A method and device for detecting acoustic feedback events with an artificial neural network in an in-ear earbud audio system that allows, by user interaction, playback of a recorded and processed signal from an environment-recording microphone by an in-ear speaker that faces or is at least acoustically coupled with the ear canal such that sound played by the speaker enters the ear canal. The audio system employs an acoustic seal that acoustically separates the speaker from the microphone, but due to external factors, the acoustical separation may not be adequate, thereby forming acoustic feedback paths. The neural network facilitates a binary classification of the time-wise segmented microphone signal, which is used to stop playback by the in-ear speaker if a feedback event is detected to protect the hearing of the user. Detection of a feedback event triggers an audible or wireless notification to be delivered to the user.

The invention discloses a method for realizing hearing aid function based on Bluetooth headset chip and a Bluetooth headset: the common Bluetooth headset chip software of Bluetooth headset is upgraded to a specific Bluetooth headset chip with hearing aid function by a hearing loss correction software; a hearing aid algorithm module is embedded into the development kit of the common Bluetooth headset chip in the form of software library by the hearing loss correction software, so that the common Bluetooth headset chip has the hearing aid function only by software upgrade; after being processed by the hearing aid algorithm module, a sound signal is output to a hearing-impaired user, so that the hearing-impaired user can use the common Bluetooth headset to realize the hearing aid function. For the Bluetooth headset, a special hearing aid chip does not need to be installed or any change does not need to be made to the headset hardwares, and the function and price can meet the needs of hearing-impaired users, so that the hearing impaired users can enjoy great convenience from such a Bluetooth headset without buying expensive special hearing aid.

A mobile terminal according to an embodiment of the present disclosure includes a microphone configured to obtain and provide an input sound source, an earphone connection module configured to support connection and communication with an earphone, and a hearing aid application configured to set a sound source fitting condition corresponding to a user hearing threshold, convert the input sound source obtained through the microphone into a corrected sound source according to the sound source fitting condition, and then output the corrected sound source to the earphone.

In a method of fitting of a hearing device having an input transducer and an output transducer, the method includes executing a fitting application on a graphical user interface of an external device in communication with the hearing device, detecting by measuring reactions of the user to picked-up sound, performing acoustic feedback measurements as a background process without a user's involvement, assessing the probability of a correct physical fit based on the position of the inserted hearing device, assessing feedback risk based on the correct physical fit assessment and the acoustic feedback measurements, and fine tuning fitting parameter of the hearing device based on the result of at least one of the detected reactions of the user, acoustic feedback measurements and saved, within the fitting application, personal information of the user.

An adaptive feedback canceller of an ear-wearable device has an adaptive foreground filter that inserts a feedback cancellation signal into a digitized input signal to produce an error signal. An instability detector of the device is configured to extract wo or more features from the error signal. The instability detector has a machine learning module that determines instability in the error signal based on the two or more features. The instability module changes the adaptive foreground filter in response to determining the instability. The change causes the adaptive foreground filter to have a faster adaptation to perturbations in the error signal compared to a previously used step size.

In one example, a method includes determining, by one or more processors of a hearing aid programmer, values for one or more properties of a first hearing aid; obtaining, by the one or more processors, based on feedback cancelation configurations of a plurality of other hearing aids having the same values for the one or more properties as the first hearing aid, a predicted initial feedback cancelation configuration for the first hearing aid; and programming, by the one or more processors, the first hearing aid based on the predicted initial feedback cancelation configuration.

A hearing device is disclosed, comprising a main microphone, M auxiliary microphones, a transform circuit, a processor, a memory and a post-processing circuit. The transform circuit transforms first sample values in current frames of a main audio signal and M auxiliary audio signals from the microphones into a main and M auxiliary spectral representations. The memory includes instructions to be executed by the processor to perform operations comprising: performing ANC over the first sample values using an end-to-end neural network to generate second sample values; and, performing audio signal processing over the main and the M auxiliary spectral representations using the end-to-end neural network to generate a compensation mask. The post-processing circuit modifies the main spectral representation with the compensation mask to generate a compensated spectral representation, and generates an output audio signal according to the second sample values and the compensated spectral representation.

A personalized sound management system for an acoustic space includes at least one transducer, a data communication system, one or more processors operatively coupled to the data communication system and the at least one transducer, and a medium coupled to the one or more processors. The processors access a database of sonic signatures and display a plurality of personalized sound management applications that perform at least one or more tasks among identifying a sonic signature, calculating a sound pressure level, storing metadata related to a sonic signature, monitoring sound pressure level dosage levels, switching to an ear canal microphone in a noisy environment, recording a user’s voice, storing the user’s voice in a memory of an earpiece device, or storing the user’s voice in a memory of a server system, or converting received text received in texts or emails to voice using text to speech conversion. Other embodiments are disclosed.

A method of estimating a real-ear-to-coupler-difference (RECD) in a hearing is provided. The hearing aid comprises an input transducer; an output transducer; and an ITE-part configured to define a residual volume when mounted in an ear canal of a user. The method comprises providing an earpiece configured to fit tightly to walls of an ear canal of the user and to provide said residual volume; that the earpiece comprises at least one ventilation channel or opening; a sound outlet allowing sound from said output transducer to be played into said residual volume; characteristics of the at least one ventilation channel or opening; a frequency dependent feedback path estimate from said output transducer to said input transducer through said ventilation channel or opening; and estimating a low-frequency and high frequency RECD values in dependence said feedback path estimate; and determining estimated frequency dependent RECD values in dependence of said estimated low-frequency RECD value, and said estimated high-frequency RECD value.

A method for detecting and mitigating parasitic oscillation in a headphone equipped with an active noise reduction (ANR) system. A fundamental frequency of a microphone signal is determined from a microphone of the ANR system and an amplitude of the determined fundamental frequency is compared to a threshold level to determine parasitic oscillation. If parasitic oscillation is determined, then the microphone signal is altered to mitigate the parasitic oscillation.