Hearing aid and binaural hearing aid system comprising binaural processing

Abstract

A hearing aid and a binaural hearing aid system comprising binaural processing are disclosed, wherein the hearing aid comprises an input unit, a wake-up word detector configured to identify a specific wake-up word based on an electrical input signal or a signal derived therefrom and to provide a wake-up word control signal indicating whether or with what probability the wake-up word was detected, and / or a self voice detector configured to estimate whether or with what probability an electrical input signal or a signal derived therefrom is derived from the user's voice and to provide a self voice control signal indicating the result of the estimation, a transceiver circuit configured to establish a communication link to another hearing aid of the binaural hearing aid system, thereby enabling the electrical input signal or a signal derived therefrom to be transmitted to the other hearing aid and / or to be received from the other hearing aid, and a pre-processor configured to control the transceiver circuit in dependence on the wake-up word control signal or in dependence on the self voice control signal.

Description

Technical Field

[0001] This application relates to hearing devices such as hearing aids, and more particularly to activating functional features in a hearing aid using voice control, such as activating binaural processing in a binaural hearing aid system. Background Technology

[0002] An important application of hearing devices is wake word or keyword detection. A wake word is a specific word (e.g., a specific keyword among several specific keywords) spoken by a hearing device user, for example, to enable (or disable) the hearing device or the function of a device or system communicating with the hearing device. Wake word detection or keyword detection can be an integral part of the hearing device. Summary of the Invention

[0003] The detection of wake words or keywords allows for more thorough computation in an external device. A cost-effective (i.e., computationally and / or power-friendly) method for wake word detection in a binaural hearing aid system is local detection within one of the hearing instruments. A more accurate but more expensive method is based on microphone detection from both hearing instruments, as this requires binaural data exchange (and data transmission between hearing instruments is a significant power consumer in binaural hearing systems). Therefore, it is important to transmit only audio data when necessary. The availability of binaural audio signals enables further signal processing (and thus, for example, achieving better confidence in the resulting parameters such as wake words / keywords and, for example, initiating binaural noise reduction, including binaural directionality).

[0004] The possibility of binaural processing for hearing device microphones may be advantageous because binaural noise reduction can be applied to attenuate background noise, thereby improving the accuracy of wake word / keyword detection or enhancing speech recognition.

[0005] On the one hand, the hearing aid (or binaural hearing aid system) is configured to begin transmitting audio data (to another device, such as another hearing aid) and stop transmitting audio data (to another device, such as another hearing aid) based on asymmetric conditions. The start of transmission may be based, for example, on the detection of a wake word and / or the detection of the user's own voice. The stop of transmission may be based, for example, on the termination of the detection of the user's own voice, such as the absence of the user's own voice for a period of time, such as ≥5s or ≥10s. The stop of transmission may also be based on the absence of the user's own voice and the absence of a wake word (or the detection of a specific "stop word" such as "stop transmission") for a period of time.

[0006] Hearing aids (such as binaural hearing aid systems)

[0007] In one aspect of this application, a hearing aid (such as a binaural hearing aid system) configured for wear by a user is provided. The hearing aid may include:

[0008] - Input unit, configured to provide an electrical input signal representing sound;

[0009] - A wake-word detector, configured to identify a specific wake-word based on the electrical input signal or a signal derived therefrom, and to provide a wake-word control signal indicating whether or with what probability the wake-word is detected; and / or

[0010] - A self-voice detector configured to estimate whether or with what probability the electrical input signal or a signal derived therefrom originates from a user's voice and to provide a self-voice control signal indicating the aforementioned estimation result.

[0011] The hearing aid may also include transceiver circuitry configured to establish a communication link to another hearing aid (such as another hearing aid in a binaural hearing aid system), thereby enabling the transmission and / or reception of the electrical input signal or a signal derived therefrom to the other hearing aid. The hearing aid may also include a preprocessor configured to control the transceiver circuitry based on the wake-word control signal and / or based on the self-voice control signal.

[0012] This can improve the control of hearing aids or binaural hearing aid systems.

[0013] The term "input unit" may be replaced by "input stage," "input section," "input module," or "input interface," or a similar structure for providing an electrical input signal or data representing sound. An input unit may include an input converter, such as a microphone, for providing an electrical input signal. An input unit may include a wireless receiver for receiving audio signals from another device, such as from the contralateral hearing aid in a binaural hearing aid system, or from an external processing device. An input unit may include an analog-to-digital converter for providing the electrical input signal as a digitized sample stream (i.e., a digitized electrical input signal). An input unit may include an analysis filter bank for providing the digitized electrical input signal in a time-frequency representation (k, l), for example, as consecutive time frames, each time frame comprising multiple time-frequency units, each time-frequency unit comprising the (e.g., complex) value of the signal at a given frequency k and time l. A given time frame l comprising time-frequency units (k, l) spanning frequency exponents k = 1, ..., K constitutes an estimated spectrum of the electrical input signal at time exponent l.

[0014] The preprocessor can be configured to enable and disable transceiver circuitry based on wake-word control signals or self-voice control signals.

[0015] "The other hearing aid" can be the hearing aid on the opposite side of a binaural hearing aid system.

[0016] Therefore, a triggering procedure for enabling binaural processing is provided. First, the local triggering phase enabling binaural communication may be based on a) the detection of a specific keyword (referred to herein as a wake word) or b) the detection of the user's self-voice. Second, the binaural triggering phase may enable other functions of the hearing aid or binaural hearing aid system or the transmission of trigger data to external devices, for example, for further processing or for enabling functions of external devices or other devices or systems (e.g., via a network). The binaural phase may, for example, be based on wake word detection or self-voice detection, which is based on binaural signals. Binaural wake word detection or self-voice detection may, for example, be based on A) a comparison of two wake word control signals or two self-voice control signals; or B) a corresponding binaural wake word control signal or self-voice control signal determined from the electrical input signals of the two hearing aids of the binaural hearing aid system or signals derived therefrom.

[0017] Using self-voice detection as a local trigger to enable binaural communication, for example, can be adapted to the telephone operating mode of a hearing aid. In this case, improving self-voice detection and / or self-voice estimation based on binaural signals may be advantageous. Similarly, a general keyword detection system for a voice control interface can benefit from local wake word detection and / or self-voice detection to trigger binaural processing of electrical input signals or signals derived therefrom.

[0018] In the expression “electrical input signal or signal derived therefrom”, “signal derived therefrom” can mean, for example, a processed version of the electrical input signal such as its spectrum (e.g., amplitude spectrum), its envelope, its filtered portion, or its downsampled version.

[0019] The hearing aid may include a binaural low-power mode (for energy saving) for its transceiver circuitry. In this low-power mode, only control signals are exchanged between the hearing aid and the "other hearing aid." Such control signals may be signals used to synchronize the basic functions of the binaural hearing system (including the hearing aid and the "other hearing aid"), such as signals regarding basic timing information (e.g., clock), noise reduction (e.g., SNR, level), etc. No audio signals are transmitted (or received) in this low-power mode. The hearing aid may be configured to enter the binaural low-power mode when binaural communication according to the invention is not enabled.

[0020] The hearing aid can be configured to enter an "audio exchange mode" based on a wake-word control signal or a self-voice control signal (e.g., when a wake-word or user self-voice is detected or detected with a probability above a threshold), including initiating the transmission of an electrical input signal or a signal derived therefrom to another hearing aid. The hearing aid can be configured to stop transmission after a certain time has elapsed. The hearing aid can also be configured to stop transmission based on a self-voice control signal (e.g., when user self-voice is not detected (or detected with a probability below a threshold), or when a certain time has elapsed since the detection of user self-voice, for example, with a probability above a threshold). The hearing aid can also be configured to stop transmission based on the detection of a specific stop word by the wake-word detector. The "stop word" can be a unique word (e.g., "stop") used to cause the transceiver circuitry to enter a low-power (non-audio exchange) mode. The "stop word" can be the same as the wake-word. The hearing aid can be configured to switch between two operating modes based on the detection of a wake-word (possibly when it is detected being spoken by the user of the hearing aid). The hearing aid can be configured to switch from audio exchange mode to low-power mode upon detection of a wake-word. Hearing aids can be configured to trigger a switch between two operating modes by being quiet or having no voice / self-voice for a certain period of time.

[0021] The start and stop of transmission can be based on asymmetric conditions. The start of transmission can be based, for example, on the detection of a wake word and / or the detection of user self-voice. The stop of transmission can be based, for example, on the termination of the detection of user self-voice, such as if no user self-voice is detected within a certain time, such as ≥5s or ≥10s.

[0022] The hearing aid may include a buffer configured to store an electrical input signal or a signal derived therefrom for a period of time. The buffer may be configured to enable storage of a period of time including a wake word. Thus, the hearing aid will be able to include a wake word in the data stream transmitted to another hearing aid. The aforementioned period of time may cover a period of time greater than 500 ms, for example, in the range of 500 ms to 2 seconds.

[0023] Wake word detection can rely on simultaneous detection of the user's own speech. In other words, the hearing aid may include a wake word detector and a self-speech detector. In this embodiment, the wake word must be detected simultaneously with the user's self-speech (i.e., the wake word spoken by the user must be detected) to enable the establishment of a communication link to another hearing aid. This increases the confidence level of wake word detection.

[0024] The input unit can be configured to provide at least two electrical input signals representing the sound. The input unit may include at least two input transducers, such as microphones, for providing the at least two electrical input signals. The at least two input transducers may include accelerometers for picking up vibrations of a user's tissue, flesh, or bone.

[0025] At least one of the electrical input signals may be received wirelessly. At least one of the electrical input signals may be received from another device, such as a wireless microphone (from a device worn by the user, such as a smartphone), such as another hearing aid located in the user's opposite ear (e.g., another ("opposite") hearing aid in a binaural hearing aid system).

[0026] Hearing aids may include a directional system comprising a self-voice beamformer configured to focus on the user's mouth when the hearing aid is mounted on the user's body. The self-voice beamformer may be used in conjunction with self-voice detection to determine the presence (or probability of presence) of the user's self-voice at a given point in time. The self-voice beamformer may be configured to provide an estimate of the user's self-voice at a given point in time, such as in a particular operating mode. However, the hearing aid may also be configured to provide the estimate of the user's self-voice to a wake word detector, for example, to increase detection quality (since the wake word is planned to be spoken by the user).

[0027] The self-voice beamformer can be based on a local electrical input signal or a binaural signal or a signal derived therefrom, depending on the wake word control signal and / or the self-voice control signal. Here, "self-voice beamformer" can be a beamforming signal (e.g., one that will be heard by the user, further analyzed, or transmitted to another device such as the contralateral hearing aid in a binaural hearing aid system).

[0028] Hearing aids can be configured to provide signals from one or more detectors that influence (e.g., control) the value of a wake word control signal or a self-voice control signal at a given point in time. One or more detectors may be located in the hearing aid and / or another device, such as the contralateral hearing aid in a binaural hearing aid system. One or more detectors may include a motion detector (e.g., an accelerometer), a voice activity detector (e.g., another device), or, for example, a self-voice detector in the contralateral hearing aid of another device worn by the user, such as a binaural hearing aid system.

[0029] The hearing aid can be configured to transmit wake word control signals and / or self-voice control signals to another hearing aid (such as the contralateral hearing aid in a binaural hearing aid system), and / or receive wake word control signals or self-voice control signals from another hearing aid (such as the contralateral hearing aid in a binaural hearing aid system).

[0030] Hearing aids may include a binaural processor configured to process signals received from the hearing aid itself and corresponding signals received from another hearing aid (such as the contralateral hearing aid in a binaural hearing aid system). The binaural processor may be configured to compare a wake word (or self-voice) control signal with a wake word (or self-voice) control signal received from the other hearing aid and provide binaural wake word (or self-voice) control signals indicating whether or with what probability a wake word (or user self-voice) was detected.

[0031] "The other hearing aid" can be the contralateral hearing aid in a binaural hearing aid system. The combination between the current values ​​of the local and contralateral wake word or self-voice control signals can be a logical combination (e.g., based on an AND operation in the case of binaural wake word control signals), or it can be based on the multiplication of the current values ​​of the wake word control signals (where they are represented by probabilities), or it can be a weighted combination (e.g., an average) of the corresponding wake word or self-voice control signals.

[0032] The dual-ear processor can be configured to operate independently based on...

[0033] --(e.g., the wake word control signal of the hearing aid on the same side of the body); and

[0034] --Wake word control signal received from another hearing aid (such as the contralateral hearing aid in a binaural hearing aid system)

[0035] - Provides binaural wake word control signals; or

[0036] --(e.g., the self-voice control signal of the hearing aid on the same side of the body); and

[0037] --Self-voice control signals received from another hearing aid (such as the contralateral hearing aid in a binaural hearing aid system).

[0038] - Provides binaural self-voice control signals.

[0039] The binaural processor can be configured to provide binaural wake-up word control signals or binaural self-voice control signals based on the following signals:

[0040] - The electrical input signal of a hearing aid (e.g., on the same side of the body) or a signal originating from it; and

[0041] - Electrical input signals received from or originating from another hearing aid (such as the contralateral hearing aid in a binaural hearing aid system).

[0042] The binaural processor can be configured to control the function of a hearing aid (or a binaural hearing aid system, wherein the hearing aid may be part of the binaural hearing aid system) based on binaural wake word control signals and / or binaural self-voice control signals.

[0043] The binaural processor can be configured to trigger the transmission of data from the hearing aid to an external device or system based on binaural wake word control signals and / or binaural self-voice control signals. The external device or system may include a mobile phone such as a smartphone or a similar communication device such as a tablet or laptop (connected to a communication network). The external device or system may include a separate processing unit, such as a remote control or a user interface. The external device or system can be configured to provide (additional) processing capabilities to, for example, a hearing aid or binaural hearing aid system controlled by the binaural processor via binaural wake word control signals and / or binaural self-voice control signals. The data transmitted to the external device or system may include electrical input signals (from the input unit, such as microphone signals including ambient sounds, such as user self-voice). The data (including self-voice, for example) may be transmitted, for example, to a speech analyzer in the external device (such as the processing unit) or system (such as a network (e.g., the Internet) and associated servers (e.g., the "cloud"), for example, to identify keywords in the voice control interface within the data and, possibly, to respond to commands associated with the aforementioned keywords. The results of the analysis or the results of actions taken after the analysis may be reported (transmitted) to the hearing aid or binaural hearing aid system (or another device or system).

[0044] External devices or systems may include the contralateral hearing aid in a binaural hearing aid system.

[0045] Hearing aids may consist of or include air conduction hearing aids, bone conduction hearing aids, cochlear implant hearing aids, or combinations thereof.

[0046] Hearing aids may be adapted to provide frequency-varying gain and / or level-varying compression and / or frequency shifting (with or without frequency compression) from one or more frequency ranges to one or more other frequency ranges to compensate for a user's hearing loss. Hearing aids may include a signal processor for amplifying the input signal and providing a processed output signal.

[0047] Hearing aids may include an output unit for providing stimulation, perceived by the user as an acoustic signal, based on processed electrical signals. The output unit may include multiple electrodes of a cochlear implant (for CI-type hearing aids), a vibrator of a bone conduction hearing aid, or a speaker (“receiver”) of an air conduction hearing aid. The output unit may include an output converter. The output converter may include a receiver (speaker) for providing the stimulation as an acoustic signal to the user (e.g., in an acoustic (air conduction-based) hearing aid). The output converter may include a vibrator for providing the stimulation as mechanical vibrations of the skull to the user (e.g., in a bone-attached or bone-anchored hearing aid). The output unit may include a synthesis filter bank for converting a time-frequency representation (k, l) (e.g., processed) signal into a time-domain signal. The output unit may include a digital-to-analog converter for providing a (digitized) electrical output signal (e.g., before it is presented to the output converter) as an analog electrical output signal.

[0048] The hearing aid includes an input unit for providing an electrical input signal representing sound. The input unit may include an input transducer, such as a microphone, for converting the input sound into an electrical input signal. The input unit may include a wireless receiver for receiving wireless signals that include or represent sound and providing an electrical input signal representing said sound. The wireless receiver may, for example, be configured to receive electromagnetic signals in the radio frequency range (3 kHz to 300 GHz). The wireless receiver may, for example, be configured to receive electromagnetic signals in the optical frequency range (e.g., infrared light 300 GHz to 430 THz or visible light such as 430 THz to 770 THz).

[0049] Hearing aids may include directional systems such as directional microphone systems, which are adapted to spatially filter sound from the environment to enhance a target sound source among multiple sound sources in the local environment of the hearing aid wearer. The directional system may be adapted to detect (e.g., adaptive detection) the direction from which a specific portion of the microphone signal originates. This can be achieved, for example, in a variety of different ways described in the prior art. In hearing aids, microphone array beamformers are commonly used to spatially attenuate background noise sources. Many beamformer variations can be found in the literature. Minimum variance distortionless response (MVDR) beamformers are widely used in microphone array signal processing. Ideally, an MVDR beamformer keeps the signal from the target direction (also known as the line of sight) unchanged while attenuating sound signals from other directions to the greatest extent possible. A generalized sidelobe canceller (GSC) structure is an equivalent representation of an MVDR beamformer, offering computational and digital representation advantages over a direct implementation of the original form.

[0050] Hearing aids may include antennas and transceiver circuitry (such as a wireless receiver) for wirelessly receiving direct electrical input signals from another device, such as an entertainment device (e.g., a television), a communication device, a wireless microphone, or another hearing aid. The direct electrical input signals may represent or include audio signals and / or control signals and / or information signals. Hearing aids may include demodulation circuitry for demodulating the received direct electrical input signals, thereby providing direct electrical input signals representing audio signals and / or control signals, such as those used to set operating parameters (e.g., volume) and / or processing parameters of the hearing aid. Generally, the wireless link established by the antenna and transceiver circuitry of the hearing aid can be of any type. The wireless link can be established between two devices, such as between an entertainment device (e.g., a TV) and a hearing aid, or between two hearing aids, such as via a third intermediary device (e.g., a processing device, such as a remote control, smartphone, etc.). The wireless link can be used under power-limited conditions, for example, because the hearing aid may constitute or include a portable (typically battery-powered) device. Wireless links can be based on near-field communication, such as inductive links based on inductive coupling between the antenna coils of the transmitter and receiver sections. Wireless links can also be based on far-field electromagnetic radiation. Communication via a wireless link can be arranged according to specific modulation schemes, such as analog modulation schemes like FM (Frequency Modulation), AM (Amplitude Modulation), or PM (Phase Modulation), or digital modulation schemes like ASK (Amplitude Shift Keying) such as On-Key, FSK (Frequency Shift Keying), PSK (Phase Shift Keying) such as MSK (Minimum Frequency Shift Keying), or QAM (Quadrature Amplitude Modulation), etc.

[0051] Communication between the hearing aid and another device can be in baseband (an audio frequency range, such as between 0 and 20 kHz). Preferably, the communication between the hearing aid and the other device is based on a type of modulation at a frequency higher than 100 kHz. Preferably, the frequency used to establish the communication link between the hearing aid and the other device is below 70 GHz, for example, in the range from 50 MHz to 70 GHz, for example, above 300 MHz, for example, in the ISM range above 300 MHz, for example, in the 900 MHz range, or in the 2.4 GHz range, or in the 5.8 GHz range, or in the 60 GHz range (ISM = Industrial, Scientific and Medical, such standardized ranges are defined, for example, by the International Telecommunication Union ITU). The wireless link can be based on standardized or proprietary technologies. The wireless link can be based on Bluetooth technology (such as Bluetooth Low Energy technology).

[0052] Hearing aids can be portable (i.e., configured to be wearable) devices or integral to them, such as devices that include an internal power source, such as a battery, for example a rechargeable battery. Hearing aids can be, for example, lightweight, easy-to-wear devices, such as having a total weight of less than 100g, such as less than 20g.

[0053] A hearing aid may include a forward or signal path between an input unit (such as an input converter, for example a microphone or microphone system and / or a direct electrical input (such as a wireless receiver)) and an output unit such as an output converter. A signal processor may be located in this forward path. The signal processor may be adapted to provide frequency-varying gain according to the user's needs. The hearing aid may include an analysis path having functionalities for analyzing the input signal (such as determining level, modulation, signal type, acoustic feedback estimate, etc.). Some or all of the signal processing of the analysis path and / or signal path may be performed in the frequency domain. Some or all of the signal processing of the analysis path and / or signal path may be performed in the time domain.

[0054] Analog electrical signals representing sound signals can be converted into digital audio signals during analog-to-digital (AD) conversion, where the analog signal is sampled at a predetermined sampling frequency or sampling rate f. s Perform sampling, f s For example, in the range from 8kHz to 48kHz (to suit specific application needs) at discrete time points t n (or n) provides digital samples x n (or x[n]), each audio sample passes through a predetermined N b Bit represents the acoustic signal at t n The value of N at time b For example, in a range from 1 to 48 bits, such as 24 bits. Each audio sample therefore uses N. b Bit quantization (resulting in 2^n voltammetry of audio samples) Nb (Number of different possible values). The numerical sample x has 1 / f s The duration of the time, such as 50 μs, for f s =20kHz. Multiple audio samples can be arranged in time frames. A time frame can include 64 or 128 audio data samples. Other frame lengths can be used depending on the application.

[0055] Hearing aids may include analog-to-digital (AD) converters to digitize analog inputs (e.g., from an input converter such as a microphone) at a predetermined sampling rate such as 20 kHz. Hearing aids may also include digital-to-analog (DA) converters to convert digital signals into analog output signals, for example, for presentation to the user via an output converter.

[0056] Hearing aids, such as input units and / or antenna and transceiver circuitry, include a time-frequency (TF) conversion unit for providing a time-frequency representation of the input signal. The time-frequency representation may include an array or mapping of corresponding complex or real values ​​of the signal in question over a specific time and frequency range. The TF conversion unit may include a filter bank for filtering the (time-varying) input signal and providing multiple (time-varying) output signals, each output signal encompassing a distinctly different frequency range of the input signal. The TF conversion unit may include a Fourier transform unit for converting the time-varying input signal into a (time-varying) signal in the (time-frequency) domain. The hearing aid considers a frequency range starting from the minimum frequency f. min up to the maximum frequency f max The frequency range can include a portion of the typical human hearing range from 20Hz to 20kHz, such as a portion of the range from 20Hz to 12kHz. Typically, the sampling rate f... s Greater than or equal to the maximum frequency f max twice that, i.e., f s ≥2f max The signals from the forward and / or analytical pathways of the hearing aid can be divided into NI (e.g., uniformly wide) frequency bands, where NI is, for example, greater than 5, greater than 10, greater than 50, greater than 100, or greater than 500, and at least some of these bands are processed individually. The hearing aid may be adapted to process the signals from the forward and / or analytical pathways (NP≤NI) on NP different channels. The channels may have consistent or inconsistent widths (e.g., width increases with frequency), and may overlap or not overlap.

[0057] Hearing aids can be configured to operate in different modes, such as a normal mode and one or more specific modes, which may be user-selectable or automatically selectable. Operating modes can be optimized for specific acoustic conditions or environments. Operating modes may include low-power modes, where the hearing aid's functionality is reduced (e.g., for energy saving), such as disabling wireless communication and / or disabling specific features of the hearing aid.

[0058] Hearing aids may include multiple detectors configured to provide status signals relating to the hearing aid's current network environment (such as the current acoustic environment), and / or the current state of the user wearing the hearing aid, and / or the current state or operating mode of the hearing aid. Alternatively or additionally, one or more detectors may form part of an external device that communicates with the hearing aid (e.g., wirelessly). External devices may include, for example, another hearing aid, a remote control, an audio transmission device, a telephone (e.g., a smartphone), external sensors, etc.

[0059] One or more of a plurality of detectors can operate on a full-band signal (time domain). One or more of a plurality of detectors can operate on a band-split signal ((time-)frequency domain), for example, in a finite number of frequency bands.

[0060] Multiple detectors may include level detectors for estimating the current level of the signal in the forward path. Detectors may be configured to determine whether the current level of the signal in the forward path is above or below a given (L-) threshold. Level detectors operate on full-band signals (time domain). Level detectors operate on band-split signals ((time-)frequency domain).

[0061] Hearing aids may include a voice activity detector (VAD) for estimating whether (or with what probability) an input signal (at a specific point in time) includes a voice signal. In this specification, a voice signal may include speech signals from humans. It may also include other forms of vocalization produced by the human speech system (such as singing). The voice activity detector unit may be adapted to classify the user's current acoustic environment as a "voice" or "no-voice" environment. This has the advantage that time periods including electrophonic signals of human vocalizations (such as speech) in the user's environment can be identified and thus separated from time periods that include only (or primarily) other sound sources (such as artificially generated noise). The voice activity detector may be adapted to also detect the user's own voice as "voice." Alternatively, the voice activity detector may be adapted to exclude the user's own voice from the detection of "voice."

[0062] Hearing aids may include a self-voice detector for estimating whether (or with what probability) a particular input sound (such as speech) originates from the user of the hearing aid system. The microphone system of the hearing aid may be adapted to distinguish between the user's own voice and the voice of another person, and possibly between the user's own voice and non-voice sounds.

[0063] Multiple detectors may include motion detectors, such as accelerometers. Motion detectors may be configured to detect movements of a user's facial muscles and / or bones, such as those caused by speech or chewing (e.g., jaw movements), and provide detector signals indicating those movements.

[0064] The hearing aid may include a classification unit configured to classify the current situation based on input signals from (at least partially) a detector and possibly other inputs. In this specification, "current situation" may be defined by one or more of the following:

[0065] a) Physical environment (including the current electromagnetic environment, such as the presence of electromagnetic signals (including audio and / or control signals) that are planned or unplanned to be received by the hearing aid, or other properties of the current environment that are different from acoustics);

[0066] b) Current acoustic conditions (input level, feedback, etc.); and

[0067] c) The user's current mode or state (movement, temperature, cognitive load, etc.);

[0068] d) The current mode or state of the hearing aid and / or another device communicating with the hearing aid (selected program, time elapsed since the last user interaction, etc.).

[0069] The classification unit may be based on or include a neural network, such as a trained neural network.

[0070] Hearing aids may also include other suitable functions for the applications involved, such as compression, noise reduction, and feedback control.

[0071] Hearing aids may include hearing instruments, such as hearing instruments adapted to be located at the user's ear or wholly or partially in the ear canal, such as headphones, headsets, ear protection devices, or combinations thereof.

[0072] application

[0073] On the one hand, applications of the hearing aids described in detail in the "Detailed Description" section and as defined in the claims are provided. Applications can be provided in systems including one or more hearing aids (such as hearing instruments), such as binaural hearing aid systems.

[0074] method

[0075] On one hand, a method for operating a hearing aid configured for wear by a user (such as the contralateral hearing aid in a binaural hearing aid system) is provided. The method may include:

[0076] - Provides an electrical input signal representing sound;

[0077] - Identify a specific wake word based on the electrical input signal or a signal derived therefrom, and provide a wake word control signal indicating whether or with what probability the wake word is detected; and / or

[0078] - Estimate whether or with what probability the electrical input signal or the signal derived therefrom originates from the user's voice and provide a self-voice control signal indicating the aforementioned estimation result.

[0079] The method may further include:

[0080] - A transceiver circuit that establishes a communication link to another hearing aid (such as the contralateral hearing aid in a binaural hearing aid system), thereby enabling the transmission of the electrical input signal or a signal derived therefrom to the other hearing aid and / or the reception of the electrical input signal or a signal derived therefrom from the other hearing aid; and

[0081] - Control the transmission and / or the reception according to the wake-up word control signal and / or according to the self-voice control signal.

[0082] When appropriately replaced by a corresponding process, some or all of the structural features of the apparatus described above, in detail in the "Detailed Description," or as defined in the claims can be combined with the implementation of the method of the present invention, and vice versa. The implementation of the method has the same advantages as the corresponding apparatus.

[0083] Computer-readable media or data carrier

[0084] The present invention further provides a tangible computer-readable medium (data carrier) storing a computer program including program code (instructions), which, when the computer program is run on a data processing system (computer), causes the data processing system to perform (implement) at least some (such as most or all) of the steps of the methods described above, in detail in the "Detailed Description" and as defined in the claims.

[0085] By way of example, but not limitation, the aforementioned tangible computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to execute or store required program code in the form of instructions or data structures and is accessible by a computer. As used herein, disks include compact discs (CDs), laser discs, optical discs, digital multipurpose discs (DVDs), floppy disks, and Blu-ray discs, wherein these disks typically magnetically copy data while simultaneously being optically copied using lasers. Other storage media include those stored in DNA (e.g., in synthetic DNA strands). Combinations of the aforementioned disks should also be included within the scope of computer-readable media. In addition to being stored on tangible media, computer programs may also be transmitted via transmission media such as wired or wireless links or networks such as the Internet and loaded into data processing systems to run at locations other than tangible media.

[0086] Computer program

[0087] In addition, this application provides a computer program (product) including instructions that, when run by a computer, cause the computer to perform the steps of the methods (methods) described above, in detail in the "Detailed Description" section, and as defined in the claims.

[0088] Data processing system

[0089] In one aspect, the present invention further provides a data processing system, including a processor and program code, the program code causing the processor to perform at least some (such as most or all) of the steps of the methods described above, in detail in the "Detailed Description" section, and as defined in the claims.

[0090] Hearing system

[0091] On the other hand, hearing aids and hearing systems including assistive devices are provided, including those described above, described in detail in the "Detailed Description" section, and defined in the claims.

[0092] Hearing systems can be adapted to establish a communication link between hearing aids and assistive devices so that information (such as control and status signals, possibly audio signals) can be exchanged or forwarded from one device to another.

[0093] Auxiliary devices may include remote controls, smartphones, or other portable or wearable electronic devices such as smartwatches.

[0094] The assistive device may consist of or include a remote control for controlling the functions and operation of the hearing aid. The remote control functionality is implemented in a smartphone, which may run an app that enables control of the audio processing device via the smartphone (the hearing aid includes a suitable wireless interface to the smartphone, such as Bluetooth or some other standardized or proprietary solution).

[0095] The assistive device may be constituted by or include an audio gateway device, which is adapted to receive multiple audio signals (e.g., from an entertainment device such as a TV or music player, from a telephone device such as a mobile phone, or from a computer such as a PC) and to select and / or combine appropriate signals (or combinations of signals) from the received audio signals to transmit to the hearing aid.

[0096] Binaural hearing aid system

[0097] On the other hand, a binaural hearing aid system is provided, comprising the first and second hearing aids described in detail in the "Detailed Description" section above.

[0098] Each of the first and second hearing aids in a binaural hearing aid system may include:

[0099] - Input unit, configured to provide an electrical input signal representing sound;

[0100] - A wake-word detector, configured to identify a specific wake-word based on the electrical input signal or a signal derived therefrom, and to provide a wake-word control signal indicating whether or with what probability the wake-word is detected; and / or

[0101] - A self-voice detector configured to estimate whether or with what probability the electrical input signal or a signal derived therefrom originates from a user's voice and to provide a self-voice control signal indicating the aforementioned estimation result.

[0102] Each of the first and second hearing aids may further include transceiver circuitry configured to establish a communication link to the other hearing aid, thereby enabling the transmission of the electrical input signal or a signal derived therefrom to the other hearing aid and / or the reception of the electrical input signal or a signal derived therefrom from the other hearing aid. Each of the first and second hearing aids may further include a preprocessor configured to control the transceiver circuitry according to the wake-word control signal and / or according to the self-voice control signal.

[0103] The transceiver circuitry of the first and second hearing aids can be configured to establish a communication link (as described above) between the first and second hearing aids. This communication link can be based on a standardized or proprietary protocol and can be based on radiated field (e.g., Bluetooth or similar technologies, such as ultra-wideband (UWB) technology) or near-field communication (e.g., an inductive link).

[0104] At least one of the first and second hearing aids may include a binaural processor configured to process signals from the hearing aid involved (the hearing aid on the same side of the body) and corresponding signals received from the other (contralateral) hearing aid in the binaural hearing aid system. The binaural processor may be configured to compare a wake word (or self-voice) control signal and / or a wake word (or self-voice) control signal received from the other hearing aid and provide binaural wake word (and / or self-voice) control signals indicating whether or with what probability a wake word (and / or user self-voice) is detected.

[0105] Therefore, a triggering procedure for enabling binaural processing is provided. First, the local triggering phase enabling binaural communication may be based on a) the detection of a specific keyword (referred to herein as a wake word) and / or b) the detection of the user's self-voice. Second, the binaural triggering phase may enable other functions of the hearing aid or binaural hearing aid system or the transmission of trigger data to external devices, for example, for further processing or for enabling functions of external devices or other devices or systems (e.g., via a network). The binaural phase may, for example, be based on wake word detection and / or self-voice detection, which is based on binaural signals. Binaural wake word detection and / or self-voice detection may, for example, be based on A) the comparison of two wake word control signals and / or the comparison of two self-voice control signals; or B) the corresponding binaural-generated wake word control signals and / or self-voice control signals determined from the electrical input signals of the two hearing aids of the binaural hearing aid system or signals derived therefrom.

[0106] A binaural processor in at least one of the first and second hearing aids may be configured to initiate the transmission of an electrical input signal or a signal derived therefrom to an external processing device when a binaural wake word control signal or self-voice control signal indicates that a wake word and / or user self-voice has been detected or detected with a probability above a certain threshold. The electrical signal of one of the first and second hearing aids may include a wake word (and subsequent audio data) for further processing by an external processing device such as a smartphone or a server such as a cloud-based server. The wake word may also be verified by the external processing device. The external processing device may transmit a confirmation control signal to at least one hearing aid, indicating confirmation or non-confirmation of the wake word detection. At least one hearing aid may be configured to continue or stop the transmission of the electrical input signal based on the confirmation control signal from the external processing device.

[0107] The start and stop of transmission can be based on asymmetric decisions (i.e., start based on a wake word and stop based on self-voice detection (OVD) such as OVD termination, for example, if no self-voice is detected at a certain time, such as >5s or 10s).

[0108] Calibration of the self-voice beamformer in a binaural hearing aid system can begin based on binaurally determined self-voice control signals. Acoustic parameters related to self-voice detection / pickup, such as the steering vector of the local self-voice beamformer (e.g., a self-voice cancellation beamformer) (and appropriate self-voice beamformer weights based thereon), can be updated based on binaural self-voice detection. Local updates can be based, for example, on local detection of the self-voice OV and simultaneous detection of the wake word (e.g., depending on the probability of the aforementioned detection being greater than a minimum threshold). Wake word detection can be based on the local signal or binaurally.

[0109] APP

[0110] On the other hand, the present invention also provides a non-transitory application called an APP. An APP includes executable instructions configured to run on an assistive device to implement a user interface for the hearing aid or hearing system described above, in detail in the "Detailed Description," and as defined in the claims. The APP can be configured to run on a mobile phone, such as a smartphone, or another portable device enabled to communicate with said hearing aid or hearing system.

[0111] definition

[0112] In this specification, "hearing aid" as a hearing instrument refers to a device suitable for improving, enhancing, and / or protecting a user's hearing ability, which achieves this by receiving sound signals from the user's environment, generating corresponding audio signals, possibly modifying the audio signals, and providing the possibly modified audio signals as audible signals to at least one of the user's ears. The audible signals may be provided, for example, as sound signals radiating into the user's outer ear, sound signals transmitted as mechanical vibrations through the bone structures of the user's head and / or through parts of the middle ear to the user's inner ear, and electrical signals transmitted directly or indirectly to the user's cochlear nerve.

[0113] Hearing aids can be configured to be worn in any known manner, such as as a unit worn behind the ear (having a tube that directs radiated sound signals into the ear canal or having an output transducer, such as a speaker, arranged close to or located within the ear canal), as a unit wholly or partially arranged in the auricle and / or ear canal, as a unit connected to a fixed structure implanted in the skull, such as a vibrator, or as a connectable unit that is wholly or partially implanted. Hearing aids may include a single unit or several units that communicate with each other (e.g., acoustically, electrically, or optically). The speaker may be housed within the housing along with other components of the hearing aid, or it may be an external unit (possibly combined with a flexible guiding element such as a dome-shaped element).

[0114] More generally, a hearing aid includes an input transducer for receiving sound signals from the user's environment and providing a corresponding input audio signal, and / or a receiver for receiving the input audio signal electronically (i.e., wired or wirelessly); signal processing circuitry (typically configurable) for processing the input audio signal (such as a signal processor, for example including a configurable (programmable) processor, such as a digital signal processor); and an output unit for providing an audible signal to the user based on the processed audio signal. The signal processor may be adapted to process the input signal in the time domain or in multiple frequency bands. In some hearing aids, amplifiers and / or compressors may constitute the signal processing circuitry. The signal processing circuitry typically includes one or more (integrated or separate) storage elements for executing programs and / or for storing parameters used (or potentially used) in the processing and / or for storing information suitable for the hearing aid's functionality and / or for storing information used, for example, in conjunction with an interface to the user and / or an interface to a programming device (such as processed information, for example, provided by the signal processing circuitry). In some hearing aids, the output unit may include an output transducer, such as a loudspeaker for providing airborne sound signals or a vibrator for providing sound signals propagating through structures or fluids. In some hearing aids, the output unit may include one or more output electrodes for providing electrical signals that electrically stimulate the cochlear nerve (e.g., to a multi-electrode array) (cochlear implant hearing aids).

[0115] In some hearing aids, the vibrator may be adapted to transmit structurally propagated sound signals to the skull transdermally or through the skin. In some hearing aids, the vibrator may be implanted in the middle ear and / or inner ear. In some hearing aids, the vibrator may be adapted to provide structurally propagated sound signals to the middle ear bones and / or cochlea. In some hearing aids, the vibrator may be adapted to provide fluid-propagated sound signals to the cochlear fluid, for example, through the oval window. In some hearing aids, the output electrode may be implanted in the cochlea or on the medial side of the skull and may be adapted to provide electrical signals to the hair cells of the cochlea, one or more auditory nerves, the auditory brainstem, the auditory midbrain, the auditory cortex, and / or other parts of the cerebral cortex.

[0116] Hearing aids can be adapted to the specific needs of users, such as those with hearing loss. The configurable signal processing circuitry of a hearing aid can be adapted to apply frequency- and level-variable compression and amplification of the input signal. Customized frequency- and level-variable gain (amplification or compression) can be determined during the fitting process by the fitting system based on the user's hearing data, such as an audiogram, using basic fitting principles (e.g., speech adaptation). This frequency- and level-variable gain can be reflected, for example, in processing parameters, uploaded to the hearing aid via an interface to a programming device (fitting system), and used by a processing algorithm executed by the hearing aid's configurable signal processing circuitry.

[0117] A “hearing system” refers to a system that includes one or two hearing aids. A “binaural hearing system” refers to a system that includes two hearing aids and is adapted to work together to provide audible signals to both of a user’s ears. A hearing system or a binaural hearing system may also include one or more “assistive devices” that communicate with the hearing aids and influence and / or benefit from the functionality of the hearing aids. The aforementioned assistive devices may include at least one of the following: a remote control, a remote microphone, an audio gateway device, an entertainment device such as a music player, a wireless communication device such as a mobile phone (e.g., a smartphone), or a tablet computer, or another device, such as one that includes a graphical interface. Hearing aids, hearing systems, or binaural hearing systems may be used, for example, to compensate for hearing loss in individuals with hearing impairments, enhance or protect the hearing ability of individuals with normal hearing, and / or transmit electronic audio signals to individuals. Hearing aids or hearing systems may, for example, be part of or interact with broadcasting systems, active ear protection systems, hands-free telephone systems, car audio systems, entertainment systems (such as TV, music playback, or karaoke), teleconferencing systems, classroom amplification systems, etc.

[0118] The present invention can be used, for example, in applications such as binaural hearing aid systems and related applications such as communication systems. Attached Figure Description

[0119] Various aspects of the invention will be best understood from the following detailed description taken in conjunction with the accompanying drawings. For clarity, these drawings are schematic and simplified, showing only the details necessary for understanding the invention while omitting other details. Throughout the specification, the same reference numerals are used for the same or corresponding parts. Features of each aspect may be combined with any or all features of other aspects. These and other aspects, features, and / or technical effects will be apparent from and illustrated in the following figures, wherein:

[0120] Figure 1 A first embodiment of a binaural hearing aid system communicating with an external device according to the present invention is shown;

[0121] Figure 2 A second embodiment of the binaural hearing aid system according to the present invention is shown;

[0122] Figure 3A A first embodiment of a binaural hearing aid system including first and second hearing aids according to the present invention is shown;

[0123] Figure 3B A second embodiment of the binaural hearing aid system including first and second hearing aids according to the present invention is shown;

[0124] Figure 4 The input stage of the hearing aid according to the present invention is shown;

[0125] Figure 5 The self-voice beamformer configuration is shown, where the k-th sub-band Y OV (k) is created as a combination of target cancellation beamformer C2(k) and omnidirectional beamformer C1(k).

[0126] The further applicability of the invention will become apparent from the detailed description given below. However, it should be understood that while the detailed description and specific examples illustrate preferred embodiments of the invention, they are given for illustrative purposes only. Other embodiments of the invention will become apparent to those skilled in the art based on the following detailed description. Detailed Implementation

[0127] The detailed description below, taken in conjunction with the accompanying drawings, serves as a description of various different configurations. This detailed description includes specific details to provide a thorough understanding of several different concepts. However, it will be apparent to those skilled in the art that these concepts can be implemented without these specific details. Several aspects of the apparatus and method are described by various different blocks, functional units, modules, elements, circuits, steps, processes, algorithms, etc. (collectively, “elements”). Depending on the specific application, design constraints, or other reasons, these elements may be implemented using electronic hardware, computer programs, or any combination thereof.

[0128] Electronic hardware may include microelectromechanical systems (MEMS), (e.g., application-specific integrated circuits), microprocessors, microcontrollers, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), gating logic, discrete hardware circuits, printed circuit boards (PCBs) (e.g., flexible PCBs), and other suitable hardware configured to perform the various functions described in this specification, such as sensors for sensing and / or recording the physical properties of the environment, devices, users, etc. Computer programs should be interpreted broadly as instructions, instruction sets, code, code segments, program code, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, programs, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description languages, or other names.

[0129] This application relates to the field of hearing aids, and more particularly to the enabling of binaural communication based on wake word detection in binaural hearing aid systems.

[0130] This invention relates to a binaural hearing aid system in which binaural communication is enabled via a locally detected wake word. This is in Figure 1 The diagram in the middle is shown. Figure 1 A first embodiment of a binaural hearing aid system that communicates with an external device according to the present invention is shown.

[0131] In each hearing instrument (HA1, HA2), a self-voice wake-up word detector (“detection”) operates locally (or a wake-up word detector only (preferably only detecting wake-up words when the user speaks)). If a wake-up word is detected, the audio signal from one instrument (HA2) is transmitted to the other instrument (HA1) to amplify the signal based on the microphone M from both hearing instruments (HA1, HA2).

[0132] Each instrument (HA1, HA2) may have a local wake-word detector (“detection”), which may be based on the instrument’s local microphone M. Since the local wake-word detector relies solely on the instrument’s local microphone, detectors relying on the microphones of both instruments (and additional sensors), such as user self-voice activity detectors, are expected to be more accurate than local detectors because they have access to more information. Furthermore, the combination of binaural microphone signals can initiate further speech enhancement, such as user self-voice signals, because a binaural self-voice enhancement beamformer (using more microphone signals than a local self-voice beamformer) can be obtained from the combination of binaural microphone signals. The combined binaural signals, such as the enhanced self-voice signal, can be transmitted to an external device, such as a smartphone, for further processing (such as keyword detection or further verification of the wake-word).

[0133] A full-band version of the electrical input signal, including ambient sound, can be transmitted to an external device (or between hearing aids). However, only selected portions of the audio signal can be transmitted binaurally. This can be a high-pass filtered, low-pass filtered, or band-pass filtered portion of the full-band signal. It can also be a signal in the frequency domain, such as a signal composed of (multiple) frequency bands (which can be combined into a wider channel, for example, by summing across the frequency band range, if resynthesis of the transmitted signal is not necessary). Similarly, the transmitted signal can be an amplitude spectrum. The transmitted signal can also be a downsampled signal (see, for example, US2019182607A1).

[0134] Similarly, when binaural microphone signals are available, wake-up word detection can be verified based on binaural microphone signals. This is in Figure 2 As shown in the image. Figure 2 A second embodiment of the binaural hearing aid system according to the present invention is shown. Higher accuracy can be achieved through a second verification step based on binaural microphone signals.

[0135] Preferably, a wake-word detector is used to initiate binaural communication, but in principle, other local detectors can also trigger binaural communication. Such detectors can be local self-voice detectors, local on / off detectors, or combinations of different detectors (such as a combination of a local self-voice detector and a local wake-word detector). The detectors can also be based on other or additional sensors such as accelerometers. A "telephone call" detector (such as a detector indicating that the hearing aid has entered "telephone operation mode") can also trigger binaural communication, for example, by initiating the generation of a beamforming signal created from input signals from both hearing instruments (thus providing a better SNR for the beamforming signal).

[0136] Figure 3A An embodiment of a binaural hearing aid system according to the present invention, comprising first and second hearing aids, is shown. Each of the first and second hearing aids (HA1, HA2) includes a wake word detector (WWD), which generates a beamforming signal Y based on a "local" electrical input signal (here based on a beamforming signal Y generated from the first and second electrical input signals (IN1, IN2) provided by the self-voice beamformer (OVBF) focused on the user's mouth and supplied from the input unit IU). OV Provide wake word control signals WW ctr The first and second electrical input signals (IN1, IN2) both originate from the hearing aid itself, for example, from the two input converters located within the hearing aid (i.e., no signal from another hearing aid is involved in the local wake word detection). The wake word control signal WW... ctr It is fed to the transmit controller Tx-CTR, which controls the transmitter Tx. The wake-up word control signal WW ctrThis can be similarly fed to a receiver controller (not shown) for controlling the receiver Rx. The first and second transmitters Tx and the first and second receivers Rx of the first and second hearing aids together form the first and second transceivers for establishing a wireless link WL between the first and second hearing aids, thereby enabling the exchange of signals (including audio signals) therebetween. When the wake word control signal WW... ctr When the wake word detector has detected a wake word for binaural processing (e.g., "binaural mode"), at least one signal (here, electrical input signal IN1) from the hearing aid in question, such as HA1, is transmitted to the contralateral hearing aid, such as HA2 (thus initiating the reception of a corresponding signal (e.g., electrical input signal or its selected frequency range) from the contralateral hearing aid, such as HA2). The signal (here, IN1) transmitted from one hearing aid to the other is passed through a buffer MEM / BUF, for example, to allow the start sequence of interest, such as the wake word, to be included in the transmitted data stream. The transmitted data stream is then forwarded to the transmitter Tx for transmission and received in the receiver Rx of the other hearing aid (here, HA2) and used in the binaural processing unit, here, beamformer BF, see signal Inx fed to the beamformer BF in the forward path of the hearing aid in question. Electrical input signals (IN1, IN2) representing sound, locally generated at the hearing aids (HA1, HA2) in question, along with an electrical input signal (Inx in this case) received from the contralateral hearing aid, are fed to the corresponding beamformer BF. This improves beamforming (e.g., provides improved noise reduction). Each of the first and second hearing devices (HA1, HA2) includes a forward path for processing sound signals from the user's environment. This forward path includes an input unit IU for picking up sound from the user's environment and providing one or more electrical input signals representing that sound. The forward path also includes a beamformer BF. The beamformer provides a spatially filtered signal Y based on the electrical input signal at a given point in time. BF In binaural operation mode (activated via wake word detection), the input signals include electrical input signals (IN1, IN2) from the local hearing aid and one or more electrical input signals Inx from the contralateral hearing aid. In monoaural operation mode, the beamformer BF's input signals consist only of electrical input signals (IN1, IN2) from the local hearing aid. The forward path also includes the hearing aid processor PRO, configured to process the input signal (here, the beamforming signal Y). BF ) and provides the processed output signal (in this case, Y) G For example, to compensate for a user's hearing loss. The processed output signal Y GThe input unit IU is fed to the output unit OU to provide stimuli that can be perceived by the user as sound (e.g., representing the sound picked up by the input unit IU). Depending on the application, the input and output units may include corresponding analog-to-digital converters and digital-to-analog converters, as well as corresponding analysis and synthesis filter banks (so that processing can be performed in the (time-)frequency domain).

[0137] Figure 3B It shows the relationship with Figure 3A Similar to the embodiments of the present invention, this is an embodiment of a binaural hearing aid system including first and second hearing aids, but the wake word detector WWD is replaced by an autovoice detector OVD. The autovoice detector OVD has the same characteristics as the wake word detector ( Figure 3A The same function as WWD is used to initiate the binaural exchange (transmission and / or reception) of signals between the first and second hearing aids (HA1, HA2). Figure 3B In the middle, via self-voice control signal OV ctr .

[0138] In both embodiments, a self-voice beamformer (OVBF) is not required. Generally, the wake-word detector and / or self-voice detector may be based on a single electrical input signal, or they may take two or more electrical input signals representing sound as direct inputs, or they may rely on other (additional) inputs such as detector or sensor inputs.

[0139] Similarly, the binaural processing unit may not be (or may be more than) a beamformer (BF). Generally, the binaural processing unit may include, for example, wake-word detection or more generally, keyword detection, and / or self-voice detection, for example, in a voice control interface, thereby making the corresponding detection more robust. Furthermore, the binaural processing unit may include binaural noise reduction, binaural speech intelligibility estimation, binaural feedback detection, etc.

[0140] Based on robust self-voice detection and calibration self-voice beamformer

[0141] In one aspect of the invention, it is proposed to use more robust binaural detection of self-voice to trigger local calibration of the self-voice beamformer.

[0142] The self-voice beamformer weights can be updated simultaneously with the detection of self-voice. The advantage of updating the self-voice beamformer weights only when the binaural detector detects self-voice is that the beamformer weights are updated only when self-voice is detected with high certainty. This optimizes the hearing aid's power consumption while maintaining the quality of self-voice estimation.

[0143] Figure 4 The input stage of a hearing aid according to the present invention is shown. The hearing aid includes M input converters M1, ..., M2. M(Here, microphones). Each of the M microphones provides an electrical input signal x1,…,x1 representing the sound in the hearing aid environment. M M electrical input signals x1,…,x M The beamformer is fed to a beamformer filter MVDR BF (here, an MVDR beamformer), such as a self-voice beamformer (pointing towards the user's mouth) with the user's self-voice as its target signal. The parameters of the self-voice MVDR beamformer are updated when the self-voice is detected. The output of the MVDR beamformer can be used as the input to the self-voice detector OVD. An MVDR beamformer implemented as a generalized sidelobe canceller can provide different (output) signals, such as a) a target-preserving beamformer T+N containing the target signal T and (potentially reduced) noise signal N, and b) different target-cancelling beamformers N1,…N. M-1 Self-voice can be detected based on a comparison between a target-preserving beamformer and a target-cancelling beamformer. The self-voice detector (OVD) can have different decision thresholds, for example, reflected in multiple different decision modules (Decision 1, Decision 2, two in this case). "Decision 1" is used to determine whether the beamformer parameters should be updated. In this case, self-voice is detected only when the detector is very certain that it has detected self-voice (e.g., when the probability of self-voice presence is greater than a first decision threshold, such as ≥70%-80%). The other decision (from Decision 2) has a lower (second) decision threshold (e.g., ≥50%-60%), thus enabling the detection of more self-voice, but potentially including more false self-voice detections. "Decision 2" can be used, for example, to count the amount of time a person is speaking. "Decision 2" can also be used, for example, to suspend microphone matching system adjustments during self-voice, as self-voice may induce time level differences between microphones in the hearing aid (both use cases are characterized by the fact that the consequences of false detection are small). Alternatively, the self-voice detector (OVD) may also rely on other input data, such as signals from a self-voice detector located in the contralateral ear (see [link to OVD]). Figure 4 "Binaural input" (as mentioned in the text), or other sensory inputs that can pick up the user's own voice, such as accelerometer data (see...). Figure 4 (See "Other sensor inputs (such as accelerometers)").

[0144] The weights of the MVDR beamformer depend on a) the steering vector d, which includes the relative transfer function of the microphone from the desired direction of interest to the hearing aid; and b) an estimate of the noise covariance matrix. Since the noise covariance matrix is ​​updated when the target signal is absent, the steering vector needs to be updated when the target signal is present. The MVDR beamformer can also be implemented as a generalized sidelobe canceller, consisting of a target-preserving beamformer and multiple noise estimates (according to M-1 target-cancelling beamformers, where M is the number of microphones). The beamformer weights of the target-preserving and target-cancelling beamformers also depend on the steering vector d.

[0145] In special cases where the speaker's self-voice is of interest, the steering vector d will contain the relative transfer function between microphones (e.g., the relative transfer function between microphones relative to a reference microphone). The self-voice transfer function will depend on how the hearing device is mounted in the ear, and therefore can vary over time and across individuals. For optimal performance, it is advantageous to calibrate the steering vector according to the current mounting method of the hearing device.

[0146] For the steering vector to be calibrated, the speaker's voice should be present. This calibration can be part of an artificial routine in which the speaker is speaking during a specific calibration procedure, but performing calibration every time the hearing device is installed can be tedious. Preferably, calibration should occur seamlessly, for example, when detecting one's own voice.

[0147] The self-voice detector can depend on the beamformer's calibrated parameters (steering vector d). This dependency is undesirable because the detector relies on the same parameters that are updated based on the detector. Therefore, what is desirable is:

[0148] -If the self-voice detector depends on any of the following other inputs

[0149] --For example, data from an accelerometer capable of picking up vibrations from a user's own voice (see...) Figure 4 (Other sensor inputs (such as accelerometers));

[0150] --An intraocular microphone located in the ear canal, primarily picking up sound from in front of the eardrum in the ear canal (see...) Figure 4 (Other sensor inputs (such as accelerometers));

[0151] --Data from another hearing device located in the opposite ear, such as a self-voice detector based on input from the opposite ear or combined data from both ears (see [link to data]). Figure 4 (Binaural input);

[0152] - Alternatively, the self-voice detector used to update the beamformer weights has a very high threshold, i.e., only self-voice data, where the detector is very certain about its decisions regarding the calibration of beamformer parameters (see...). Figure 4 (Decision 1 in the text);

[0153] - or a combination thereof.

[0154] The scheme based on a robust self-voice detection and calibration self-voice beamformer, as outlined above, can be used independently of other aspects of the invention or in combination with other aspects of the invention.

[0155] Figure 5 The self-voice beamformer configuration is shown, where the k-th sub-band Y OV (k) is created as a combination of target cancellation beamformer C2(k) and omnidirectional beamformer C1(k).

[0156] Figure 5 An embodiment of a beamformer configuration is shown, which can be used to implement a self-voice beamformer OV-BF in a hearing aid (or hearing aid system) according to the invention. Figure 5 A dual-microphone configuration is shown, which is frequently used in hearing devices such as hearing aids (or other sound capture devices) at the current level of technological development. However, these beamformers can be based on more than two microphones, for example, more than three microphones (e.g., as a linear array, or possibly set up in a non-linear configuration). For a given frequency band k, the adaptive beammap Y(k) can be obtained by linearly combining the two beamformers C1(k) and C2(k), see [link to relevant documentation]. Figure 5 The combination unit COMB in the diagram represents different (possibly fixed, or occasionally updated, e.g., based on specific criteria) linear combinations of the first and second electrical input signals X1 and X2 from the first and second microphones M1 and M2, respectively. The first and second electrical input signals X1 and X2 are provided by corresponding analysis filter banks (“filter banks”). Frequency domain signals (downstream of the corresponding analysis filter banks) are indicated by thick arrows, while the time-domain properties of the outputs of the first and second microphones (M1, M2) are indicated by thin arrows. Figure 5 The input module IBF uses beamformer weights w based on input signals X1 and X2. 11 ,w 12 ,w 21 ,w 22 The linear combination of beamformers C1 and C2 provides the beamformers.

[0157] Figure 5This can represent an adaptive beamformer configuration, where the adaptive beamformer Y(k) of the k-th subband is created by subtracting the omnidirectional beamformer C1(k) from the target cancellation beamformer C2(k) calculated using an adaptive factor β(k). The adaptive factor β can be determined, for example, as:

[0158]

[0159] Figure 5 The two beamformers C1 and C2 are, for example, orthogonal. However, this is not actually necessary.

[0160] Acoustic parameters of the self-voice beamformer OV-BF, such as the steering vectors of the two beamformers C1(k) and C2(k) and the beamformer weights w based on them. 11 ,w 12 ,w 21 ,w 22 For example, updates (calibrations) can be made based on criteria. Such criteria may involve self-voice detection and / or wake-word detection, for example, based on local or binaural detection. This criterion may depend, for example, on the probability of the aforementioned self-voice or wake-word detection being greater than a predetermined probability, such as greater than 90% or greater than 95%.

[0161] When appropriately replaced by a corresponding process, the structural features of the apparatus described above, in detail in the "Detailed Description" section, and as defined in the claims can be combined with the steps of the method of the present invention.

[0162] Unless explicitly stated otherwise, the singular forms “a” and “the” used herein include the plural forms (i.e., meaning “at least one”). It should be further understood that the terms “having,” “comprising,” and / or “including” as used in the specification indicate the presence of the stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof. It should be understood that, unless explicitly stated otherwise, when an element is referred to as “connected” or “coupled” to another element, it can be a direct connection or coupling to the other element, or there may be intermediate inserting elements. The term “and / or” as used herein includes any and all combinations of one or more of the listed related items. Unless explicitly stated otherwise, the steps of any method disclosed herein do not necessarily have to be performed in the exact order disclosed.

[0163] It should be understood that references to "an embodiment," "an embodiment," "an aspect," or "may" in this specification mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment of the invention. Furthermore, particular features, structures, or characteristics may be suitably combined in one or more embodiments of the invention. The foregoing description is provided to enable those skilled in the art to implement the various aspects described herein. Various modifications will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects.

[0164] The claims are not limited to the aspects shown herein, but encompass the full scope consistent with the language of the claims, wherein, unless expressly stated, an element referred to in the singular does not mean "one and only one," but rather "one or more." Unless expressly stated, the term "some" means one or more.

[0165] References

[0166] ·US2019182607A1(Oticon)13.06.2019.

Claims

1. A hearing aid configured for wear by a user in a binaural hearing aid system, the hearing aid comprising: - Input unit, configured to provide an electrical input signal representing sound; - A wake word detector configured to identify a specific wake word based on the electrical input signal or a signal derived therefrom and to provide a wake word control signal indicating whether or with what probability the wake word is detected; and / or - A self-voice detector configured to estimate whether or with what probability the electrical input signal or a signal derived therefrom originates from a user's voice and to provide a self-voice control signal indicating the aforementioned estimation result; - A transceiver circuit configured to establish a communication link to another hearing aid in the binaural hearing aid system, thereby enabling the transmission of the electrical input signal or a signal derived therefrom to the other hearing aid and / or the reception of the electrical input signal or a signal derived therefrom from the other hearing aid; - A preprocessor configured to control the transceiver circuitry based on the wake-word control signal or the self-voice control signal; and - A binaural processor configured to process signals received from one hearing aid and corresponding signals received from the other hearing aid in the binaural hearing aid system; In the first local triggering phase, the binaural processor enables binaural communication based on a) the detection of a specific wake word and / or b) the detection of the user's own voice. And in the second binaural triggering phase, data transmission to an external device is triggered based on A) the comparison of two local wake word control signals and / or the comparison of two local self-voice control signals or B) the corresponding binaural wake word control signals and / or self-voice control signals determined from the electrical input signals of the two hearing aids of the binaural hearing aid system or signals derived therefrom.

2. The hearing aid of claim 1, further comprising a buffer configured to store an electrical input signal or a signal derived therefrom for a period of time.

3. The hearing aid according to claim 1, wherein, The detection of wake words relies on the simultaneous detection of the user's own voice.

4. The hearing aid according to claim 1, wherein, The input unit is configured to provide at least two electrical input signals representing the sound.

5. The hearing aid according to claim 4, wherein, At least one of the two electrical input signals is received wirelessly.

6. The hearing aid of claim 4, further comprising a directional system including a self-voice beamformer configured to focus on the user's mouth when the hearing aid is mounted on the user's body.

7. The hearing aid according to claim 6, wherein, The self-voice beamformer is based on local electrical input signals or binaural signals or signals derived from local electrical input signals or binaural signals, depending on the wake-up word control signal and / or the self-voice control signal.

8. The hearing aid of claim 1, configured to provide signals from one or more detectors that affect the values ​​of a wake word control signal and / or a self-voice control signal at a given point in time.

9. The hearing aid of claim 1, configured to transmit a wake word control signal and / or a self-voice control signal to the other hearing aid, and / or receive a wake word control signal and / or a self-voice control signal from the other hearing aid.

10. The hearing aid according to claim 1, wherein, The binaural processor is configured to initiate the transmission of the electrical input signal or a signal derived therefrom to an external processing device when a binaural wake word control signal or a binaural self-voice control signal indicates that the wake word and / or the user's self-voice has been detected.

11. The hearing aid according to claim 1, wherein, The dual-ear processors are configured to be based on -- The wake word control signal of the hearing aid; and -- Wake word control signal received from another hearing aid - Provide binaural wake word control signals; and / or -- Hearing aid self-voice control signals; and -- Self-voice control signals received from another hearing aid - Provides binaural self-voice control signals.

12. The hearing aid according to claim 1, wherein, The binaural processor is configured to provide binaural wake-up word control signals and / or binaural self-voice control signals based on the following signals: - The electrical input signal of the hearing aid or the signal from which it originates; and - Electrical input signals received from or derived from another hearing aid.

13. The hearing aid according to claim 11, wherein, The binaural processor is configured to control the function of the hearing aid based on binaural wake word control signals and / or binaural self-voice control signals.

14. The hearing aid according to claim 1, comprising or including an air conduction hearing aid, a bone conduction hearing aid, a cochlear implant hearing aid, or a combination thereof.

15. A binaural hearing aid system comprising first and second hearing aids according to any one of claims 1-14.

16. A method for operating a hearing aid configured for use by a user in a binaural hearing aid system, the method comprising: - Provides an electrical input signal representing sound; - Identify a specific wake word based on the electrical input signal or a signal derived therefrom and provide a wake word control signal indicating whether or with what probability the wake word is detected; and / or - Estimate whether or with what probability the electrical input signal or the signal derived therefrom originates from the user's voice and provide a self-voice control signal indicating the aforementioned estimation result; - Establish a communication link to another hearing aid in the binaural hearing aid system, thereby enabling the transmission of the electrical input signal or a signal derived therefrom to the other hearing aid and / or the reception of the electrical input signal or a signal derived therefrom from the other hearing aid; - Control the transmission and / or the reception according to the wake-up word control signal or according to the self-voice control signal; - Processing signals from the hearing aid itself and corresponding signals received from the other hearing aid in the binaural hearing aid system; and - Binaural communication is enabled during the first local triggering phase based on a) the detection of a specific wake word and / or b) the detection of the user’s own voice. And in the second binaural triggering phase, data transmission to an external device is triggered based on A) the comparison of two local wake word control signals and / or the comparison of two local self-voice control signals or B) the corresponding binaural wake word control signals and / or self-voice control signals determined from the electrical input signals of the two hearing aids of the binaural hearing aid system or signals derived therefrom.

Images