Understanding User Experience in Voice Assistants: The Impact of Functional Suitability and Robust Speech Recognition

Abstract

This study investigates user experience in the context of voice assistants, with a particular focus on the role of speech interaction quality. While prior research has emphasized multiple dimensions of system quality, voice-based interaction introduces unique challenges related to the accurate interpretation of spoken input. To address this, a research model comprising four constructs—Robust Speech Recognition, Functional Suitability, Completeness, and Attitude Toward Use—was developed and empirically tested. Data were collected from 50 voice assistant users and analyzed using partial least squares structural equation modeling (PLS-SEM). The results indicate that robust speech recognition significantly influences functional suitability, completeness, and attitude toward use, highlighting its central role in shaping user evaluations. In contrast, functional suitability did not exhibit a significant effect on attitude toward use, suggesting that users may form attitudes primarily based on immediate interaction quality rather than overall system performance. The findings contribute to the understanding of voice assistants by demonstrating that speech recognition represents a key driver of perceived system effectiveness and user experience. They further suggest that traditional assumptions from technology acceptance research may not fully apply in voice-based interaction contexts. From a practical perspective, the results emphasize the importance of improving speech recognition performance under real-world conditions to enhance both system effectiveness and user satisfaction.

Keywords: Voice Assistants, Robust Speech Recognition, Functional Suitability, Completeness, Attitude Toward Use, User Experience, Pls-Sem

DOI: 10.54941/ahfe1008223