Clinical evaluation of the performance of a blind source separation algorithm combining beamforming and independent component analysis in hearing aid use

[Display omitted] ► We investigated the clinical efficacy of the combination of beamforming and ICA. ► We implemented the algorithm according to the specifications of hearing aids. ► We performed the mean opinion score test for hearing-impaired patients. ► We performed the speech recognition threshold test for hearing-impaired patients. ► The testing algorithm showed the best performance in those clinical tests. There have been several reports on improved blind source separation algorithms that combine beamforming and independent component analysis. However, none of the prior reports verified the clinical efficacy of such combinational algorithms in real hearing aid situations. In the current study, we evaluated the clinical efficacy of such a combinational algorithm using the mean opinion score and speech recognition threshold tests in various types of real-world hearing aid situations involving environmental noise. Parameters of the testing algorithm were adjusted to match the geometric specifications of the real behind-the-ear type hearing aid housing. The study included 15 normal-hearing volunteers and 15 hearing-impaired patients. Experimental results demonstrated that the testing algorithm improved the speech intelligibility of all of the participants in noisy environments, and the clinical efficacy of the combinational algorithm was superior to either the beamforming or independent component analysis algorithms alone. Despite the computational complexity of the testing algorithm, our experimental results and the rapid enhancement of hardware technology indicate that the testing algorithm has the potential to be applied to real hearing aids in the near future, thereby improving the speech intelligibility of hearing-impaired patients in noisy environments.