Hearing device with own voice detection

Abstract

The invention relates to a hearing device comprising a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; a voice detector module for processing the first microphone input signal and the second microphone input signal, the voice detector module being configured to detect own voice of a user; a processor for providing an electrical output signal; and a receiver for providing an audio output signal, wherein the voice detector module is configured to determine a direction parameter indicative of a direction of a sound source based on the first and / or the second microphone input signal; to determine whether a direction criterion based on the direction parameter is fulfilled; to determine a first distance parameter indicative of a distance to the sound source; to determine whether a distance criterion based on the first distance parameter is fulfilled; and to provide a voice detector output.

Description

Technical Field

[0001] This invention relates to a hearing device and hearing system with its own speech detection. Background Technology

[0002] Hearing devices help users capture and process signals from surrounding speakers and other sources. Microphone array-based beamforming techniques are commonly used to amplify the target signal and suppress interfering sources. These sources are typically at least 1 to 2 meters away from the user; these are known as far-field sources. Of course, hearing devices also capture and process the user's own speech, which can often be uncomfortable for the user due to its perceived unnaturalness and loudness. Detecting the user's own speech within a hearing device remains challenging. Summary of the Invention

[0003] Therefore, there is a need for a hearing device with improved self-speech detection.

[0004] Therefore, a hearing device is disclosed, comprising a set of microphones, including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; a speech detector module connected to the first and second microphones to process the first and second microphone input signals, and the speech detector module being configured to detect the user's own speech; a processing unit for providing an electrical output signal based on the first and second microphone input signals; and a receiver for converting the electrical output signal into an audio output signal. The speech detector module is optionally configured to: determine a directional parameter indicating the direction of a sound source based on one or more microphone input signals from the microphones in the set of microphones, and determine whether a directional criterion is met based on the directional parameter. The speech detector module is optionally configured to determine a first distance parameter (e.g., indicating the distance to a sound source) based on one or more microphone input signals from the microphones in the set of microphones (e.g., the first microphone input signal and / or the second microphone input signal), and optionally determine whether a distance criterion is met based on the first distance parameter. The speech detector module is optionally configured to, for example, provide a speech detector output indicating the detection of its own speech to a processor based on the determination that the directional criterion and / or distance criterion are met.

[0005] A hearing device is disclosed, comprising a set of microphones including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; a speech detector module connected to the first and second microphones to process the first and second microphone input signals, the speech detector module being configured to detect the user's own speech; a processor for processing the first and second microphone input signals to provide an electrical output signal based on the first and second microphone input signals; and a receiver for converting the electrical output signal into an audio output signal, wherein the speech detector module is configured to determine a first distance parameter indicating a distance to a sound source based on one or more microphone input signals from the microphones in the set of microphones; and a speech detector output indicating self-speech detection being provided to the processor, wherein providing the speech detector output indicating self-speech detection includes applying a machine learning module that takes the first distance parameter as input and provides the speech detector output indicating self-speech detection as output.

[0006] Furthermore, a hearing system is disclosed, comprising a first hearing device and a second hearing device, wherein the first hearing device is a hearing device as disclosed herein. The second hearing device may be a hearing device as disclosed herein.

[0007] The present invention can provide improved and more robust self-speech detection, which in turn can improve the processing of microphone input signals, for example, by avoiding over-amplification of the user's own speech. Attached Figure Description

[0008] The above and other features and advantages of the present invention will become apparent to those skilled in the art from the following detailed description of specific embodiments in conjunction with the accompanying drawings.

[0009] in:

[0010] Figure 1 An exemplary hearing device according to the present invention is illustrated schematically;

[0011] Figure 2 An exemplary speech detector module according to the present invention is illustrated schematically;

[0012] Figure 3 An exemplary speech detector module according to the present invention is illustrated schematically; and

[0013] Figure 4 The spectral curves of different sources are shown. Detailed Implementation

[0014] Various exemplary embodiments and details are described below with reference to the accompanying drawings. It should be noted that the drawings may be drawn to scale or not, and elements having similar structures or functions are indicated by similar reference numerals throughout the drawings. It should also be noted that these drawings are intended only to facilitate the description of embodiments and are not intended as an exhaustive description of the invention or as a limitation on the scope of the invention. Furthermore, the illustrated embodiments do not necessarily possess all the aspects or advantages shown. Aspects or advantages described in connection with a particular embodiment are not necessarily limited to that embodiment and may be implemented in any other embodiment even if not so shown or so explicitly described.

[0015] A hearing device is disclosed. During use, the hearing device can be positioned at the user's ear, on the user's ear, above the user's ear, in the user's ear, in the user's ear canal, behind the user's ear, and / or in the user's outer ear; that is, the hearing device is configured to be worn inside, on, above, and / or at the user's ear. The user can wear two hearing devices, one in each ear. These two hearing devices can be connected, for example, wirelessly and / or via wires, such as in a binaural hearing aid system.

[0016] Hearing devices can be various types of hearing devices, such as headphones, headsets, earphones, earplugs, hearing aids, personal speech amplification products (PSAPs), over-the-counter (OTC) hearing devices, hearing protection devices, one-size-fits-all hearing devices, custom-made hearing devices, or other types of hearing devices. Hearing devices can include both prescription and over-the-counter devices.

[0017] Hearing devices can be implemented in various housing styles or form factors. Some form factors are behind-the-ear (BTE) hearing devices, in-the-canal (RIC) hearing devices, in-the-ear (RIE) hearing devices, or hearing devices with a microphone and in-the-ear (MaRIE) receiver. These devices may include a BTE unit and an in-the-ear (ITE) unit, with the BTE unit configured to be worn behind the user's ear and the ITE unit configured to be partially or fully inserted into the user's ear canal. Typically, a BTE unit may include at least one input transducer, a power supply, and a processing unit. The term BTE hearing device refers to a hearing device in which the receiver (i.e., the output transducer) is contained within the BTE unit and speech is guided to the ITE unit via a sound tube connecting the BTE and ITE units, while the terms RIE, RIC, and MaRIE hearing devices refer to hearing devices in which the receiver may be contained within the ITE unit, coupled to the BTE unit via a connector cable or wire configured to transmit electrical signals between the BTE and ITE units.

[0018] Some form factors are in-ear (ITE) hearing aids, completely in-the-canal (CIC) hearing aids, or invisible in-the-canal (IIC) hearing aids. These hearing devices may include an ITE unit, which may include at least one input transducer, a power supply, a processing unit, and an output transducer. These form factors can be custom-designed devices, meaning that the ITE unit may include a housing that can have a shell made of a hard material such as a hard polymer or metal, or a soft material such as a rubber-like polymer, molded to have an external shape that conforms to the shape of a particular user's ear canal.

[0019] Some form factors are earbuds, in-ear headphones, or in-ear headphones. Those skilled in the art will understand the different types of hearing devices and the various options for placing the hearing device inside, on, above, and / or at the ear of the hearing device wearer. Hearing devices (or a pair of hearing devices) can be custom-fit, standard-fit, open-fit, and / or closed-fit.

[0020] In one or more examples, the hearing device may include one or more input transducers. The one or more input transducers include a set of microphones, which may include one or more microphones. The one or more input transducers may include one or more vibration sensors configured to detect bone vibrations. The one or more input transducers may be configured to convert an acoustic signal into a first electrical input signal. The first electrical input signal may be an analog signal. The first electrical input signal may be a digital signal. The one or more input transducers may be coupled to one or more analog-to-digital converters configured to convert the analog first input signal into a digital first input signal.

[0021] In one or more examples, the hearing device may include one or more antennas configured for wireless communication. The one or more antennas may include an electrical antenna. The electrical antenna may be configured to communicate wirelessly at a first frequency. The first frequency may be above 800 MHz, preferably between 900 MHz and 6 GHz. The first frequency may be between 902 MHz and 928 MHz. The first frequency may be between 2.4 and 2.5 GHz. The first frequency may be between 5.725 GHz and 5.875 GHz. The one or more antennas may include a magnetic antenna. The magnetic antenna may include a magnetic core. The magnetic antenna may include a coil. The coil may be wound around the magnetic core. The magnetic antenna may be configured to communicate wirelessly at a second frequency. The second frequency may be below 100 MHz. The second frequency may be between 9 MHz and 15 MHz.

[0022] In one or more examples, the hearing device may include one or more wireless communication units. The one or more wireless communication units may include one or more wireless receivers, one or more wireless transmitters, one or more transmitter-receiver pairs, and / or one or more transceivers. At least one of the one or more wireless communication units may be coupled to one or more antennas. The wireless communication units may be configured to convert wireless signals received by at least one of the one or more antennas into a second electrical input signal. The hearing device may be configured for wired / wireless audio communication, such as enabling a user to listen to media such as music or radio and / or enabling a user to make telephone calls.

[0023] In one or more examples, the wireless signal may originate from one or more external sources and / or external devices, such as a spouse microphone device, a wireless audio transmitter, a smart computer, and / or a distributed microphone array associated with the wireless transmitter. The wireless input signal may come from another hearing device, for example, as part of a binaural hearing system, and / or from one or more accessory devices, such as a smartphone and / or a smartwatch.

[0024] In one or more examples, the hearing device may include a processor. The processor may be configured to process a first and / or a second electrical input signal. This processing may include compensating for a user's hearing loss, i.e., applying a frequency-related gain to the input signal based on the user's frequency-related hearing impairment. The processing may include performing one or more of feedback cancellation, beamforming, tinnitus reduction / masking, noise reduction, noise cancellation, speech recognition, bass adjustment, treble adjustment, and processing user input. The processor may be a processor, integrated circuit, application program, functional module, etc. The processor may be implemented in a signal processing chip or a printed circuit board (PCB). The processor may be configured to provide a (first) electrical output signal based on the processing of the first and / or second electrical input signals. The processor unit may be configured to provide a second electrical output signal. The second electrical output signal may be based on the processing of the first and / or second electrical input signals.

[0025] In one or more examples, the hearing device may include an output transducer. The output transducer may be coupled to a processor. The output transducer may be a receiver. It should be noted that, in this context, the receiver may be a speaker, and a wireless receiver may be a device configured to process wireless signals. The receiver may be configured to convert a (first) electrical output signal into an acoustic output signal, also referred to as an audio output signal. The output transducer may be coupled to the processor unit via a magnetic antenna. The output transducer / receiver may be included in the ITE unit or earpiece of the hearing device, such as an in-ear receiver (RIE) unit or a microphone and in-ear receiver (MaRIE) unit. One or more input transducers may be included in the ITE unit or in headphones.

[0026] In one or more examples, the wireless communication unit can be configured to convert the second electrical output signal into a wireless output signal. The wireless output signal may include synchronization data. The wireless communication unit can be configured to transmit the wireless output signal via at least one of one or more antennas.

[0027] In one or more examples, the hearing device may include a digital-to-analog converter configured to convert a first electrical output signal, a second electrical output signal, and / or a wireless output signal into an analog signal.

[0028] In one or more examples, the hearing device may include a vent. A vent is a physical channel, such as a passage or conduit, primarily used to provide pressure equalization across a housing placed in the ear (e.g., an ITE hearing device, an ITE unit of a BTE hearing device, a CIC hearing device, a RIE hearing device, a RIC hearing device, a MaRIE hearing device, or a domed tip / earmold). The vent may be a pressure vent with a small cross-sectional area, preferably acoustically sealed. The vent may be an acoustic vent configured for occlusion cancellation. The vent may be an active vent, allowing it to be opened or closed during use of the hearing device. An active vent may include a valve.

[0029] In one or more examples, the hearing device may include a power source. The power source may include a battery providing a first voltage. The battery may be a rechargeable battery. The battery may be a replaceable battery. The power source may include a power management unit. The power management unit may be configured to convert the first voltage to a second voltage. The power source may include a charging coil. The charging coil may be provided by a magnetic antenna.

[0030] In one or more examples, the hearing device may include memory, including memory in volatile and non-volatile forms.

[0031] A hearing device may include a set of microphones. This set of microphones may include one or more microphones. The set of microphones includes a first microphone for providing a first microphone input signal, also denoted as m_1, and / or a second microphone for providing a second microphone input signal, also denoted as m_2. The set of microphones may include N microphones for providing N microphone signals, where N is an integer from 1 to 10. In one or more exemplary hearing devices, the number of microphones N is two, three, four, five, or more. The set of microphones may include a third microphone for providing a third microphone input signal, also denoted as m_3.

[0032] The hearing device may include a speech detector module. The speech detector module is configured to detect the presence of speech (e.g., the user's own speech) based on one or more microphone input signals, including a first microphone input signal and / or a second microphone input signal. The speech detector module may be embedded in a processor or formed as a separate unit. The speech detector module is connected to the first microphone and / or the second microphone to process the first microphone input signal and / or the second microphone input signal, and is configured to detect the user's own speech, for example, based on one or more microphone input signals from a microphone group.

[0033] In one or more exemplary hearing devices, the hearing device includes a set of microphones, the set of microphones including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; a speech detector module, connected to the first and second microphones, for processing the first and second microphone input signals, the speech detector module being configured to detect the user's own speech; a processor for processing the first and second microphone input signals to provide an electrical output signal based on the first and second microphone input signals; and a receiver for converting the electrical output signal into an audio output signal, wherein the speech detector module is configured to determine a directional parameter indicating the direction of a sound source based on one or more microphone input signals from the microphones in the set of microphones; determine whether a directional criterion based on the directional parameter is satisfied; determine a first distance parameter indicating the distance from the sound source based on one or more microphone input signals from the microphones in the set of microphones; determine whether a distance criterion based on the first distance parameter is satisfied; and provide a speech detector output indicating its own speech detection to the processor based on the determination that the directional criterion and the distance criterion are satisfied.

[0034] In one or more exemplary hearing devices, determining the first distance parameter includes determining two, three, or more differential / gradient test signals based on one or more microphone input signals, such as m_1, m_2, and m_3. For simplicity, the delay component may not be used in the subtraction because there may be interest in the low-frequency region, where near-field effects are strong, and the wavelength λ >> microphone spacing satisfies the gradient microphone / differential condition.

[0035] In one or more exemplary hearing devices, determining the directional parameter includes determining the cross-correlation between two microphone input signals, such as the cross-correlation between a first microphone input signal from a first microphone and a contralateral first microphone input signal from a first microphone of a contralateral hearing device. In one or more examples, determining the directional parameter includes determining the cross-correlation between a test signal from the hearing device and a corresponding contralateral test signal from the contralateral hearing device. A high correlation between two microphone input signals from microphones arranged symmetrically or substantially symmetrically with respect to the mouth can indicate that the microphone input signals represent audio from a central location or zero direction relative to the user.

[0036] In one or more exemplary hearing devices, determining a first distance parameter includes determining a first test measurement based on a first microphone input signal, and determining the first distance parameter based on the first test measurement. The first test measurement may be denoted as SP_1.

[0037] In one or more exemplary hearing devices, determining a first test measurement SP_1 includes determining a first test signal, also denoted as s_1(t), based on a first microphone input signal m_1. The first test measurement SP_1 may be the power of the first test signal s_1(t). In other words, the first test measurement may be the power spectrum of the first test signal.

[0038] In one or more exemplary hearing devices, determining the first distance parameter includes determining a second test measurement based on a second microphone input signal, and determining the first distance parameter based on the second test measurement. The second test measurement may be denoted as SP_2.

[0039] In one or more exemplary hearing devices, determining the second test measurement includes determining a second test signal, also denoted as s_2(t), based on a second microphone input signal m_2. The second test measurement SP_2 may be the power of the second test signal s_2(t). In other words, the second test measurement may be the power spectrum of the second test signal.

[0040] In one or more exemplary hearing devices, a second test signal s_2(t) is based on a first microphone input signal m_1. The second test signal may be based on a ratio or difference between the second microphone input signal m_2 and the first microphone input signal m_1.

[0041] The second test signal s_2(t) can be a differential / gradient test signal, and optionally it is:

[0042] s_2(t)=m_2-m_1 or s_2(t)=m_1-m_2,

[0043] Where m_1 is the first microphone input signal and m_2 is the second microphone input signal. In one or more examples, the second test signal can be a linear combination of m_1 and m_2.

[0044] In one or more exemplary hearing devices, the hearing device includes a first housing configured to be worn inside or at the ear canal of a user, and a first microphone is an in-ear microphone disposed in the first housing.

[0045] In one or more exemplary hearing devices, the first microphone is a front BTE microphone or a rear BTE microphone disposed in a second housing.

[0046] In one or more exemplary hearing devices, the hearing device includes a second housing configured to be worn behind a user's auricle as a behind-the-ear housing, and a second microphone is a behind-the-ear microphone disposed in the second housing, such as a front BTE microphone or a rear BTE microphone.

[0047] In one or more exemplary hearing devices, the first microphone is a front BTE microphone or a rear BTE microphone disposed in a second housing.

[0048] In one or more exemplary hearing devices, the second microphone is an in-ear microphone disposed in the first housing or a rear BTE microphone disposed in the second housing.

[0049] In one or more exemplary hearing devices, a microphone array includes a third microphone for providing a third microphone input signal, also denoted as m_3. Determining a first distance parameter may optionally include determining a third test measurement, also denoted as SP_3, based on the third microphone input signal. The third test measurement may be based on one or more of the first microphone input signal, the second microphone input signal, and the third microphone input signal. The first distance parameter may be based on the third test measurement. In other words, determining the first distance parameter may include determining the first distance parameter based on the third test measurement.

[0050] In one or more exemplary hearing devices, determining a third test measurement involves determining a third test signal, also denoted as s_3(t), based on a third microphone input signal m_3. The third test measurement SP_3 can be the power of the third test signal s_3(t). In other words, the third test measurement can be the power spectrum of the third test signal.

[0051] The third test signal s_3(t) can be a differential / gradient test signal, and optionally it can be:

[0052] s_3(t) = m_2 - m_3 or s_3(t) = m_3 - m_2,

[0053] Where m_2 is the second microphone input signal and m_3 is the third microphone input signal. In one or more examples, the third test signal can be a linear combination of m_2 and m_3. The third test signal can be based on the ratio or difference between the second microphone input signal m_2 and the third microphone input signal m_3.

[0054] In one or more exemplary hearing devices, the first test signal s_1(t) may be a differential / gradient test signal, and optionally:

[0055] s_1(t) = m_3 – m_1 or s_1(t) = m_1 – m_3,

[0056] Where m_3 is the third microphone input signal and m_1 is the first microphone input signal. In other words, the first test signal can be based on the third microphone input signal. In one or more examples, the first test signal can be a linear combination of m_1 and m_3.

[0057] In one or more exemplary hearing devices, the third microphone is a behind-the-ear microphone (e.g., a rear BTE microphone) disposed in a second housing, for example, wherein the first microphone is an in-ear microphone disposed in the first housing and the second microphone is a front BTE microphone disposed in the second housing.

[0058] In one or more exemplary hearing devices, the third microphone is a front-ear microphone disposed in a second housing, for example, wherein the first microphone is an in-ear microphone disposed in a first housing.

[0059] In one or more exemplary hearing devices, the first distance parameter includes, for example, a first primary distance parameter associated with a primary frequency band and / or a first secondary distance parameter associated with a secondary frequency band. Determining whether a distance criterion based on the first distance parameter is met may include determining whether a primary distance criterion based on the first primary distance parameter is met and / or whether a secondary distance criterion based on the first secondary distance parameter is met.

[0060] The first distance parameter, also represented as DP_1, can be:

[0061]

[0062] Among them, SP_1, SP_2 and SP_3 are the power spectra of the first test signal s_1(t), the second test signal s_2(t) and the third test signal s_3(t), respectively.

[0063] The first distance parameter can be a spectrum, such as a vector (e.g., power) representing values ​​of sub-bands, for example, at least 3 sub-bands, for example, in the range of 5 to 20 sub-bands. The first distance parameter can be a power spectrum vector with 10 sub-bands.

[0064] The first primary distance parameter can be selected or determined as a first distance parameter at or related to the primary frequency band. The primary frequency band can be in the range of 300Hz to 900Hz. The primary frequency band can have a primary center frequency of less than 1kHz, for example, in the range of 400Hz to 800Hz, such as 600Hz.

[0065] The first sub-range parameter can be selected or determined as a first range parameter at or related to the sub-band. The sub-band can be in the range of 1.4 kHz to 2.0 kHz. The sub-band can have a sub-center frequency greater than 1 kHz, for example, in the range of 1.4 kHz to 2.0 kHz, such as 1.7 kHz.

[0066] In one or more exemplary hearing devices, the hearing device includes a transceiver, for example as part of a wireless communication unit, connected to a speech detector module for receiving one or more contralateral input signals from the contralateral hearing device, such as including a first contralateral microphone input signal. A direction criterion may be based on the first contralateral microphone input signal. The first contralateral microphone input signal may originate from a first contralateral microphone of the contralateral hearing device. The first contralateral microphone may be an in-ear microphone disposed within a first housing of the contralateral hearing device.

[0067] In one or more exemplary hearing devices, one or more contralateral input signals include a contralateral speech detector output indicating that one's own speech has been detected in the contralateral hearing device, and wherein the speech detector output indicating the detection of one's own speech may optionally be based on the contralateral speech detector output. For example, the speech detector output may indicate the presence of one's own speech based on the determination that direction and distance criteria are met and the contralateral speech detector output indicates the detection of one's own speech. In other words, the detection of one's own speech may require that direction and distance criteria be met in both the hearing device and the contralateral hearing device.

[0068] In one or more exemplary hearing devices, a speech detector module is configured to determine a second distance parameter indicating the distance to a sound source based on one or more microphone input signals from one or more microphones of a microphone group, such as one or more of m_1, m_2 and m_3, and wherein the distance criterion is based on the second distance parameter.

[0069] In one or more exemplary hearing devices, the second distance parameter includes, for example, a second primary distance parameter related to a primary frequency band and / or a second secondary distance parameter related to a secondary frequency band. Determining whether a distance criterion based on the second distance parameter is met may include determining whether a primary distance criterion based on the second primary distance parameter is met and / or whether a secondary distance criterion based on the second secondary distance parameter is met.

[0070] The second distance parameter of DP_2 can also be expressed as:

[0071]

[0072] Among them, SP_1, SP_2 and SP_3 are the power spectra of the first test signal s_1(t), the second test signal s_2(t) and the third test signal s_3(t), respectively.

[0073] The second distance parameter can be a spectrum, such as a vector (e.g., power) representing values ​​of sub-bands, for example, at least 3 sub-bands, for example, in the range of 5 to 20 sub-bands. The second distance parameter can be a power spectrum vector with 10 sub-bands.

[0074] The second primary distance parameter can be selected or determined as a second distance parameter at or related to the primary frequency band. The primary frequency band can be in the range of 300Hz to 900Hz. The primary frequency band can have a primary center frequency of less than 1kHz, for example, in the range of 400Hz to 800Hz, such as 600Hz.

[0075] The second sub-distance parameter can be selected or determined as a second distance parameter at or related to the sub-band. The sub-band can be in the range of 1.4 kHz to 2.0 kHz. The sub-band can have a sub-center frequency greater than 1 kHz, for example, in the range of 1.4 kHz to 2.0 kHz, such as 1.7 kHz.

[0076] In one or more exemplary hearing devices, the hearing device includes a set of microphones, the set of microphones including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; a speech detector module, connected to the first and second microphones, for processing the first and second microphone input signals, the speech detector module being configured to detect the user's own speech; a processor for processing the first and second microphone input signals to provide an electrical output signal based on the first and second microphone input signals; and a receiver for converting the electrical output signal into an audio output signal, wherein the speech detector module is configured to determine a first distance parameter indicating a distance to a sound source based on one or more microphone input signals from the microphones in the set of microphones; and a speech detector output indicating the detection of its own speech being provided to the processor, wherein providing the speech detector output indicating the detection of its own speech includes applying a machine learning module, the machine learning module taking the first distance parameter as input and providing the speech detector output indicating the detection of its own speech as output.

[0077] In one or more exemplary hearing devices, a speech detector module is configured to determine a second distance parameter indicating the distance to a sound source based on one or more microphone input signals from a microphone in the set of microphones, and wherein a machine learning module takes the first distance parameter and the second distance parameter as input.

[0078] In one or more exemplary hearing devices, a processor may be connected to a speech detector module, wherein the processor is configured to process a first microphone input signal and a second microphone input signal to provide an electrical output signal based on a speech detector output indicating self-speech detection. For example, the processor may be configured to adjust the amplification of the first microphone input signal and / or the second microphone input signal based on self-speech detection, for example by reducing one or more gains when self-speech is detected.

[0079] In one or more exemplary hearing devices, a processor may be configured to adjust the beamforming of a first microphone input signal and / or a second microphone input signal based on its own speech detection, for example, by increasing the bandwidth of the beamforming when its own speech is not detected and / or decreasing the bandwidth of the beamforming when its own speech is detected.

[0080] The machine learning module can be a Gaussian distribution module trained on a large set of near-field and far-field first distance parameters.

[0081] In one or more exemplary hearing devices, the processor may be configured to control the ventilation components of the hearing device based on its own speech detection, for example, by increasing ventilation when its own speech is detected and / or reducing ventilation when its own speech is not detected.

[0082] Figure 1 An exemplary hearing device 2 according to the present invention is shown, such as a first hearing device 2A and / or a second hearing device 2B. The hearing device 2 is a MaRiE type hearing aid and includes a first housing 4 and a second housing 6, wherein the first housing 4 is configured to be worn in or at the ear canal of a user, and the second housing 6 is configured to be worn behind the ear of a user. The hearing device 2 includes a set of microphones, including a first microphone 8 for providing a first microphone input signal 8A (also denoted as m_1), a second microphone 10 for providing a second microphone input signal 10A (also denoted as m_2), and a third microphone 12 for providing a third microphone input signal 12A. The hearing device 2 includes a voice detector module 14 connected to microphones 8, 10, and 12 for processing microphone input signals 8A, 10A, and 12A; the voice detector module is configured to detect the user's own voice; a processor 16 for processing the first microphone input signal 8A and the second microphone input signal 10A to provide an electrical output signal 16A based on the first microphone input signal 8A and the second microphone input signal 10A; and a receiver 18 for converting the electrical output signal 16A into an audio output signal.

[0083] The hearing device 2 includes a wireless communication unit 20, which includes a transceiver 22 and an antenna 24 coupled to the transceiver 22. The wireless communication unit 18 is configured to perform wireless communication, for example, using the contralateral hearing device, as indicated by arrow 26. The transceiver 22 / wireless communication unit 18 is configured to convert a wireless input signal including one or more contralateral input signals 27 into one or more transceiver input signals 28 including a first contralateral microphone input signal 28A.

[0084] The processor 16 is configured to process one or more input signals 8A, 10A, 12A, 28, and to provide an electrical output signal 16A based on one or more of the input signals 8A, 10A, 12A, 28.

[0085] The speech detector module 14 is configured to provide the processor 16 with a speech detector output 14A indicating its own speech detection. The processor 16 is configured to control the processing of input signals 8A, 10A, 12A, and 28 based on the speech detector output 14A. In other words, the speech detector output 14A is a control signal.

[0086] Optionally, the hearing device 2 includes a button 30 for receiving user input from the user.

[0087] Figure 2 An exemplary speech detector module is shown. Speech detector module 14 includes bandpass filters BP_1, BP_2, BP_3, and CBP for bandpass filtering the corresponding microphone input signals 8A, 10A, 12A and the opposite microphone input signal 28A. Speech detector module 14 includes a correlator or direction determiner 32 configured to determine and output a direction parameter DIRP indicating the direction of the sound source based on the first microphone input signal 8A and the opposite microphone input signal 28A, for example, by cross-correlating the first microphone input signal 8A with the opposite microphone input signal 28A. The low or no time difference between the first microphone input signal 8A and the opposite microphone input signal 28A indicated by DIRP can be used to determine whether the sound source is centered in front of the user, i.e., whether the sound is the user's own speech.

[0088] Furthermore, the voice detector module 14 is configured to determine a first distance parameter DP_1, indicating the distance to a sound source, based on one or more microphone input signals from microphones in the group of microphones, by determining a first test measurement SP_1, a second test measurement SP_2, and a third test measurement SP_3 in corresponding first determiners 34 or blocks, second determiners 36 or blocks, and third determiners 38 or blocks. Test measurements SP_1, SP_2, and SP_3 represent the power of the corresponding first test signal s_1(t), second test signal s_2(t), and third test signal s_3(t), respectively. Test measurement SP_i, i = 1, 2, 3, can be the total power in one or more frequency bands of the test signal s_i(t). In other words, the voice detector module 14 includes a distance parameter determiner 40 or block configured to determine one or more distance parameters, such as the first distance parameter DP_1 and / or the second distance parameter DP_2.

[0089] The speech detector module 14 is configured to, within the criterion determiner 42 or block, determine whether a distance criterion based on the first distance parameter is met, for example, if the first distance parameter meets one or more thresholds. For example, the distance criterion can be met if a first primary distance parameter in the first distance parameter meets a first primary threshold and / or a first secondary distance parameter of the first distance parameter meets a first secondary threshold.

[0090] Optionally or in combination, the speech detector module 14 can be configured to determine whether a distance criterion based on the second distance parameter is met, for example, if the second distance parameter meets one or more thresholds. For example, the distance criterion can be met if the second primary distance parameter of the second distance parameter meets a second primary threshold and / or the second secondary distance parameter of the second distance parameter meets a first secondary threshold.

[0091] The speech detector module 14 is configured to provide the processor with a speech detector output indicating the detection of its own speech based on the determination of the direction and distance criteria, for example, "1" when its own speech is detected and "0" when its own speech is not detected.

[0092] The first test signal s_1(t) is defined as s_1(t)=m_3–m_1, where m_1 is the first microphone input signal or the first microphone input signal with bandpass filtering, and m_3 is the third microphone input signal or the third microphone input signal with bandpass filtering.

[0093] The second test signal s_2(t) is defined as s_2(t)=m_2–m_1, where m_1 is the first microphone input signal or the first microphone input signal with bandpass filtering, and m_2 is the second microphone input signal or the second microphone input signal with bandpass filtering.

[0094] The third test signal s_3(t) is defined as s_3(t)=m_2–m_3, where m_2 is the second microphone input signal or the second microphone input signal with bandpass filtering, and m_3 is the third microphone input signal or the third microphone input signal with bandpass filtering.

[0095] Figure 3 An exemplary speech detector module is shown. The speech detector module 14B includes an ML block or module 44 that takes one or more of a first distance parameter DP_1, a second distance parameter DP_2, and a direction parameter DIRP as input, and provides a speech detector output 14A indicating its own speech detection as output.

[0096] Figure 4 The spectral curves of the first distance parameter DP_1 for different sources are shown, where curve 100 is a far-field source with an elevation angle of 75° and an azimuth of 0°, curve 102 is a far-field source with an elevation angle of 90° and an azimuth of -15°, curve 104 is a far-field source with an elevation angle of 90° and an azimuth of 0°, dashed line 106 is a near-field source with an elevation angle of 90° and an azimuth of 0°, curve 108 is a far-field source with an elevation angle of 90° and an azimuth of 15°, and curve 110 is a far-field source with an elevation angle of 105° and an azimuth of 0°. Figure 4 The curves clearly show that speech detection based on the first distance parameter can distinguish between near-field sources (one's own speech) and far-field sources (other speakers).

[0097] It should be understood that the characteristic descriptions associated with hearing devices also apply to the corresponding methods of operating hearing devices, and vice versa.

[0098] The use of terms such as "first," "second," "third," and "fourth," "primary," "secondary," and "third-level" does not imply any specific order, but rather serves to identify individual elements. Furthermore, the use of terms such as "first," "second," "third," and "fourth," "primary," "secondary," and "third-level" does not indicate any order or importance, but rather distinguishes one element from another. It is important to note that the words "first," "second," "third," and "fourth," "primary," "secondary," and "third-level" used here and elsewhere are for labelling purposes only and do not indicate any specific spatial or temporal order.

[0099] Furthermore, marking the first element does not imply the existence of the second element, and vice versa.

[0100] Understandable. Figure 1-3 This includes modules or operations shown in solid lines and modules or operations shown in dashed lines. Modules or operations included in solid lines are those included in the most widely exemplary implementation. Modules or operations included in dashed lines are exemplary implementations that may be included in or part of the modules or operations of the solid-line exemplary implementation, or may be other modules or operations that can be taken besides those of the solid-line exemplary implementation. It should be understood that these operations do not need to be performed in the order presented. Furthermore, it should be understood that not all operations need to be performed. Exemplary operations can be performed in any order and in any combination.

[0101] It should be noted that the word "including" does not necessarily exclude the existence of other elements or steps not listed.

[0102] It should be noted that the word "one" or "a" preceding a component does not preclude the existence of multiple such components.

[0103] It should also be noted that no reference numerals in the drawings limit the scope of the claims, exemplary embodiments may be implemented at least in part by hardware and software, and multiple instances of “method,” “unit,” or “apparatus” may be represented by the same hardware item.

[0104] The various example methods, apparatuses, and systems described herein are described in the general context of method steps that can be implemented in one aspect by a computer program product contained in a computer-readable medium, including computer-executable instructions, such as program code, that are executed by a computer in a networked environment. Computer-readable media may include removable and non-removable storage devices, including but not limited to read-only memory (ROM), random access memory (RAM), optical disc (CD), digital versatile disc (DVD), etc. Typically, program modules may include routines, programs, objects, components, data structures, etc., that perform a specified task or implement a particular abstract data type. Computer-executable instructions, associated data structures, and program modules represent examples of program code for performing steps of the methods disclosed herein. A particular sequence of such executable instructions or associated data structures represents examples of corresponding actions for implementing the functionality described in such steps or processes.

[0105] The following items disclose one or more of the features described in this article:

[0106] Project 1. A hearing device, comprising:

[0107] A set of microphones, including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal;

[0108] A voice detector module is connected to a first microphone and a second microphone to process the first microphone input signal and the second microphone input signal, and the voice detector module is configured to detect the user's own voice of the hearing device;

[0109] Processor, configured to process the first microphone input signal and the second microphone input signal based on the first microphone input signal and the second microphone input signal to provide an electrical output signal; and

[0110] A receiver used to convert electrical output signals into audio output signals;

[0111] The speech detector module is configured as follows:

[0112] The directional parameters indicating the direction of the sound source are determined based on one or more input signals from the microphones in this group of microphones;

[0113] Determine whether the orientation criteria based on orientation parameters are met;

[0114] A first distance parameter indicating the distance to the sound source is determined based on one or more microphone input signals from the microphones of the microphone group;

[0115] Determine whether the distance criterion based on the first distance parameter is met; and

[0116] Based on the determined direction and distance criteria, a speech detector outputs an indication of its own speech detection to the processor.

[0117] Project 2. According to the hearing device described in Project 1, determining the first distance parameter includes:

[0118] The first test measurement is determined based on the input signal from the first microphone; and

[0119] The first distance parameter is determined based on the first test measurement.

[0120] Project 3. The hearing device according to Project 2, wherein determining the first test measurement includes determining a first test signal based on a first microphone input signal and determining the first test measurement as the power of the first test signal.

[0121] Item 4. The hearing device according to any one of Items 2 to 3, wherein determining the first distance parameter includes:

[0122] The second test measurement is determined based on the input signal from the second microphone, and

[0123] The first distance parameter is determined based on the second test measurement.

[0124] Item 5. The hearing device according to Item 4, wherein determining the second test measurement includes determining the power of the test signal based on the second microphone input signal and determining the second test measurement as the power of the test signal.

[0125] Item 6. The hearing device according to Item 5, wherein the second test signal is based on the first microphone input signal.

[0126] Item 7. The hearing device according to any one of Items 1 to 6, wherein the hearing device includes a first housing configured to be worn in or at the ear canal of a user, and the first microphone is an in-ear microphone disposed in the first housing.

[0127] Item 8. The hearing device according to any one of Items 1 to 7, the hearing device further comprising a second housing configured to be worn behind the user's auricle as a postauricular housing, and a second microphone being a postauricular microphone disposed within the second housing.

[0128] Item 9. The hearing device according to any one of Items 1 to 8, wherein a set of microphones includes a third microphone for providing a third microphone input signal; and wherein determining the first distance parameter includes determining a third test measurement based on the third microphone input signal and determining the first distance parameter based on the third test measurement.

[0129] Item 10. The hearing device according to Item 9, wherein determining the third test measurement includes determining the power of the third test signal based on the third microphone input signal and determining the third test measurement as the power of the third test signal.

[0130] Item 11. The hearing device according to any one of Items 9 and 10, wherein the third microphone is a behind-the-ear microphone disposed in the second housing.

[0131] Item 12. The hearing device according to any one of Items 1 to 11, wherein the first distance parameter includes a first primary distance parameter related to the primary frequency band and a first secondary distance parameter related to the secondary frequency band, and wherein determining whether a distance criterion based on the first primary distance parameter is satisfied includes determining whether a primary distance criterion based on the first primary distance parameter is satisfied and whether a secondary distance criterion based on the first secondary distance parameter is satisfied.

[0132] Item 13. The hearing device according to any one of Items 1 to 12, wherein the hearing device includes a transceiver connected to a speech detector module for receiving one or more contralateral input signals from a contralateral hearing device, and wherein the direction criterion is based on a first contralateral microphone input signal from a first contralateral microphone of the contralateral hearing device.

[0133] Item 14. The hearing device according to Item 13, wherein one or more contralateral input signals include the output of a contralateral speech detector indicative of self-speech detection in the contralateral hearing device, and wherein the speech detector output indicative of self-speech detection is based on the contralateral speech detector output.

[0134] Item 15. The hearing device according to any one of Items 1 to 14, wherein the speech detector module is configured to determine a second distance parameter indicating the distance to a sound source based on one or more microphone input signals from the microphones of the microphone group, and wherein the distance criterion is based on the second distance parameter.

[0135] Item 16. A hearing device, comprising:

[0136] A set of microphones, including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal;

[0137] A voice detector module, connected to a first microphone and a second microphone, is used to process the first microphone input signal and the second microphone input signal. The voice detector module is configured to detect the user's own voice of the hearing device.

[0138] A processor is configured to process a first microphone input signal and a second microphone input signal to provide an electrical output signal based on the first microphone input signal and the second microphone input signal; and

[0139] The receiver converts the electrical output signal into an audio output signal.

[0140] The speech detector module is configured as follows:

[0141] A first distance parameter indicating the distance to a sound source is determined based on one or more microphone input signals from the microphones of the microphone array; and

[0142] The processor is provided with a speech detector output indicating its own speech detection, wherein providing the speech detector output indicating its own speech detection includes applying a machine learning module, which takes a first distance parameter as input and provides a speech detection output indicating its own voice detection as output.

[0143] Item 17. The hearing device according to Item 16, wherein the speech detector module is configured to determine a second distance parameter indicating the distance to a sound source based on one or more microphone input signals from a microphone in a set of microphones, and wherein the machine learning module takes the first distance parameter and the second distance parameter as input.

[0144] Item 18. The hearing device according to any one of Items 16-17, wherein the speech detector module is configured to determine a directional standard indicating the direction to a sound source based on one or more microphone input signals from the microphones in the group of microphones, and wherein the machine learning module takes the directional parameters as input.

[0145] Item 19. A hearing system comprising a first hearing device and a second hearing device, wherein the first hearing device is a hearing device according to any one of items 1 to 18, and the second hearing device is another hearing device according to any one of items 1 to 18.

[0146] Although features have been shown and described, it should be understood that they are not intended to limit the claimed invention, and it will be apparent to those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of the claimed invention. Therefore, the specification and drawings should be considered illustrative, not restrictive. The claimed invention is intended to cover all alternatives, modifications, and equivalents.

[0147] List of reference numerals in the attached diagram:

[0148] 2 Hearing devices

[0149] 2A First Hearing Device

[0150] 2B Second Hearing Device

[0151] 4 First shell

[0152] 6 Second shell

[0153] 8 First Microphone

[0154] 8A First Microphone Input Signal

[0155] 10 Second microphone

[0156] 10A Second Microphone Input Signal

[0157] 12 Third Microphone

[0158] 12A Third Microphone Input Signal

[0159] 13 Memory

[0160] 14. Speech Detector Module

[0161] 14A speech detector output

[0162] 16 processors / processing units

[0163] 16A electrical output signal

[0164] 18 receivers

[0165] 20 wireless communication units

[0166] 22 transceivers

[0167] 24 antennas

[0168] 26 Wireless Communication

[0169] 27 One or more contralateral input signals

[0170] 28 Transceiver Input Signals

[0171] 28A opposite side microphone input signal

[0172] 30 buttons

[0173] 32 correlators, direction determiners

[0174] 34 First Determiner

[0175] 36 Second Determiner

[0176] 38 Third Determiner

[0177] 40 Distance Parameter Determiner

[0178] 42 Standard Determiner

[0179] 44 Machine Learning Module

Claims

1. A hearing device, comprising: A set of microphones, including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; A voice detector module connected to the first microphone and the second microphone, wherein the voice detector module is configured to process the first microphone input signal and the second microphone input signal, and detect the user's own voice of the hearing device; A processing unit configured to provide an electrical output signal based on the first microphone input signal and the second microphone input signal; and A receiver configured to provide an audio output signal based on the electrical output signal; The speech detector module is configured as follows: A directional parameter indicating the direction of the sound source is determined based on the first microphone input signal and / or the second microphone input signal; Determine whether the direction standard is met based on the aforementioned direction parameters; A first distance parameter indicating the distance to the sound source is determined based on the first microphone input signal and / or the second microphone input signal, wherein determining the first distance parameter includes: determining a second test measurement based on the second microphone input signal, and determining the first distance parameter based on the second test measurement, wherein the second test measurement is determined by determining the second test signal based on the first microphone input signal and the second microphone input signal, and determining the power of the second test signal as the second test measurement; Based on the first distance parameter, determine whether the distance standard is met; and Based on the determined direction and distance criteria, a voice detector output is provided that indicates the detection of the user's own voice.

2. The hearing device according to claim 1, wherein, The voice detector module is configured to determine the first distance parameter in the following manner: The first test measurement is determined based on the first microphone input signal; and The first distance parameter is determined based on the first test measurement.

3. The hearing device according to claim 2, wherein, The voice detector module is configured to determine the first test measurement by determining a test signal based on the first microphone input signal and determining the power of the test signal as the first test measurement.

4. The hearing device according to claim 1, wherein, The set of microphones includes a third microphone for providing a third microphone input signal; and The voice detector module is configured to determine the first distance parameter by determining a third test measurement based on the third microphone input signal and determining the first distance parameter based on the third test measurement.

5. The hearing device according to claim 4, wherein, The voice detector module is configured to determine the third test measurement by determining a test signal based on the third microphone input signal and determining the power of the test signal as the third test measurement.

6. The hearing device according to claim 4, wherein, The third microphone is a behind-the-ear microphone located in the ear canal housing.

7. The hearing device of claim 1 further includes an earphone housing, the earphone housing being configured to be worn in the user's ear canal or on the ear, wherein, The first microphone is an in-ear microphone located in the earphone housing.

8. The hearing device of claim 1, further comprising a postauricular housing configured to be worn behind the user's auricle, wherein, The second microphone is a behind-the-ear microphone located in the behind-the-ear housing.

9. The hearing device according to claim 1, wherein, The first distance parameter includes a first primary distance parameter related to the primary frequency band and a first secondary distance parameter related to the secondary frequency band, wherein the speech detector module is configured to determine whether the distance standard is met by determining whether the primary distance standard is met based on the first primary distance parameter and whether the secondary distance standard is met based on the first secondary distance parameter.

10. The hearing device according to claim 1, further comprising a transceiver connected to the speech detector module, wherein, The transceiver is configured to receive one or more contralateral input signals from the contralateral hearing device.

11. The hearing device according to claim 1, wherein, The speech detector module is configured to determine a second distance parameter, wherein the speech detector module is configured to determine whether the distance criterion is met based on the second distance parameter.

12. The hearing device according to claim 1, wherein, The speech detector module is configured to apply a machine learning model, wherein the machine learning model is configured to obtain the first distance parameter and provide the speech detector output indicating the detection of the user's own speech.

13. A hearing system, comprising a first hearing device and a second hearing device, wherein, The first hearing device is The second hearing device is another hearing device according to claim 1.

14. A hearing device, comprising: A set of microphones, including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; A voice detector module connected to the first microphone and the second microphone, wherein the voice detector module is configured to process the first microphone input signal and the second microphone input signal, and detect the user's own voice of the hearing device; A processing unit configured to provide an electrical output signal based on the first microphone input signal and the second microphone input signal; and A receiver configured to provide an audio output signal based on the electrical output signal; The speech detector module is configured as follows: A directional parameter indicating the direction of the sound source is determined based on the first microphone input signal and / or the second microphone input signal; Determine whether the direction standard is met based on the aforementioned direction parameters; A first distance parameter indicating the distance to the sound source is determined based on the first microphone input signal and / or the second microphone input signal, wherein determining the first distance parameter includes: determining a second test measurement based on the second microphone input signal, and determining the first distance parameter based on the second test measurement, wherein the second test measurement is determined by determining the second test signal based on the first microphone input signal and the second microphone input signal, and determining the power of the second test signal as the second test measurement; Determine whether the distance standard is met based on the first distance parameter; and Based on determining that the direction and distance criteria are satisfied, a speech detector output is provided that indicates the detection of the user's own speech. The hearing device further includes a transceiver connected to the speech detector module, wherein the transceiver is configured to receive one or more contralateral input signals from the contralateral hearing device; and Wherein, the one or more contralateral input signals include a first contralateral microphone of the contralateral hearing device, and wherein, the speech detector module is configured to further determine whether the directional criterion is met based on the first contralateral microphone input signal from the first contralateral microphone of the contralateral hearing device.

15. A hearing device, comprising: A set of microphones, including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; A voice detector module connected to the first microphone and the second microphone, wherein the voice detector module is configured to process the first microphone input signal and the second microphone input signal, and detect the user's own voice of the hearing device; A processing unit configured to provide an electrical output signal based on the first microphone input signal and the second microphone input signal; and A receiver configured to provide an audio output signal based on the electrical output signal; The speech detector module is configured as follows: A directional parameter indicating the direction of the sound source is determined based on the first microphone input signal and / or the second microphone input signal; Determine whether the direction standard is met based on the aforementioned direction parameters; A first distance parameter indicating the distance to the sound source is determined based on the first microphone input signal and / or the second microphone input signal, wherein determining the first distance parameter includes: determining a second test measurement based on the second microphone input signal, and determining the first distance parameter based on the second test measurement, wherein the second test measurement is determined by determining the second test signal based on the first microphone input signal and the second microphone input signal, and determining the power of the second test signal as the second test measurement; Determine whether the distance standard is met based on the first distance parameter; and Based on determining that the direction and distance criteria are satisfied, a speech detector output is provided that indicates the detection of the user's own speech. The hearing device further includes a transceiver connected to the speech detector module, wherein the transceiver is configured to receive one or more contralateral input signals from the contralateral hearing device; and Wherein, the one or more contralateral input signals include a contralateral speech detector output indicating self-speech detection by the contralateral hearing device, and wherein the speech detector output is based on the contralateral speech detector output.

16. A hearing device, comprising: A set of microphones, including a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; A voice detector module connected to the first microphone and the second microphone, wherein the voice detector module is configured to process the first microphone input signal and the second microphone input signal, and detect the user's own voice of the hearing device; A processing unit configured to provide an electrical output signal based on the first microphone input signal and the second microphone input signal; and A receiver configured to provide an audio output signal based on the electrical output signal; The speech detector module is configured as follows: A first distance parameter indicating the distance to a sound source is determined based on the first microphone input signal and / or the second microphone input signal, wherein determining the first distance parameter includes: determining a second test measurement based on the second microphone input signal, and determining the first distance parameter based on the second test measurement, wherein the second test measurement is determined by determining a second test signal based on the first microphone input signal and the second microphone input signal, and determining the power of the second test signal as the second test measurement; and Provides the output of a speech detector that indicates the detection of its own speech. The speech detector module is configured to apply a machine learning module, which is configured to obtain the first distance parameter as input and provide the speech detection output indicating the detection of its own speech.

17. The hearing device according to claim 16, wherein, The speech detector module is configured to determine a second distance parameter, and the machine learning module is configured to obtain the first distance parameter and the second distance parameter as input.

18. The hearing device according to claim 16, wherein, The speech detector module is configured to determine a direction parameter indicating the direction of the sound source based on the first microphone input signal and / or the second microphone input signal, and wherein the machine learning module is configured to obtain the direction parameter as input.

Images