Acoustic feedback suppression in binaural hearing aids

The hearing loss and acoustic feedback signal in the binaural hearing aids may annoy users, make speech reorganization difficult, and affect the sound quality. This paper presents a new method for acoustic feedback suppression in binaural hearing aids, based on the combination of binaural information and blind source separation. This method can enhance sound from the specific direction of the user and cancels acoustic feedback signal so that the user can hear clearly.
In the proposed method, the binaural information (interaural time differences (ITDs) and interaural level differences (ILDs)) was generated using computational auditory scene analysis (CASA). In addition, we used underdetermined blind source separation (BSS) for the automatic classification of the time-frequency (T-F) units of the speech mixture spectrogram. The system performance was evaluated using 32 acoustic English speech mixtures. The sound quality was assessed using 19 normal-hearing listeners of both genders.
The system achieved a good acoustic feedback suppression performance by giving a higher signal to noise ratio and 18.07 dB on average for the signal-to-feedback ratio. In addition, the sound after processing had a high quality according to the subjective assessment.
Our system allowed the user to increase the gain of the hearing aid without affecting the sound quality.