Evaluation of generalized maximum a posteriori spectral amplitude (GMAPA) speech enhancement algorithm in hearing aids

Abstract

Speech enhancement is an important segment in digital hearing aids, which aims to improve signal-to-noise (SNR) level of received speech signals and thus enhance speech intelligibility for hearing-loss individuals. Recently, we proposed a generalized maximum a posteriori spectral amplitude (GMAPA) speech enhancement algorithm. The proposed GMAPA algorithm has been confirmed effective in a series of objective evaluations and speech recognition tests. In this study, we conduct experiments and observe that GMAPA also provides clear long-term SNR increases in a simulated hearing-aids testing condition. The result demonstrates that GMAPA can be suitably applied in digital hearing aids.