@inproceedings{10.1145/3772318.3791747,

title = {Beyond Words: Measuring User Experience through Speech Analysis in Voice User Interfaces},

author = {Yong Ma and Xuesong Zhang and Xuedong Zhang and Natalia Bartłomiejczyk and Seungwoo Je and Adrian Holzer and Morten Fjeld and Andreas Martin Butz},

url = {https://doi.org/10.1145/3772318.3791747},

doi = {10.1145/3772318.3791747},

isbn = {9798400722783},

year  = {2026},

date = {2026-01-01},

booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

series = {CHI '26},

abstract = {Voice assistants (VAs) are typically evaluated through task performance metrics and self-report questionnaires, but people’s voices themselves carry rich paralinguistic cues that reveal affect, effort, and interaction breakdowns. We present a within-subjects study (N=49) that systematically compared three VA personas across three usage scenarios to investigate whether speech-derived audio features can serve as a proxy for user experience (UX). Participants’ speech was analyzed for temporal, spectral, and linguistic markers, alongside standardized UX measures, brief mood and stress ratings, and a post-study questionnaire. We found correlations between specific speech features and self-reported satisfaction and experience. Furthermore, a machine learning model trained on speech features achieved promising accuracy in classifying UX levels, indicating that this might be a reasonable alternative to self-report instruments. Our findings establish speech as a viable, real-time signal for implicitly measuring UX and point toward adaptive VUIs that respond dynamically to emotional and usability-related vocal cues.},

keywords = {Voice user interfaces; user experience; speech analytics; paralinguistics; implicit UX sensing.},

pubstate = {published},

tppubtype = {inproceedings}

}