User interaction patterns and breakdowns in conversing with LLM-powered voice assistants

A Mahmood, J Wang, B Yao, D Wang… - International Journal of …, 2025 - Elsevier
Abstract Conventional Voice Assistants (VAs) rely on traditional language models to discern
user intent and respond to their queries, leading to interactions that often lack a broader …

ChatGPT and me: First-time and experienced users' perceptions of ChatGPT's communicative ability as a dialogue partner

I Gessinger, K Seaborn, M Steeds… - International Journal of …, 2025 - Elsevier
Chatbots like ChatGPT have the potential to produce more natural conversational user
interface interactions. Yet, we currently know little about perceptions of ChatGPT as a …

Cross-cultural validation of partner models for voice user interfaces

K Seaborn, I Gessinger, S Yoshida, BR Cowan… - Proceedings of the 6th …, 2024 - dl.acm.org
Recent research has begun to assess people's perceptions of voice user interfaces (VUIs)
as dialogue partners, termed partner models. Current self-report measures are only …

HASI: A Model for Human-Agent Speech Interaction

N Zargham, V Avanesi, T Mildner… - Proceedings of the 6th …, 2024 - dl.acm.org
In recent years, the widespread adoption of voice user interfaces (VUIs) highlighted the
growing significance of speech interaction in our everyday activities. However, researchers …

[PDF][PDF] The Use of Modifiers and f0 in Remote Referential Communication with Human and Computer Partners

I Gessinger, B Andreeva, BR Cowan - Proc. Interspeech 2024, 2024 - isca-archive.org
The present study investigates referring expressions in a remote interaction context with a
human or computer partner (both simulated). Across these conditions, we compare the effect …