Real-Time Speech Processing Algorithms for Smartphone Based Hearing Aid Applications

Abstract

Signal processing algorithms are extensively used in hearing aid applications to improve the quality and intelligibility of speech. The hearing aid device (HAD) signal processing pipeline consists of several key modules that help to improve the perception for hearing-impaired listeners. In this dissertation, novel speech processing algorithms have been proposed that can be used in smartphone-based hearing aid (HA) setup. Every chapter of this dissertation concentrates on the individual modules of the signal processing pipeline in HADs. The first algorithm is developed for speech enhancement (SE) to suppress the background noise. A voice activity detector (VAD) to classify the incoming signal into speech or noise is developed. Signal enhancement techniques like blind source separation and dereverberation are developed. The algorithms are developed using conventional and supervised learning techniques. Objective and subjective evaluations are conducted for each of the proposed techniques to show substantial improvements in speech quality and intelligibility.