On subband adaptive modeling of compression hearing aids

The current generation of digital hearing aids perform amplitude compression in multiple channels. The resulting non-linear processing has the potential to create distortion components which reduce their effectiveness and user satisfaction. The performance of these devices is typically evaluated using subjective test procedures. While these approaches are preferred, they are time consuming. Objective electroacoustic measurements of speech quality are attractive but require effective modeling of these devices. Subband adaptive modeling architectures have been found to facilitate these measurements. It is shown that optimal modeling occurs only when the number of channels in the subband adaptive model matches the number of hearing aid channels. A technique based on combined sinusoidal and broadband noise excitation is then exploited to identify the number of channels in the hearing aid to be used in the optimal subband adaptive model.