University of Twente Student Theses
A Cross-Cultural Study on the Perceived Urgency of Semantic-Free Utterances for a Hospital Delivery Robot
Narwane, Ishitaa (2024) A Cross-Cultural Study on the Perceived Urgency of Semantic-Free Utterances for a Hospital Delivery Robot.
|
PDF
32MB |
| Abstract: | With social robots becoming ubiquitous, like smartphones, and their presence in sectors like healthcare increasing, effective communication strategies for such public environments with diverse users are essential. Natural language is common in Human-Robot Interaction (HRI), which however faces limitations, especially in cross-cultural contexts due to inconsistency, complexity, and bias in training data. Semantic-free utterances (SFUs), which are vocalizations devoid of semantic content, emerge as a promising solution. SFUs, used by media droids like R2D2, WALL-E, and Minions, convey emotion and intent without language barriers, and their ease of implementation provides designers with greater control compared to NLP. This study examines the potential of SFUs for signalling urgency in a hospital delivery robot, focusing on Indian and Dutch national cultural backgrounds. Using Gibberish Speech (GS) and Non-Linguistic Utterances (NLUs) from the EMOGIB and BEST databases, which convey anger, participants' perceptions of these SFUs were assessed for urgency through an online survey in two parts. Part 1 (Pre-Study) narrowed down the SFUs and investigated the correlation between anger and dominance, and Part 2 (Main-Study) assessed selected SFUs for urgency. Results showed no significant main effects for culture or database alone, but a significant interaction between them. Qualitative feedback indicated that pitch, tone, and loudness influence urgency perception across cultures. A correlation between Dominance and Urgency was also found. These findings support SFUs' effectiveness in conveying urgency amongst two contrasting cultures, with implications for designing communication strategies for service robots in multicultural environments. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Programme: | Interaction Technology MSc (60030) |
| Link to this item: | https://purl.utwente.nl/essays/103244 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page