A Synthetic Voice for an Assistive Conversational Agent: A Survey to Discover Italian Preferences regarding Synthetic Voice’s Gender and Quality Level

Figure 1

Adolescents, young adults, middle-aged, and seniors’ willingness to interact with high-quality female and male voices and low-quality female and male voices, respectively. The symbol “” above the bars indicates that scores are significantly different. Mean ranges go from 1 (interaction with the systems is very likely) to 5(interaction with the system seems very unlikely). Low scores correspond to high willingness to interact, while high scores correspond to low willingness to interact.