English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Article history: Received: 16 May, 2020 Accepted: 26 June, 2020 Online: 09 August, 2020 Trust is essential in many interdependent human relationships. Trustworthiness is measured via the effectiveness of the relationships involving human perception. The decision to trust others is often made quickly (even at zero acquaintance). Previous research has shown the significance of voice in perceived trustworthiness. However, the listeners’ characteristics were not considered. A system has yet to be produced that can quantitatively predict the degree of trustworthiness in a voice. This research aims to investigate the relationship between trustworthiness and different vocal features while considering the listener’s physical characteristics, towards modelling a computational trust model. This study attempts to predict the degree of trustworthiness in voice by using an Artificial Neural Network (ANN) model. A set of 30 audio clips of white males were obtained, acoustically analyzed and then distributed to a large group of untrained Malaysian respondents who rated their degree of trust in the speakers of each audio clip on a scale of 0 to 10. The ANOVA test showed a statistically significant difference of trust ratings across different types and intensities of emotion, duration of audio clip, average fundamental frequencies, speech rates, articulation rates, average loudness, ethnicity of listener and ages of listener (p <.01). The findings conclude that Malaysians tend to trust white males who talk faster and longer, speak louder, have an f0 between 132.03Hz & 149.52Hz, and show a neutral emotion or rather stoic (arousal<.325). Results suggest that Indians are the most trusting Malaysian ethnic group, followed by Bumiputera from East Malaysia and then followed by Malays. Chinese are the least trusting Malaysian ethnic group. The data was fed into an ANN model to be evaluated, which yielded a perfect percentage accuracy (100%) in degree of trustworthiness 39.70% of the time. Given a threshold of two-point deviation, the ANN had a prediction accuracy of 76.86%.

The Sound of Trust: Towards Modelling Computational Trust using Voice-only Cues at Zero-Acquaintance