Oticon A/s

Emina Alickovic

Thomas Lunner

Carina Graversen

Fredrik Gustafsson

Dorothea Wendt

Andrew Segar

Carlos Francisco Mendoza Lara

Patrycja Ksia̧żek

Patrycja Ksiazek

There is provided a speech classification apparatus for hearing devices with electroencephalography, EEG, dependent sound processing, comprising a sound processing unit configured to capturing sound input signals from at least one external microphone and segmenting said captured sound input signals into segmented sound signals, a speech classification unit comprising a speech cepstrum calculation unit configured to calculate a speech cepstrum for each segmented sound signal, an EEG cepstrum calculation unit configured to calculate an EEG cepstrum for an EEG signal of a user's brain, a mapping unit configured to select a predetermined number of coefficients from each calculated sound cepstrum and from the calculated EEG cepstrum, and a correlation unit configured to calculate a correlation value for each captured sound input signal based on a correlation of the predetermined number of selected coefficients from the respective calculated sound cepstrum with the predetermined number of selected coefficients from the calculated EEG cepstrum, wherein an attended speech source is classified based on the obtained correlation values.

Sound processing apparatus utilizing an electroencephalography (EEG) signal

The disclosure presents a hearing device system and a method for adjusting hearing aid configuration, where a user is wearing a hearing device, the method comprising transmitting a first background sound signal to the hearing device, transmitting a first sound pattern to the hearing device, evaluating, via a camera unit, a first pupillary information of a first eye of the user in response to a first sound scene comprising the first background sound signal and the first sound pattern. The evaluating may be repeated providing at least a second pupillary information of the first eye of the user in response to a second sound scene being different from the first sound scene, and where an averaged pupillary information is provided based on an average between the first pupillary information and at least the second pupillary information, and selecting a pupillary fitting model based on the averaged pupillary information, determining a first parameter and at least a second parameter of the pupillary fitting model based on the averaged pupillary information, classifying the averaged pupillary information into either a first category or at least a second category based on the first parameter and the at least second parameter, and wherein the hearing aid configuration is adjusted if the averaged pupillary information is in the first category, and the hearing aid configuration is not adjusted if the averaged pupillary information is in the second category.

Method for adjusting hearing aid configuration based on pupillary information

A hearing assistance system comprises an input unit for providing electric input sound signals u, each representing sound signals Ufrom a multitude nof sound sources S, an electroencephalography (EEG) system for recording activity of the auditory system of the user's brain and providing a multitude nof EEG signals y, and a source selection processing unit receiving said electric input sound signals uand said EEG signals y, and in dependence thereof configured to provide a source selection signal &#x15c;indicative of the sound source Sthat the user currently pays attention to using a selective algorithm that determines a sparse model to select the most relevant EEG electrodes and time intervals based on minimizing a cost function measuring the correlation between the individual sound sources and the EEG signals, and to determine the source selection signal &#x15c;based on the cost functions obtained for said multitude of sound sources.

Hearing assistance system comprising an EEG-recording and analysis system

Growing community of inventors

Smørum, Denmark

Emina Alickovic