Cross-channel amplitude sweeps are crucial to speech intelligibility

Garreth Prendergast, Gary G R Green

    Research output: Contribution to journalArticlepeer-review


    Classical views of speech perception argue that the static and dynamic characteristics of spectral energy peaks (formants) are the acoustic features that underpin phoneme recognition. Here we use representations where the amplitude modulations of sub-band filtered speech are described, precisely, in terms of co-sinusoidal pulses. These pulses are parameterised in terms of their amplitude, duration and position in time across a large number of spectral channels. Coherent sweeps of energy across this parameter space are identified and the local transitions of pulse features across spectral channels are extracted. Synthesised speech based on manipulations of these local amplitude modulation features was used to explore the basis of intelligibility. The results show that removing changes in amplitude across channels has a much greater impact on intelligibility than differences in sweep transition or duration across channels. This finding has severe implications for future experimental design in the fields of psychophysics, electrophysiology and neuroimaging. © 2011 Elsevier Inc.
    Original languageEnglish
    Pages (from-to)406-411
    Number of pages5
    JournalBrain and Language
    Issue number3
    Publication statusPublished - Mar 2012


    • Amplitude modulation
    • Speech intelligibility
    • Vocoded speech


    Dive into the research topics of 'Cross-channel amplitude sweeps are crucial to speech intelligibility'. Together they form a unique fingerprint.

    Cite this