A comparison of machine learning algorithms and human listeners in the identification of phonemic contrasts

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    To elucidate the processes by which automatic speech recognition (ASR) architectures reach transcription decisions, our study compared human and ASR responses to stimuli with manipulated cues for stop manner (burst, silence, and vocalic onset) and voicing (voice onset time, aspiration amplitude, and vocalic onset). Fourteen participants and two ASR systems completed a forced-response identification task. Results indicated that the cues were of perceptual significance for human participants, and though weighted differently, significant predictors of ASR output. This demonstrated that ASR systems may be relying on the same key acoustic information as do human listeners for phonemic classification.
    Original languageEnglish
    Title of host publicationProceedings of the Eighteenth Australasian International Conference on Speech Science and Technology
    Place of PublicationCanberra, Australia
    PublisherThe Australasian Speech Science and Technology Association, Inc.
    Pages41-45
    Publication statusPublished - 2022
    EventEighteenth Australasian International Conference on Speech Science and Technology - Canberra, Australia, Australia
    Duration: 1 Jan 2022 → …

    Conference

    ConferenceEighteenth Australasian International Conference on Speech Science and Technology
    Country/TerritoryAustralia
    Period1/01/22 → …
    Other13-16 December 2022

    Fingerprint

    Dive into the research topics of 'A comparison of machine learning algorithms and human listeners in the identification of phonemic contrasts'. Together they form a unique fingerprint.

    Cite this