A media system and a method of using the media system to accommodate hearing loss of a user, are described. The method includes selecting a personal level-and-frequency dependent audio filter that corresponds to a hearing loss profile of the user. The personal level-and-frequency dependent audio filter can be one of several level-and-frequency-dependent audio filters having respective average gain levels and respective gain contours. An accommodative audio output signal can be generated by applying the personal level-and-frequency dependent audio filter to an audio input signal to enhance the audio input signal based on an input level and an input frequency of the audio input signal. The audio output signal can be played by an audio output device to deliver speech or music that the user perceives clearly, despite the hearing loss of the user. Other aspects are also described and claimed.

Signal to noise ratio, SNR, is determined in an acoustic ambient environment of an against-the-ear audio device worn by a user, wherein the acoustic ambient environment contains speech by a talker. When the SNR is above a threshold, dynamic range control is applied, as positive gain versus input level, to an audio signal from one or more microphones of the audio device. When the SNR is below the threshold, the dynamic range control applies as zero gain or negative gain to the audio signal. Other aspects are also described and claimed.

Various implementations include systems for processing audio signals. In particular implementations, a system includes at least one microphone configured to capture acoustic signals; a wearable hearing assist device configured to amplify captured acoustic signals from the at least one microphone and output amplified audio signals to a transducer; a voice activity detector (VAD) configured to detect voice signals of a user from the captured acoustic signals; and a voice suppression system configured to suppress the voice signals of the user from the amplified audio signals being output to the transducer.

A public address method for live broadcast, in a helmet, of an audio signal conditioned from a plurality of raw audio channels, includes a pre-processing phase including the operations that consist of taking into account characteristics of the auditory perception of the listener; correcting each channel as a function of the characteristics of the auditory perception of the listener; a mixing phase including the production, from the channels thus pre-processed, of a mixed audio signal; a post-processing phase including the operations that consist of: measuring the sound level of a background noise; correcting the mixed audio signal as a function of the sound level of the background noise; a phase of reproducing, in the helmet, the conditioned audio signal resulting from post-processing.

Systems and methods used in a cognitive assistant for detecting human emotions from speech audio signals is described. The system obtains audio signals from an audio receiver and extracts human speech samples. Subsequently, it runs a machine learning based classifier to analyze the human speech signal and classify the emotion observed in it. The user is then notified, based on their preferences, with a summary of the emotion detected. Notifications can also be sent to other systems that have been configured to receive them. Optionally, the system may include the ability to store the speech sample and emotion classification detected for future analysis. The system's machine learning classifier is periodically re-trained based on labelled audio speech data and updated.

An electronic apparatus and method for enhancement of audio for users with a hearing impairment in a shared listening environment is provided. The electronic apparatus receives first audio content from a media source and detects a first user with a hearing disability as a wearer of the personal listening device. The electronic apparatus modifies one or more features of the first audio content based on an audio enhancement profile associated with the detected first user. Thereafter, the electronic apparatus generates second audio content based on the modification and shares the generated second audio content with the personal listening device.

An audio system has an ambient sound enhancement function, in which an against-the-ear audio device having a speaker converts a digitally processed version of an input audio signal into sound. The input audio signal may be amplified where the amplification may be in accordance with a stored hearing profile of the user (personalized ambient sound enhancement.) The audio system also has an acoustic noise cancellation (ANC) function that may be combined in various ways with the sound enhancement function, and that may be responsive to voice activity detection. Other aspects are also described and claimed.

In one aspect, a method for providing a binaural recording to a listener with a head applied in a hearing system, whereas the binaural recording is listened to using a hearing device and whereas the binaural recording consists of a left binaural ear signal intended for a left ear of the listener, and a right binaural ear signal intended for a right ear of the listener, comprises determining a head orientation, determining a source direction of the binaural recording with respect to the head orientation, detecting a change of the head orientation to a new head orientation, adapting the binaural recording considering the source direction of the binaural recording and the new head orientation.

Systems and Methods for assisting the hearing-impaired are described. The methods rely on obtaining audio signals from the ambient environment of a hearing-impaired person. The audio signals are analyzed by a machine learning model that can classify audio signals into audio categories (e.g. Emergency, Animal Sounds) and audio types (e.g. Ambulance Siren, Dog Barking) and notify the user leveraging a mobile or wearable device. The user can configure notification preferences and view historical logs. The machine learning classifier is periodically trained externally based on labelled audio samples. Additional system features include an audio amplification option and a speech to text option for transcribing human speech to text output.

Aspects include identifying each of a plurality of audio sources proximate to a user wearing a headset. The audio sources include a primary audio source and a plurality of background audio sources. Aspects include causing the headset to play a set of audio sources to the user by causing each audio source of the set to be unfiltered by the headset. Aspects include determining an acceptance level of the user. Aspects also include determining a background noise filtering adjustment based on the acceptance level and the set of audio sources being played by the headset to the user. Aspects also include causing the headset to adjust a filtering of one or more of the plurality of background audio sources by the headset based on the background noise filtering adjustment.