Leveraging Cochlear Implant-Based Spatial Cues for Location-Guided Target Speaker Extraction in Dynamic Environments

We train a compact deep learning model to extract a moving target speaker in the presence of interfering speech and noise, while retaining the spatial information of the target's location in the extracted speech.

Continue ReadingLeveraging Cochlear Implant-Based Spatial Cues for Location-Guided Target Speaker Extraction in Dynamic Environments

Brain-controlled hearing technology: Setting targets for real-world applications

To assess the requirements of auditory attention decoding (AAD) algorithms for real-world applications of intelligent, brain-controlled hearing technology, we conducted a series of psychoacoustic experiments which quantify the effects of various AAD parameters on user experience for normal hearing and hearing impaired listeners and illustrate that AAD user experience is dependent on the properties of the listening scene as well as the listening context.

Continue ReadingBrain-controlled hearing technology: Setting targets for real-world applications

Effect Of Broadband Gain Frequency Shaping On Horizontal Localization Performance In Individuals With Normal Hearing

The study investigates the effect of channel interaction between the bandpass filters in multi-channel Hearing Aids on sound localization abilities. This was done by implementing broadband frequency shaping at low frequency channels. The study finding indicates that custom-written MATLAB code effectively preserves spatial cues, potentially due to characteristics of the filters used and high-resolution signal processing.

Continue ReadingEffect Of Broadband Gain Frequency Shaping On Horizontal Localization Performance In Individuals With Normal Hearing

Recovering speech intelligibility for cochlear implants in noisy and reverberant situations using multi-microphone deep learning algorithms

Coping with noise and reverberation using multi-channel speech enhancement DNN algorithms for cochlear implants

Continue ReadingRecovering speech intelligibility for cochlear implants in noisy and reverberant situations using multi-microphone deep learning algorithms