Hearing Aid-controlled Beamformer for Binaural Speech Enhancement Using a Model-based Approach

Abstract

The understanding of speech from a particular speaker in the presence of other interfering speakers can be severely degraded for a hearing impaired person. Beamforming techniques have been proven to be effective to improve the speech understanding in such scenarios. However, the number of microphones in a hearing aid (HA) is limited due to the space and power constraints present in the HA. In this paper, we propose to use an external device e.g., a microphone array, that can communicate with the HA to overcome this limitation. We propose a method to control this external device based on the look direction of the HA user. We show, by means of simulations, the robustness of the proposed method at very low SNRs in a reverberant scenario. Moreover, we have also conducted experiments that show the benefit of using this framework for binaural and monaural enhancement.

Comparison of Binaural RTF-Vector-Based Direction of Arrival Estimation Methods Exploiting an External Microphone

“…In such an acoustic sensor network, jointly processing all available microphones, i.e. the hearing aid microphones in conjunction with the external microphones, has been shown to be beneficial for, e.g., noise reduction [2][3][4][5][6] as well as for direction of arrival (DOA) estimation [7][8][9].…”

“…Large research effort has already been dedicated to DOA estimation [10][11][12][13][14], in particular also for binaural hearing aid applications [7][8][9][15][16][17]. In [7] we proposed a DOA estimation method for a binaural hearing aid setup, which exploits an external microphone at an unknown position.…”

“…The DOA of the target speaker relative to the binaural hearing aid setup is then estimated as the direction for which the spatial spectrum is maximized. Contrary to [8], in [7] the external microphone does not need to be in the vicinity of the target speaker in order to capture a nearly clean speech reference, while contrary to [9] no pre-trained representation of clean speech spectral envelopes is required for DOA estimation.…”

Distributed Microphone Speech Enhancement based on Deep Learning

“…Real-world environments are always contain stationary and/or timevarying noises that are received together with speech signals by recording devices. The received noises inevitably degrade the performance of multi-channel (MC)-based human-human and humanmachine interfaces, and this issue has attracted significant attention over the years [1,2,3]. In recent decades, numerous MC speechenhancement (SE) approaches have been proposed to alleviate the effect of noise and improve the quality and intelligibility [4,5,6,7] of received speech signals.…”