Modulation masking in cochlear implant listeners: envelope versus tonotopic components

Abstract

It is hypothesized that channel-interaction in cochlear implant listeners as measured in a modulation-masking experiment would be influenced by both the tonotopic overlap between masker and signal as well as an interaction between their envelopes. Two experiments were conducted to measure the effects of maskers with noisy and steady-state envelopes on modulation detection by four adult Nucleus-22 cochlear implant listeners, as a function of tonotopic distance between the masker and the signal. In the first experiment, we measured detection thresholds for a 50-Hz modulation in the envelope of a 500-Hz carrier pulse train, in the presence of a masker stimulating regions basal and apical to, as well as overlapping with, the signal. The maskers had two kinds of envelopes: (i) amplitude-modulated by flat-spectrum noise (NAM) and (ii) steady-state (SS(peak)) at a level corresponding to the maximum of the noise fluctuation range. In general, modulation thresholds obtained in the presence of the NAM maskers significantly exceeded thresholds obtained with the corresponding SS(peak) maskers. The ratio p of the threshold modulation depth m obtained with the NAM masker to that obtained with the SS(peak) masker was defined as a conservative index of "envelope masking." In the second experiment, p was determined for two different tasks: the detection of modulation at 20 Hz and steady-state intensity increment detection. Compared to the 50-Hz modulation detection results, the ratio p was reduced for the 20-Hz modulation detection task and even more so for the steady-state increment detection task. It is concluded that channel-interaction can be significantly increased in cochlear implant listeners when dynamic stimuli are used in place of steady-state stimuli.