Designing for Speech Practice Systems: How Do User-Controlled Voice Manipulation and Model Speakers Impact Self-Perceptions of Voice?

要旨

Can you speak the way you desire without feeling the pressure to conform to standards of speaking? In this study, we investigated the impact of user-controlled voice manipulation and listening to recordings of model speakers on self-perceptions of voice and speech. Quantitative analysis showed that there was a significant improvement in the perceived confidence of tone by listening to model speakers, but there were no significant improvements due to voice manipulation. Qualitative analysis of interviews revealed that participants responded positively to the visual and auditory feedback provided by the voice manipulation software. The participants also evaluated the quality of model speakers to decide whether or not they wanted to refer to them for speech practice. Based on the results of these analyses, we summarized the design implications for a speech practice system that would allow further investigation of the impact of the system on self-perceptions of speech performance.

著者
Lisa Orii
University of Washington, Seattle, Washington, United States
Nami Ogawa
The University of Tokyo, Tokyo, Japan
Yuji Hatada
The University of Tokyo, Tokyo, Japan
Takuji Narumi
the University of Tokyo, Tokyo, Japan
論文URL

https://dl.acm.org/doi/abs/10.1145/3491102.3502093

動画

会議: CHI 2022

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2022.acm.org/)

セッション: Voice, Conversation and Design

New Orleans Theater A
5 件の発表
2022-05-03 20:00:00
2022-05-03 21:15:00