SPL of the same-side audio signal including its own speech content may be about 30 dB higher than the second SPL. Therefore, the threshold SPL amount can be set for values ​​between the average differences (e.g., 15 dB, 20 dB, 25 dB, etc.).

[0037] Additionally or alternatively, the hearing device 102 can determine whether the first SPL is at least a threshold amount greater than the second SPL by determining the ratio between the first SPL and the second SPL and by determining whether that ratio is higher than a threshold ratio associated with a threshold SPL amount. The threshold SPL ratio can be any suitable SPL ratio that indicates the attenuation threshold SPL amount of the first spectral portion compared to the second spectral portion. Therefore, the threshold SPL ratio can indicate that the SPL of the first spectral portion is at least a threshold SPL amount greater than the SPL of the second spectral portion. For example, the threshold ratio can be between 25 and 35 (e.g., between 28 and 32, set to 30, or any other threshold between 25 and 35, etc.) or any other suitable ratio.

[0038] The hearing device 102 can perform direction analysis 506 in any suitable manner. For example, the hearing device 102 (e.g., a direction / spatial classifier of the hearing device 102) can determine the level of symmetry between the ipsilateral audio signal 502-1 and the contralateral audio signal 502-2 and compare that level of symmetry with a threshold level of symmetry. The hearing device 102 can also use a head-related transfer function to determine the direction of the audio signal 502 relative to the user's arrival. Since the mouth is located in front of the user's ears, the audio signal generated by the mouth may appear to come from in front of the user (and / or may be reflected by an object and actually come from in front of the user).

[0039] Audio signals from the front of the user can be relatively symmetrical, such as those detected by the left and right ears. Therefore, the hearing device 102 can determine the level of symmetry between the ipsilateral audio signal 502-1 and the contralateral audio signal 502-2. The level of symmetry can be determined in any suitable manner, such as by comparing the SPL of audio signal 502, the waveform of audio signal 502, etc. The hearing device 102 can determine whether the level of symmetry is at least a threshold symmetry level. The threshold symmetry level can be any suitable threshold symmetry level. Additionally, the hearing device 102 can also determine whether the relatively symmetrical audio signals appear to originate from the front or the back of the user, since audio signals from the back of the user may also be relatively symmetrical. Such determination can be performed in any suitable manner, such as using a head-related transfer function.

[0040] The hearing device 102 can perform total SPL analysis 508 in any suitable manner. For example, the hearing device 102 can determine the SPL of the ipsilateral audio signal 502 (e.g., across most or all frequencies). Audio signals with their own speech content generally have a higher SPL than audio signals without their own speech content because the source of the speech content is the user's mouth and therefore at a fixed distance from the user's ear. On the other hand, audio signals without their own speech content typically originate from sources farther from the user's ear than from the user's mouth, and therefore generally have a lower total SPL. The hearing device 102 can compare the total SPL to a threshold SPL to determine whether the audio content can include its own speech content. The threshold SPL can be any suitable SPL.

[0041] The hearing device 102 can perform sound content analysis 510 in any suitable manner. Self-speech content can often include sound content, and therefore the detection of sound content can be another factor used to determine whether audio content includes self-speech content. Furthermore, a generally higher total SPL may be especially true for audio signals representing audio content that includes sound content.

[0042] Hearing device 102 can provide an output 512 of self-speech determination based on one or more of these analyses. In some examples, machine learning algorithms can be used to optimize the detection of self-speech content based on these and other factors. In some examples, self-speech determination can also be based on the self-speech determination of the contralateral hearing device. Based on analysis functions 504-510, both the ipsilateral hearing device and the contralateral hearing device should make the same determination as to whether the audio signal includes self-speech content. Therefore, each device can also base its corresponding self-speech determination on the self-speech determination of the other hearing device.

[0043] Figure 6An exemplary configuration 600 of a hearing device 102 is shown, including a machine learning module 602 configured to implement such machine learning algorithms. Configuration 600 shows the hearing device 102 as having the machine learning module 602 added to configuration 500. The machine learning module 602 can be implemented using any suitable machine learning algorithm, such as neural networks (e.g., artificial neural networks (ANN), convolutional neural networks (CNN), deep neural networks (DNN) and / or recurrent neural networks (RNN), etc.), reinforcement learning, linear regression, etc. The machine learning module 602 can determine optimal parameters, weights, etc., for various characteristics of the audio signal 502 analyzed by the hearing device 102. For example, the machine learning module 602 can determine the optimal threshold for spectral SPL analysis 504, the optimal frequency range for spectral SPL analysis 504, the threshold for the symmetry level for directional analysis 506, the threshold for total SPL analysis 508, and so on. The machine learning module 602 can be trained in any suitable manner. For example, the machine learning module 602 can be configured to update the thresholds based on the determination that the audio signal 502 includes its own speech content. Such optimizations are described herein. Additionally or alternatively, the machine learning module 602 can be trained in a supervised manner, for example using an initial dataset of audio signals labeled based on whether the audio signal includes its own speech content and / or when the audio signal includes (or does not include) its own speech content, receiving input from the user.

[0044] Although configuration 600 shows that machine learning module 602 is included in hearing device 102, alternatively, the machine learning module may be implemented remotely and communicatively coupled to hearing device 102 (e.g., on a smartphone, server, etc.). Additionally or alternatively, any of the analysis functions 504-510 may also be executed on a remote device communicatively coupled to hearing device 102.

[0045] Figure 7 An exemplary figure 700 is shown, illustrating the SPL ratio of audio signals representing audio content with and without its own speech content. Figure 700 includes a y-axis 702 representing the SPL ratio and an x-axis 704 representing eight objects for which sample SPL ratios were determined. For each object, S1-S8, the SPL was measured for the frequency ranges of audio signals with and without their own speech content, and the SPL ratio was determined based on the SPL.

[0046] Solid line 706 shows the SPL ratio of audio signals with their own speech content for objects S1-S8, while dashed line 708 shows the SPL ratio of audio signals without their own speech content for objects S1-S8. For example, solid line 706-1 shows an SPL ratio of approximately 36 between the high-frequency range SPL of the audio signal with its own speech content for object S1 and the low-frequency range SPL of the audio signal with its own speech content for object S1. Dashed line 708-1 shows an SPL ratio of approximately 27 between the high-frequency range SPL of the audio signal without its own speech content for object S1 and the low-frequency range SPL of the audio signal without its own speech content for object S1.

[0047] Between the solid line 706 and the dashed line 708 is the dashed line 710, which can be an example threshold between the SPL ratio of an audio signal with its own speech content and an audio signal without its own speech content. For example, dashed line 710-1 shows an SPL ratio of approximately 31, which can be used as a threshold SPL ratio for object S1. Additionally or alternatively, dashed line 712 shows an average threshold SPL ratio (e.g., an SPL ratio of approximately 30) determined based on the threshold SPL ratios for objects S1-S8. The average threshold SPL ratio can be used as a default threshold SPL ratio (e.g., an SPL ratio between 28 and 32), which can then be adjusted based on the individual SPL ratios described herein.

[0048] Figure 8 An exemplary flowchart 800 is shown for a hearing device (e.g., hearing device 102) to determine its own speech content. Hearing device 102 may receive ipsilateral and contralateral audio signals, and at operation 802, determines a first spectral portion (SPL) for a low-frequency range including the ipsilateral audio signal. The SPL may be determined in any suitable manner. At operation 804, hearing device 102 may determine a second spectral portion (SPL) including a high-frequency range including the ipsilateral audio signal.

[0049] At operation 806, the hearing device 102 can determine the SPL ratio between the SPL in the low-frequency range and the SPL in the high-frequency range. The SPL ratio can be determined in any of the ways described herein. For example, the SPL in the low-frequency range can be divided by the SPL in the high-frequency range. Alternatively or additionally, in the frequency domain, the SPL in the high-frequency range can be subtracted from the SPL in the low-frequency range. Alternatively or additionally, the slope can be determined based on the difference in SPL and the difference in frequency ranges.

[0050] At operation 808, the hearing device 102 can determine the level of symmetry between the ipsilateral and contralateral audio signals. The level of symmetry can be determined in any of the ways described herein.

[0051] At operation 810, hearing device 102 can determine whether the audio signal appears to originate from in front of the user based on the level of symmetry. In some examples, this determination can also be based on a head-related transfer function, as described herein. If hearing device 102 determines that the audio signal does not appear to originate from in front of the user (No, operation 810), then hearing device 102 can determine at operation 812 that the audio content represented by the audio signal does not include its own speech content.

[0052] In some examples, the hearing device 102 may also update analysis parameters at operation 812. For example, the hearing device 102 may use characteristics of the audio signal to determine and / or adjust a threshold, comparing an additional audio signal to that threshold to determine its own speech content. For example, characteristics of the audio signal may include total SPL, SPL ratio, SPL of different spectral portions of the audio signal (e.g., frequency ranges used to adjust spectral portions), and so on. Based on such characteristics, the hearing device 102 may adjust the threshold SPL amount, the total SPL threshold, the frequency ranges of the first and second spectral portions, the threshold symmetry level, and / or any other thresholds used to detect its own speech content. (As in combination...) Figure 7 As described, in some examples, the machine learning module 702 can be used to perform these adjustments. Additionally or alternatively, any other suitable procedure can be used to perform the adjustments.

[0053] In some examples, hearing device 102 may also determine at operation 814 whether the audio content includes sound content. Hearing device 102 may analyze the audio signal in any suitable manner to detect sound content. If hearing device 102 determines that the audio content does not include sound content (No, operation 814), then hearing device 102 may perform operation 812, determining that the audio signal does not represent its own speech content, and updating the analysis parameters accordingly based on the characteristics of the audio signal. If hearing device 102 determines that the audio content does indeed include sound content (Yes, operation 814), then hearing device 102 may perform operation 816.

[0054] If, at operation 810, the hearing device 102 determines that the audio signal appears to originate from in front of the user (Yes, operation 810), then at operation 816, the hearing device 102 can determine whether the SPL ratio determined at operation 806 is at least a threshold SPL ratio. If the hearing device 102 determines that the SPL ratio is less than the threshold SPL ratio (No, operation 816), then the hearing device 102 can perform operation 812, determining that the audio signal does not represent its own speech content, and update the analysis parameters accordingly based on the characteristics of the audio signal. Therefore, the hearing device 102 can determine that the ipsilateral audio signal does not include its own speech content based on the ipsilateral audio signal's SPL ratio not meeting the threshold SPL ratio, even though the ipsilateral audio signal and the contralateral audio signal have at least a threshold symmetry level. Conversely, the hearing device 102 can determine that the ipsilateral audio signal does not include its own speech content based on the ipsilateral audio signal and the contralateral audio signal not meeting the threshold symmetry level, even though it has at least a threshold SPL ratio.

[0055] If the hearing device 102 determines that the SPL ratio is at least a threshold SPL ratio (yes, operation 816), then the hearing device 102 can determine at operation 818 that the audio signal represents its own speech content. Therefore, determining that the audio signal represents its own speech content is based on determining that the SPL ratio is at least an SPL ratio (yes, operation 816) and determining that the audio signal appears to be coming from in front of the user (yes, operation 810).

[0056] The hearing device 102 can utilize this determination of its own speech content in any suitable manner. For example, an audio signal including its own speech content can be processed in a different way than an audio signal that does not include its own speech content. Such processing can be configured to provide the user with the user's own speech in a way that sounds more natural to the user, to improve keyword detection, occlusion control, etc. For example, the hearing device 102 may include various sound processing programs, some of which can be configured to process the user's own speech content. Such programs can be selected and / or adjusted based on the determination that the audio signal includes its own speech content. Additionally or alternatively, the user's own speech content can be used in any suitable manner, such as providing it to a telephone for transmission, for mixing with the sidetone of a telephone call, etc.

[0057] Furthermore, the hearing device 102 can also use the characteristics of the audio signal to update its analysis parameters based on determining that the audio signal represents its own speech content. For example, while the attenuation in the low-frequency range compared to the high-frequency range can generally follow a recognizable pattern, this pattern can vary based on each specific user. Moreover, even for each specific user, the characteristics (and therefore, the optimal threshold) can vary based on the sound content and the user's mood, volume, health, activity, acoustic environment, etc. Therefore, the hearing device 102 can further update its analysis parameters based on determining that the audio signal represents its own speech content. Any suitable machine learning algorithm can also be used. In some examples, machine algorithms can be used to initially program and / or train the analysis parameter values ​​of the hearing device 102 based on a specific user's profile, characteristics, model, and / or speech samples.

[0058] Figure 9 An exemplary computing device 900 is shown, which can be specifically configured to perform one or more processes described herein. Any system, unit, computing device, and / or other component described herein may be implemented by computing device 900.

[0059] like Figure 9 As shown, computing device 900 may include communication interface 902, processor 904, storage device 906, and input / output (“I / O”) module 908, which are communicatively connected to each other via communication infrastructure 910. Although in Figure 9 An exemplary computing device 900 is shown, but Figure 9 The components shown are not intended to be limiting. Additional or alternative components may be used in other embodiments. A more detailed description will now follow. Figure 9 The components of the computing device 900 shown.

[0060] Communication interface 902 can be configured to communicate with one or more computing devices. Examples of communication interface 902 include, but are not limited to, wired network interfaces (e.g., network interface cards), wireless network interfaces (e.g., wireless network interface cards), modems, audio / video connections, and any other suitable interfaces.

[0061] Processor 904 generally refers to any type or form of processing unit capable of processing data and / or interpreting, executing, and / or directing the execution of one or more instructions, procedures, and / or operations described herein. Processor 904 may perform operations by executing computer-executable instructions 912 (e.g., applications, software, code, and / or other executable data instances) stored in storage device 906.

[0062] Storage device 906 may include one or more non-transitory computer-readable data storage media, devices, or configurations, and may take any type, form, and combination of data storage media and / or devices. For example, storage device 906 may include, but is not limited to, any combination of non-volatile media and / or volatile media described herein. Electronic data, including the data described herein, may be stored temporarily and / or permanently in storage device 906. For example, data representing computer-executable instructions 912 configured to direct processor 904 to perform any of the operations described herein may be stored within storage device 906. In some examples, data may be arranged in one or more databases residing within storage device 906.

[0063] I / O module 908 may include one or more I / O modules configured to receive user input and provide user output. I / O module 908 may include any hardware, firmware, software, or a combination thereof that supports input and output capabilities. For example, I / O module 908 may include hardware and / or software for capturing user input, including but not limited to a keyboard or keypad, a touchscreen component (e.g., a touchscreen display), a receiver (e.g., an RF or infrared receiver), a motion sensor, and / or one or more input buttons.

[0064] I / O module 908 may include one or more devices for presenting output to a user, including but not limited to a graphics engine, a display (e.g., a screen), one or more output drivers (e.g., display drivers), one or more audio speakers, and one or more audio drivers. In some embodiments, I / O module 908 is configured to provide graphical data to the display for presentation to the user. The graphical data may represent one or more graphical user interfaces and / or any other graphical content that may serve a particular implementation.

[0065] Figure 10 An exemplary method 1000 is shown. Figure 10 One or more of the operations shown can be performed by any of the hearing devices described herein. Although Figure 10 Exemplary operation according to one embodiment is shown, but other embodiments may omit, add, reorder, and / or modify it. Figure 10 Any of the operations shown. Figure 10 Each operation shown can be performed in any of the ways described herein.

[0066] At operation 1002, a hearing device associated with the same ear determines a first sound pressure level (SPL) of a first spectral portion of the same-side audio signal, the first spectral portion having frequencies included in a first frequency range.

[0067] At operation 1004, the hearing device determines a second SPL of a second spectral portion of the same-side audio signal, the second spectral portion having frequencies included in a second frequency range that are higher than the first frequency range.

[0068] At operation 1006, the hearing device determines that the first SPL is at least a threshold SPL greater than the second SPL.

[0069] 3041-0047-CN

[0070] At operation 1008, the hearing device determines that the level of symmetry between the ipsilateral audio signal and the contralateral audio signal is at least a threshold level of symmetry.

[0071] At operation 1010, the hearing device determines that the audio content includes sound content.

[0072] At operation 1012, the hearing device determines that the audio content includes the user's own speech content, based on determining that the first SPL is at least a threshold SPL greater than the second SPL, determining that the symmetry level is at least a threshold symmetry level, and determining that the audio content includes sound content.

[0073] Various exemplary embodiments have been described in the foregoing description with reference to the accompanying drawings. However, it will be apparent that various modifications and alterations can be made thereto, and additional embodiments can be implemented, without departing from the scope of the invention as set forth in the appended claims. For example, certain features of one embodiment described herein may be combined with or substituted for features of another embodiment described herein. Therefore, this specification and the accompanying drawings should be considered illustrative rather than restrictive.

Claims

1. A hearing system, comprising: A microphone on the same side, which is associated with the user's ear on the same side and is configured to detect audio signals on the same side that represent audio content; A contralateral microphone, associated with the user's contralateral ear and configured to detect contralateral audio signals representing the audio content; as well as A hearing device, which is associated with the ipsilateral ear and is configured to: Determine a first sound pressure level (SPL) of a first spectral portion of the same-side audio signal, the first spectral portion having frequencies included in a first frequency range; Determine a second SPL for a second spectral portion of the same-side audio signal, the second spectral portion having frequencies included in a second frequency range that are higher than the first frequency range; It is determined that the first SPL is at least a threshold SPL greater than the second SPL; The symmetry level between the same-side audio signal and the opposite-side audio signal is determined to be at least a threshold symmetry level; as well as Based on determining that the first SPL is at least greater than the second SPL by the threshold SPL amount, and determining that the symmetry level is at least the threshold symmetry level, the audio content is determined to include the user's own speech content representing the user's speech.

2. The hearing system according to claim 1, wherein, Determining that the first SPL is at least greater than the threshold SPL by the second SPL includes: Determine the ratio between the first SPL and the second SPL; and The ratio between the first SPL and the second SPL is determined to be higher than a threshold ratio associated with the threshold SPL amount.

3. The hearing system according to claim 2, wherein, The first frequency range is between 800 Hz and 1200 Hz, the second frequency range is between 4 kHz and 7 kHz, and the threshold ratio is between 25 and 35.

4. The hearing system according to claim 1, wherein: The hearing device is also configured to determine the total SPL of the ipsilateral audio signal; and The audio content is determined to include its own speech content and the total SPL based on the same-side audio signal.

5. The hearing system according to claim 1, wherein: The hearing device is further configured to: determine, based on the ipsilateral audio signal, that the audio content includes sound content; and The determination that the audio content includes its own speech content is also based on the determination that the audio content includes sound content.

6. The hearing system according to claim 1, wherein: The same-side microphone is configured to detect additional same-side audio signals representing additional audio content; The contralateral microphone is configured to detect an additional contralateral audio signal representing the additional audio content; and The hearing device is also configured to: Determine that the additional symmetry level between the additional same-side audio signal and the additional opposite-side audio signal is less than the threshold symmetry level; and Based on the determination that the additional symmetry level is less than the threshold symmetry level, it is determined that the additional audio content does not include the original speech content.

7. The hearing system according to claim 6, wherein, The hearing device is also configured to: Determine the third SPL of the first spectral portion of the additional same-side audio signal; Determine the fourth SPL of the second spectral portion of the additional same-side audio signal; and The threshold SPL is adjusted based on the difference between the third SPL and the fourth SPL, based on the determination that the additional audio content does not include the original speech content.

8. The hearing system according to claim 7, wherein, Adjusting the threshold SPL value includes using machine learning algorithms.

9. The hearing system according to claim 1, wherein: The same-side microphone is configured to detect additional same-side audio signals representing additional audio content; The contralateral microphone is configured to detect an additional contralateral audio signal representing the additional audio content; and The hearing device is also configured to: Determine the third SPL of the first spectral portion of the additional same-side audio signal; Determine the fourth SPL of the second spectral portion of the additional same-side audio signal; The amount by which the third SPL is greater than the fourth SPL is less than the threshold SPL amount; as well as Based on the determination that the amount by which the third SPL is greater than the fourth SPL is less than the threshold SPL amount, it is determined that the additional audio content does not include the original speech content.

10. The hearing system according to claim 9, wherein: The hearing device is further configured to: determine that the additional symmetry level between the additional ipsilateral audio signal and the additional contralateral audio signal is at least the threshold symmetry level; and Although it is determined that the additional symmetry level is at least the threshold symmetry level, it is still determined that the additional audio content does not include the original speech content.

11. The hearing system according to claim 9, wherein, The hearing device is also configured to adjust the threshold SPL based on the difference between the third SPL and the fourth SPL.

12. The hearing system according to claim 11, wherein, Adjusting the threshold SPL value includes using machine learning algorithms.

13. The hearing system according to claim 1, wherein, The hearing device includes the microphone on the same side.

14. The hearing system of claim 1, further comprising an additional hearing device associated with the contralateral ear and including the contralateral microphone.

15. A system comprising: First hearing device and second hearing device. The first hearing device is associated with the user's ear on the same side and includes a first microphone configured to detect an audio signal from the same side representing audio content; and The second hearing device is associated with the user's contralateral ear and includes a second microphone configured to detect a contralateral audio signal representing the audio content; The first hearing device is configured as follows: Determine a first sound pressure level (SPL) of a first spectral portion of the same-side audio signal, the first spectral portion having frequencies included in a first frequency range; Determine a second SPL for a second spectral portion of the same-side audio signal, the second spectral portion having frequencies included in a second frequency range that are higher than the first frequency range; It is determined that the first SPL is at least a threshold SPL greater than the second SPL; Determine that the level of symmetry between the same-side audio signal and the opposite-side audio signal is at least a threshold level of symmetry; and Based on determining that the first SPL is at least greater than the second SPL by the threshold SPL amount, and determining that the symmetry level is at least the threshold symmetry level, the audio content is determined to include the user's own speech content representing the user's speech.

16. The system according to claim 15, wherein, The second hearing device is configured as follows: Determine the third SPL of the first spectral portion of the contralateral audio signal; Determine the fourth SPL of the second spectral portion of the contralateral audio signal; The third SPL is determined to be at least greater than the fourth SPL by the threshold SPL amount; The symmetry level between the same-side audio signal and the opposite-side audio signal is determined to be at least the threshold symmetry level; as well as Based on determining that the third SPL is at least greater than the fourth SPL by the threshold SPL amount, and determining that the symmetry level is at least the threshold symmetry level, the audio content is determined to include the user's own speech content representing the user's speech.

17. The system according to claim 15, wherein: The first microphone is configured to detect additional same-side audio signals representing additional audio content; The second microphone is configured to: detect additional contralateral audio signals representing the additional audio content; and The first hearing device is also configured to: Determine that the additional symmetry level between the additional same-side audio signal and the additional opposite-side audio signal is less than the threshold symmetry level; and Based on the determination that the additional symmetry level is less than the threshold symmetry level, it is determined that the additional audio content does not include the original speech content.

18. The system according to claim 17, wherein, The first hearing device is also configured to: Determine the third SPL of the first spectral portion of the additional same-side audio signal; Determine the fourth SPL of the second spectral portion of the additional same-side audio signal; and The threshold SPL is adjusted based on the difference between the third SPL and the fourth SPL, based on the determination that the additional audio content does not include the original speech content.

19. The system according to claim 15, wherein: The first microphone is configured to detect additional same-side audio signals representing additional audio content; The second microphone is configured to: detect additional contralateral audio signals representing the additional audio content; and The first hearing device is also configured to: Determine the third SPL of the first spectral portion of the additional same-side audio signal; Determine the fourth SPL of the second spectral portion of the additional same-side audio signal; The amount by which the third SPL is greater than the fourth SPL is less than the threshold SPL amount; as well as Based on the determination that the amount by which the third SPL is greater than the fourth SPL is less than the threshold SPL amount, it is determined that the additional audio content does not include the original speech content.

20. A method comprising: A first sound pressure level (SPL) of a first spectral portion of an audio signal representing audio content is determined using a hearing device associated with the user's ear on the same side, the first spectral portion having frequencies included in a first frequency range; The hearing device determines a second SPL of a second spectral portion of the same-side audio signal, the second spectral portion having frequencies included in a second frequency range that are higher than the first frequency range; The hearing device is used to determine that the first SPL is at least a threshold SPL greater than the second SPL. The hearing device determines that the level of symmetry between the ipsilateral audio signal and the contralateral audio signal representing the audio content is at least a threshold level of symmetry; and Based on determining that the first SPL is at least greater than the second SPL by the threshold SPL amount, and determining that the symmetry level is at least the threshold symmetry level, the audio content is determined to include the user's own speech content representing the user's speech.

Images