Speech Perception in Noise with a Harmonic Complex Excited Vocoder

Abstract

A cochlear implant (CI) presents band-pass-filtered acoustic envelope information by modulating current pulse train levels. Similarly, a vocoder presents envelope information by modulating an acoustic carrier. By studying how normal hearing (NH) listeners are able to understand degraded speech signals with a vocoder, the parameters that best simulate electric hearing and factors that might contribute to the NH-CI performance difference may be better understood. A vocoder with harmonic complex carriers (fundamental frequency, f0 = 100 Hz) was used to study the effect of carrier phase dispersion on speech envelopes and intelligibility. The starting phases of the harmonic components were randomly dispersed to varying degrees prior to carrier filtering and modulation. NH listeners were tested on recognition of a closed set of vocoded words in background noise. Two sets of synthesis filters simulated different amounts of current spread in CIs. Results showed that the speech vocoded with carriers whose starting phases were maximally dispersed was the most intelligible. Superior speech understanding may have been a result of the flattening of the dispersed-phase carrier's intrinsic temporal envelopes produced by the large number of interacting components in the high-frequency channels. Cross-correlogram analyses of auditory nerve model simulations confirmed that randomly dispersing the carrier's component starting phases resulted in better neural envelope representation. However, neural metrics extracted from these analyses were not found to accurately predict speech recognition scores for all vocoded speech conditions. It is possible that central speech understanding mechanisms are insensitive to the envelope-fine structure dichotomy exploited by vocoders.

Factors limiting vocal-tract length discrimination in cochlear implant simulations

“…Others have constructed more elaborate vocoders where the current spread was simulated using a simple model of electrical flow in the cochlear fluid (Bingabr et al, 2008;Churchill et al, 2014;Laneau et al, 2006). However, these approaches are limited by the fact that the relationship between the level of current in the cochlea and its specific contribution to loudness is unknown.…”

“…For comparison, Bingabr et al (2008) reviewed the literature for current spread estimates and reported an average value of 2.8 dB/ mm, which corresponds to slopes of about À40 dB/octave according to their calculation. Similarly, Churchill et al (2014) used filters with slopes ranging from À40 to À30 dB/ octave.…”

Simulating the dual-peak excitation pattern produced by bipolar stimulation of a cochlear implant: Effects on speech intelligibility

“…It is worth noting that the filters which led to a plateau of performance in the present study (MP and BP þ 1) had bandwidths in between the medium and broad conditions of Bingabr et al, and that they led to a similar plateau. Recently, several vocoder studies have also used synthesis filter shapes similar to those of Bingabr et al in order to simulate the spread of excitation produced by a CI (Churchill et al, 2014;Stafford et al, 2014). Strydom and Hanekom (2011a) followed a different approach.…”

Acoustic richness modulates the neural networks supporting intelligible speech processing

“…We use the term acoustic richness instead of vocal quality to emphasize that changes to acoustic detail of the speech signal can arise from many sources. Although many behavioral studies have assessed speech perception by systematically manipulating voice quality (Chen and Loizou, 2011, 2010; Churchill et al, 2014; Loizou, 2006; Maryn et al, 2009), relatively little neuroimaging research has investigated the neural consequence of acoustic richness in intelligible speech. Here we examine how acoustic clarity affects the neural processing of intelligible speech.…”