Abstract

Technological advances witnessed in cochlear implant (CI) devices, most CI users can now achieve reliable speech intelligibility in controlled quiet scenarios, particularly in predictable conversations. Environmental distortions, such as reverberation and additive noise, on the other hand, are known to significantly degrade speech intelligibility. This paper validates a novel approach to predict speech intelligibility for Cochlear Implant users (CIs) in reverberant environments. First, energy thresholding is proposed to reduce the variability caused by the differences in modulation spectral representations for different phonemes and speakers, as well as speech enhancement algorithm artifacts. Second, a narrower range of Fourier domain based echo Filter is employed to reduce fundamental frequency effects. Results indicate substantial improvements in intelligibility over that attained by human listeners with unprocessed stimuli. The findings from this study show that algorithm can estimate reliably the SNR and can improve speech intelligibility.