Impact of English Regional Accents on User Acceptance of Voice User Interfaces

A.I. Niculescu, G.M. White, S.S. Lan, R.U. Waloejo, Y. Kawaguchi

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

    7 Citations (Scopus)
    31 Downloads (Pure)


    In this paper we present an experiment addressing a critical issue in Voice User Interface (VUI) design, namely whether the user acceptance can be improved by having recorded voice prompts imitate his/her regional dialect. The claim was tested within a project aiming to develop voice animated virtual help desk assistants for intelligent mobile phone interfaces. 64 subjects native Singaporeans participated in the experiment, ranking speech quality, politeness, dialogue easiness and trustworthiness for two virtual help desk assistants: one speaking with Singaporean accent, the other one speaking with British accent. Contrary to our expectation and despite the identical content of the information presented the British accented assistant was in all categories higher ranked than its Singaporean counterpart. This result is explained by other cultural and psychological biases that dominate the expected effect of common ethnic background. We concluded that subjective preference for a voice accent obviously affects users perception of other system features but design stereotypes like "similarity attracts" are rather context dependent.
    Original languageUndefined
    Title of host publicationProceedings of the 5th Nordic conference on Human-computer interaction, NordiCHI 2008
    Place of PublicationNew York
    PublisherAssociation for Computing Machinery
    Number of pages4
    ISBN (Print)978-1-59593-704-9
    Publication statusPublished - Oct 2008
    Event5th Nordic conference on Human-computer interaction, NordiCHI 2008 - Lund, Sweden
    Duration: 20 Oct 200822 Oct 2008

    Publication series



    Conference5th Nordic conference on Human-computer interaction, NordiCHI 2008
    Other20-22 Oct 2008


    • EWI-14690
    • METIS-255041
    • IR-62636
    • HMI-HF: Human Factors

    Cite this